{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/gelu","entry":"gelu","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":308,"n_papers_ran":265,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":114,"n_samples_ran":74,"n_samples_fingerprinted":70,"n_places":367,"n_places_pointer_only":97,"by_status":{"ran_honours":42,"ran_violates":0,"ran_draft_wrong":14,"ran_fixture":5,"ran":13,"unverified":40},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2609.02204","paper":"/paper/arxiv-2609-02204","title":"TAME: Temporal-Aware Mixture-of-Experts for Text-Video Retrieval","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"sejong-rcv/TAME","path":"modules/until_module.py","file_url":"https://github.com/sejong-rcv/TAME/blob/HEAD/modules/until_module.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"40e9fee2e0b7e278","mcp_get_code":{"code_sha256":"40e9fee2e0b7e278"}},{"arxiv_id":"2609.01136","paper":"/paper/arxiv-2609-01136","title":"Different Changes Require Different Reasoning: Change-Type-Specialized Experts for Robust Change Captioning","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"VisualAIKHU/MEDIC","path":"models/CCR_expert.py","file_url":"https://github.com/VisualAIKHU/MEDIC/blob/HEAD/models/CCR_expert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a3abf3fe697fabd0","mcp_get_code":{"code_sha256":"a3abf3fe697fabd0"}},{"arxiv_id":"2608.19529","paper":"/paper/arxiv-2608-19529","title":"When Machines Speak: A Unified Generative Framework for Integrating Machine-Native Symbols into Pretrained Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"RUCAIBox/CIKM2020-S3Rec","path":"modules.py","file_url":"https://github.com/RUCAIBox/CIKM2020-S3Rec/blob/HEAD/modules.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fbd63a1fd03f517c","mcp_get_code":{"code_sha256":"fbd63a1fd03f517c"}},{"arxiv_id":"2606.18703","paper":"/paper/arxiv-2606-18703","title":"Contextualizing Biological Language Models across Modalities via Logit-Space Contrastive Alignment","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"facebookresearch/esm","path":"esm/modules.py","file_url":"https://github.com/facebookresearch/esm/blob/HEAD/esm/modules.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2e7bd6c4ccd1ed68","mcp_get_code":{"code_sha256":"2e7bd6c4ccd1ed68"}},{"arxiv_id":"2605.11189","paper":"/paper/arxiv-2605-11189","title":"Deep Learning for Protein Complex Prediction and Design by","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"zw2x/glinter","path":"glinter/esm_embed/modules.py","file_url":"https://github.com/zw2x/glinter/blob/HEAD/glinter/esm_embed/modules.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2e7bd6c4ccd1ed68","mcp_get_code":{"code_sha256":"2e7bd6c4ccd1ed68"}},{"arxiv_id":"2604.27550","paper":"/paper/arxiv-2604-27550","title":"APPSI-139: A Parallel Corpus of English Application Privacy Policy Summarization and Interpretation","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"EnlightenedAI/APPSI-139","path":"Infer/pytorch_pretrained/modeling.py","file_url":"https://github.com/EnlightenedAI/APPSI-139/blob/HEAD/Infer/pytorch_pretrained/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2604.14114","paper":"/paper/arxiv-2604-14114","title":"ID and Graph View Contrastive Learning with Multi-View Attention Fusion for Sequential Recommendation","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"sword-Lz/MMCrec","path":"src/models/sequential/MMCrec.py","file_url":"https://github.com/sword-Lz/MMCrec/blob/HEAD/src/models/sequential/MMCrec.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"eb13ab048d49bf28","mcp_get_code":{"code_sha256":"eb13ab048d49bf28"}},{"arxiv_id":"2604.04756","paper":"/paper/arxiv-2604-04756","title":"Darkness Visible: Reading the Exception Handler of a Language Model","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"pbalogh/transparent-gpt2","path":"src/null_model_controls.py","file_url":"https://github.com/pbalogh/transparent-gpt2/blob/HEAD/src/null_model_controls.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d8a18b42531fafae","mcp_get_code":{"code_sha256":"d8a18b42531fafae"}},{"arxiv_id":"2603.25752","paper":"/paper/arxiv-2603-25752","title":"Relational graph-driven differential denoising and diffusion attention fusion for multimodal conversation emotion recognition","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"liuying2023912/ReDiFu","path":"model.py","file_url":"https://github.com/liuying2023912/ReDiFu/blob/HEAD/model.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"52548f442af51038","mcp_get_code":{"code_sha256":"52548f442af51038"}},{"arxiv_id":"2603.05969","paper":"/paper/arxiv-2603-05969","title":"Imagine How To Change: Explicit Procedure Modeling for Change Captioning","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"BlueberryOreo/ProCap","path":"src/rtransformer/model.py","file_url":"https://github.com/BlueberryOreo/ProCap/blob/HEAD/src/rtransformer/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"69e3a274f98c15af","mcp_get_code":{"code_sha256":"69e3a274f98c15af"}},{"arxiv_id":"2602.16687","paper":"/paper/arxiv-2602-16687","title":"Scaling Open Discrete Audio Foundation Models with Interleaved Semantic, Acoustic, and Text Tokens","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"BytedanceSpeech/seed-tts-eval","path":"thirdparty/UniSpeech/WavLM/modules.py","file_url":"https://github.com/BytedanceSpeech/seed-tts-eval/blob/HEAD/thirdparty/UniSpeech/WavLM/modules.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f30ebf4e48b7e2d7","mcp_get_code":{"code_sha256":"f30ebf4e48b7e2d7"}},{"arxiv_id":"2602.15537","paper":"/paper/arxiv-2602-15537","title":"ZeroSyl: Simple Zero-Resource Syllable Tokenization for Spoken Language Modeling","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"nicolvisser/ZeroSyl","path":"zerosyl/zerosyl.py","file_url":"https://github.com/nicolvisser/ZeroSyl/blob/HEAD/zerosyl/zerosyl.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f30ebf4e48b7e2d7","mcp_get_code":{"code_sha256":"f30ebf4e48b7e2d7"}},{"arxiv_id":"2602.07063","paper":"/paper/arxiv-2602-07063","title":"Video-based Music Generation","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"serkansulun/video-emotion","path":"src/beats/modules.py","file_url":"https://github.com/serkansulun/video-emotion/blob/HEAD/src/beats/modules.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f30ebf4e48b7e2d7","mcp_get_code":{"code_sha256":"f30ebf4e48b7e2d7"}},{"arxiv_id":"2602.02286","paper":"/paper/arxiv-2602-02286","title":"DFKI-Speech System for WildSpoof Challenge: A robust framework for SASV In-the-Wild","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"IDRnD/redimnet","path":"redimnet/layers/attention.py","file_url":"https://github.com/IDRnD/redimnet/blob/HEAD/redimnet/layers/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"88607e3bd7f9b5be","mcp_get_code":{"code_sha256":"88607e3bd7f9b5be"}},{"arxiv_id":"2601.10926","paper":"/paper/arxiv-2601-10926","title":"Selecting Language Models for Social Science: Start Small, Start Open, and Validate Preprint XX(X):1-22 ©The Author(s) 2026","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"openai/gpt-2","path":"src/model.py","file_url":"https://github.com/openai/gpt-2/blob/HEAD/src/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"876d63d7567762a1","mcp_get_code":{"code_sha256":"876d63d7567762a1"}},{"arxiv_id":"2601.03549","paper":"/paper/arxiv-2601-03549","title":"FEA-SLT: A Gloss-Free End-to-End Framework for Facial-Expression-Aware Sign Language Translation","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"google-research/bleurt","path":"bleurt/lib/modeling.py","file_url":"https://github.com/google-research/bleurt/blob/HEAD/bleurt/lib/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"51d3bc0cfa6415a3","mcp_get_code":{"code_sha256":"51d3bc0cfa6415a3"}},{"arxiv_id":"2601.00328","paper":"/paper/arxiv-2601-00328","title":"Joint Geometry-Appearance Human Reconstruction in a Unified Latent Space via Bridge Diffusion","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"haiantyz/JGA-LBD","path":"JGA-LBD/DDBM/ddbm/unet3d.py","file_url":"https://github.com/haiantyz/JGA-LBD/blob/HEAD/JGA-LBD/DDBM/ddbm/unet3d.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f51cf2cbd3e598d8","mcp_get_code":{"code_sha256":"f51cf2cbd3e598d8"}},{"arxiv_id":"2509.01337","paper":"/paper/arxiv-2509-01337","title":"LLM-Guided Semantic Relational Reasoning for Multimodal Intent Recognition","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"thuiar/LGSRR","path":"backbones/SubNets/FeatureNets.py","file_url":"https://github.com/thuiar/LGSRR/blob/HEAD/backbones/SubNets/FeatureNets.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"50e1ffed03f484ec","mcp_get_code":{"code_sha256":"50e1ffed03f484ec"}},{"arxiv_id":"2507.02843","paper":null,"title":"arXiv:2507.02843","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"rpryzant/causal-bert-pytorch","path":"CausalBert.py","file_url":"https://github.com/rpryzant/causal-bert-pytorch/blob/HEAD/CausalBert.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3b96e7aecc63b5f0","mcp_get_code":{"code_sha256":"3b96e7aecc63b5f0"}},{"arxiv_id":"2506.13366","paper":"/paper/enhancing-goal-oriented-proactive-dialogue","title":"Enhancing Goal-oriented Proactive Dialogue Systems via Consistency Reflection and Correction","date":"2025-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"2502.07707","paper":"/paper/prvql-progressive-knowledge-guided-refinement","title":"PRVQL: Progressive Knowledge-guided Refinement for Robust Egocentric Visual Query Localization","date":"2025-02-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fb-reps/PRVQL","path":"bert_model/bert_module.py","file_url":"https://github.com/fb-reps/PRVQL/blob/HEAD/bert_model/bert_module.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"69e3a274f98c15af","mcp_get_code":{"code_sha256":"69e3a274f98c15af"}},{"arxiv_id":"2412.11959","paper":"/paper/gramian-multimodal-representation-learning","title":"Gramian Multimodal Representation Learning and Alignment","date":"2024-12-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ispamm/GRAM","path":"model/general_module.py","file_url":"https://github.com/ispamm/GRAM/blob/HEAD/model/general_module.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2410.22949","paper":"/paper/mutaplm-protein-language-modeling-for","title":"MutaPLM: Protein Language Modeling for Mutation Explanation and Engineering","date":"2024-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PharMolix/MutaPLM","path":"model/modeling_esm.py","file_url":"https://github.com/PharMolix/MutaPLM/blob/HEAD/model/modeling_esm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d59e1fd0eedc33c3","mcp_get_code":{"code_sha256":"d59e1fd0eedc33c3"}},{"arxiv_id":"2410.18373","paper":"/paper/ugotme-an-embodied-system-for-affective-human","title":"UGotMe: An Embodied System for Affective Human-Robot Interaction","date":null,"month_inferred_from_arxiv_id":"2024-10","title_source":"archive","repo":"lipzh5/amecavle","path":"models/modules/transformer.py","file_url":"https://github.com/lipzh5/amecavle/blob/HEAD/models/modules/transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"40c1552a4336406a","mcp_get_code":{"code_sha256":"40c1552a4336406a"}},{"arxiv_id":"2410.15500","paper":"/paper/anonymising-elderly-and-pathological-speech","title":"Anonymising Elderly and Pathological Speech: Voice Conversion Using DDSP and Query-by-Example","date":"2024-10-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"suhitaghosh10/ddsp-qbe","path":"wavlm/modules.py","file_url":"https://github.com/suhitaghosh10/ddsp-qbe/blob/HEAD/wavlm/modules.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f30ebf4e48b7e2d7","mcp_get_code":{"code_sha256":"f30ebf4e48b7e2d7"}},{"arxiv_id":"2410.02832","paper":"/paper/flipattack-jailbreak-llms-via-flipping","title":"FlipAttack: Jailbreak LLMs via Flipping","date":"2024-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yueliu1999/elcrec","path":"src/modules.py","file_url":"https://github.com/yueliu1999/elcrec/blob/HEAD/src/modules.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"56a9ab06b860b180","mcp_get_code":{"code_sha256":"56a9ab06b860b180"}},{"arxiv_id":"2409.17808","paper":"/paper/generative-modeling-of-molecular-dynamics","title":"Generative Modeling of Molecular Dynamics Trajectories","date":"2024-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bjing2016/mdgen","path":"mdgen/model/layers.py","file_url":"https://github.com/bjing2016/mdgen/blob/HEAD/mdgen/model/layers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"595e8ad97db860f3","mcp_get_code":{"code_sha256":"595e8ad97db860f3"}},{"arxiv_id":"2408.11363","paper":"/paper/proteingpt-multimodal-llm-for-protein","title":"ProteinGPT: Multimodal LLM for Protein Property Prediction and Structure Understanding","date":"2024-08-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ProteinGPT/ProteinGPT","path":"src/esm/modules.py","file_url":"https://github.com/ProteinGPT/ProteinGPT/blob/HEAD/src/esm/modules.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2e7bd6c4ccd1ed68","mcp_get_code":{"code_sha256":"2e7bd6c4ccd1ed68"}},{"arxiv_id":"2407.12366","paper":"/paper/navgpt-2-unleashing-navigational-reasoning","title":"NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models","date":"2024-07-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GengzeZhou/NavGPT-2","path":"map_nav_src/models/NavGPT_model.py","file_url":"https://github.com/GengzeZhou/NavGPT-2/blob/HEAD/map_nav_src/models/NavGPT_model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2407.04752","paper":"/paper/spikellm-scaling-up-spiking-neural-network-to","title":"SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spiking","date":"2024-07-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xingrun-xing/spikelm","path":"spikeLM-BERT/spike_bert.py","file_url":"https://github.com/xingrun-xing/spikelm/blob/HEAD/spikeLM-BERT/spike_bert.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"067fa79dc5c16d05","mcp_get_code":{"code_sha256":"067fa79dc5c16d05"}},{"arxiv_id":"2406.16282","paper":"/paper/reducing-fine-tuning-memory-overhead-by","title":"Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation","date":"2024-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yyyyychen/lowmemorybp","path":"search_act/sa_search.py","file_url":"https://github.com/yyyyychen/lowmemorybp/blob/HEAD/search_act/sa_search.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7fcedfc60ac103d5","mcp_get_code":{"code_sha256":"7fcedfc60ac103d5"}},{"arxiv_id":"2406.16282","paper":"/paper/reducing-fine-tuning-memory-overhead-by","title":"Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation","date":"2024-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yyyyychen/LowMemoryBP","path":"search_act/plot_results.py","file_url":"https://github.com/yyyyychen/LowMemoryBP/blob/HEAD/search_act/plot_results.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"92d332f9f6d8d916","mcp_get_code":{"code_sha256":"92d332f9f6d8d916"}},{"arxiv_id":"2406.16282","paper":"/paper/reducing-fine-tuning-memory-overhead-by","title":"Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation","date":"2024-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yyyyychen/LowMemoryBP","path":"search_act/sa_search.py","file_url":"https://github.com/yyyyychen/LowMemoryBP/blob/HEAD/search_act/sa_search.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"55935d62b8500881","mcp_get_code":{"code_sha256":"55935d62b8500881"}},{"arxiv_id":"2406.10960","paper":"/paper/escot-towards-interpretable-emotional-support","title":"ESCoT: Towards Interpretable Emotional Support Dialogue Systems","date":"2024-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-coai/Emotional-Support-Conversation","path":"codes/src/transformers/activations_tf.py","file_url":"https://github.com/thu-coai/Emotional-Support-Conversation/blob/HEAD/codes/src/transformers/activations_tf.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"4158ac7257c02b11","mcp_get_code":{"code_sha256":"4158ac7257c02b11"}},{"arxiv_id":"2406.10391","paper":"/paper/beacon-benchmark-for-comprehensive-rna-tasks","title":"BEACON: Benchmark for Comprehensive RNA Tasks and Language Models","date":"2024-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"terry-r123/rnabenchmark","path":"model/rnalm/modeling_rnalm.py","file_url":"https://github.com/terry-r123/rnabenchmark/blob/HEAD/model/rnalm/modeling_rnalm.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"82a647d4d28fc62b","mcp_get_code":{"code_sha256":"82a647d4d28fc62b"}},{"arxiv_id":"2406.02900","paper":"/paper/scaling-laws-for-reward-model-1","title":"Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms","date":"2024-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openai/summarize-from-feedback","path":"summarize_from_feedback/models/ops.py","file_url":"https://github.com/openai/summarize-from-feedback/blob/HEAD/summarize_from_feedback/models/ops.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"2405.20666","paper":"/paper/masa-motion-aware-masked-autoencoder-with","title":"MASA: Motion-aware Masked Autoencoder with Semantic Alignment for Sign Language Recognition","date":"2024-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sakura2233565548/masa","path":"moco/GCN_Transformer_mask.py","file_url":"https://github.com/sakura2233565548/masa/blob/HEAD/moco/GCN_Transformer_mask.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6f324d970195cc1d","mcp_get_code":{"code_sha256":"6f324d970195cc1d"}},{"arxiv_id":"2404.19563","paper":"/paper/repeval-effective-text-evaluation-with-llm","title":"RepEval: Effective Text Evaluation with LLM Representation","date":"2024-04-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shikib/usr","path":"transformers/modeling_gpt2.py","file_url":"https://github.com/shikib/usr/blob/HEAD/transformers/modeling_gpt2.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"2404.19563","paper":"/paper/repeval-effective-text-evaluation-with-llm","title":"RepEval: Effective Text Evaluation with LLM Representation","date":"2024-04-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shikib/usr","path":"transformers/modeling_bert.py","file_url":"https://github.com/shikib/usr/blob/HEAD/transformers/modeling_bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"211753ba29188d4e","mcp_get_code":{"code_sha256":"211753ba29188d4e"}},{"arxiv_id":"2404.19563","paper":"/paper/repeval-effective-text-evaluation-with-llm","title":"RepEval: Effective Text Evaluation with LLM Representation","date":"2024-04-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shikib/usr","path":"transformers/modeling_distilbert.py","file_url":"https://github.com/shikib/usr/blob/HEAD/transformers/modeling_distilbert.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"69c6d14de8190cfb","mcp_get_code":{"code_sha256":"69c6d14de8190cfb"}},{"arxiv_id":"2404.17169","paper":"/paper/fairgt-a-fairness-aware-graph-transformer","title":"FairGT: A Fairness-aware Graph Transformer","date":"2024-04-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yushuowiki/fairgt","path":"model.py","file_url":"https://github.com/yushuowiki/fairgt/blob/HEAD/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"be4a5b4fd2623b72","mcp_get_code":{"code_sha256":"be4a5b4fd2623b72"}},{"arxiv_id":"2404.15766","paper":"/paper/unifying-bayesian-flow-networks-and-diffusion","title":"Unifying Bayesian Flow Networks and Diffusion Models through Stochastic Differential Equations","date":"2024-04-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ML-GSAI/BFN-Solver","path":"networks/transformer.py","file_url":"https://github.com/ML-GSAI/BFN-Solver/blob/HEAD/networks/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b17ebf2b2ef1cb60","mcp_get_code":{"code_sha256":"b17ebf2b2ef1cb60"}},{"arxiv_id":"2404.07839","paper":"/paper/recurrentgemma-moving-past-transformers-for","title":"RecurrentGemma: Moving Past Transformers for Efficient Open Language Models","date":"2024-04-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-deepmind/recurrentgemma","path":"recurrentgemma/torch/modules.py","file_url":"https://github.com/google-deepmind/recurrentgemma/blob/HEAD/recurrentgemma/torch/modules.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"dd656979e56353bf","mcp_get_code":{"code_sha256":"dd656979e56353bf"}},{"arxiv_id":"2404.02845","paper":"/paper/cross-modal-conditioned-reconstruction-for","title":"Cross-Modal Conditioned Reconstruction for Language-guided Medical Image Segmentation","date":"2024-04-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shashankhuang/reclmis","path":"nets/until_module.py","file_url":"https://github.com/shashankhuang/reclmis/blob/HEAD/nets/until_module.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"50e1ffed03f484ec","mcp_get_code":{"code_sha256":"50e1ffed03f484ec"}},{"arxiv_id":"2404.00491","paper":"/paper/denoising-monte-carlo-renders-with-diffusion","title":"Denoising Monte Carlo Renders with Diffusion Models","date":"2024-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vibe007/Denoising_MC_Renders_Diffusion","path":"deepfloyd_if/model/nn.py","file_url":"https://github.com/vibe007/Denoising_MC_Renders_Diffusion/blob/HEAD/deepfloyd_if/model/nn.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f51cf2cbd3e598d8","mcp_get_code":{"code_sha256":"f51cf2cbd3e598d8"}},{"arxiv_id":"2403.16030","paper":"/paper/vcr-graphormer-a-mini-batch-graph-transformer","title":"VCR-Graphormer: A Mini-batch Graph Transformer via Virtual Connections","date":"2024-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dongqifu/vcr-graphormer","path":"model.py","file_url":"https://github.com/dongqifu/vcr-graphormer/blob/HEAD/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"be4a5b4fd2623b72","mcp_get_code":{"code_sha256":"be4a5b4fd2623b72"}},{"arxiv_id":"2403.15520","paper":"/paper/gtc-gnn-transformer-co-contrastive-learning","title":"GTC: GNN-Transformer Co-contrastive Learning for Self-supervised Heterogeneous Graph Representation","date":"2024-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"phd-lanyu/gtc","path":"code/module/transformer_model.py","file_url":"https://github.com/phd-lanyu/gtc/blob/HEAD/code/module/transformer_model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"be4a5b4fd2623b72","mcp_get_code":{"code_sha256":"be4a5b4fd2623b72"}},{"arxiv_id":"2403.12388","paper":"/paper/interpretable-user-satisfaction-estimation","title":"Interpretable User Satisfaction Estimation for Conversational Systems with Large Language Models","date":"2024-03-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dengyang17/USDA","path":"usda-clu/transformer.py","file_url":"https://github.com/dengyang17/USDA/blob/HEAD/usda-clu/transformer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"2403.07376","paper":"/paper/navcot-boosting-llm-based-vision-and-language","title":"NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning","date":"2024-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"expectorlin/navcot","path":"finetune_src/models/vilmodel_cmt.py","file_url":"https://github.com/expectorlin/navcot/blob/HEAD/finetune_src/models/vilmodel_cmt.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2403.06963","paper":"/paper/the-pitfalls-of-next-token-prediction","title":"The pitfalls of next-token prediction","date":"2024-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gregorbachmann/next-token-failures","path":"models/lib.py","file_url":"https://github.com/gregorbachmann/next-token-failures/blob/HEAD/models/lib.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"272ef5f104a11d59","mcp_get_code":{"code_sha256":"272ef5f104a11d59"}},{"arxiv_id":"2402.06320","paper":"/paper/particle-denoising-diffusion-sampler","title":"Particle Denoising Diffusion Sampler","date":"2024-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"angusphillips/particle_denoising_diffusion_sampler","path":"pdds/nn_models/mlp.py","file_url":"https://github.com/angusphillips/particle_denoising_diffusion_sampler/blob/HEAD/pdds/nn_models/mlp.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cfe15be8aba147f4","mcp_get_code":{"code_sha256":"cfe15be8aba147f4"}},{"arxiv_id":"2402.02347","paper":"/paper/riemannian-preconditioned-lora-for-fine","title":"Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models","date":"2024-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"2402.01729","paper":"/paper/contextualization-distillation-from-large","title":"Contextualization Distillation from Large Language Model for Knowledge Graph Completion","date":"2024-01-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"David-Li0406/Contextulization-Distillation","path":"kg-bert/model_distillation.py","file_url":"https://github.com/David-Li0406/Contextulization-Distillation/blob/HEAD/kg-bert/model_distillation.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2401.10487","paper":"/paper/generative-dense-retrieval-memory-can-be-a","title":"Generative Dense Retrieval: Memory Can Be a Burden","date":"2024-01-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ypw0102/gdr","path":"GDR_model/transformers/activations_tf.py","file_url":"https://github.com/ypw0102/gdr/blob/HEAD/GDR_model/transformers/activations_tf.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"14a1c81ea568d152","mcp_get_code":{"code_sha256":"14a1c81ea568d152"}},{"arxiv_id":"2401.06633","paper":"/paper/ada-retrieval-an-adaptive-multi-round","title":"Ada-Retrieval: An Adaptive Multi-Round Retrieval Paradigm for Sequential Recommendations","date":"2024-01-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ll0ruc/Ada-Retrieval","path":"src/model/sequential/fmlprec.py","file_url":"https://github.com/ll0ruc/Ada-Retrieval/blob/HEAD/src/model/sequential/fmlprec.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"eb13ab048d49bf28","mcp_get_code":{"code_sha256":"eb13ab048d49bf28"}},{"arxiv_id":"2401.00793","paper":"/paper/secformer-towards-fast-and-accurate-privacy","title":"SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC","date":"2024-01-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2312.15820","paper":"/paper/webvln-vision-and-language-navigation-on","title":"WebVLN: Vision-and-Language Navigation on Websites","date":"2023-12-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"webvln/webvln","path":"r2r_src/vlnbert/vlnbert_PREVALENT.py","file_url":"https://github.com/webvln/webvln/blob/HEAD/r2r_src/vlnbert/vlnbert_PREVALENT.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2312.09059","paper":"/paper/auto-prox-training-free-vision-transformer","title":"Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery","date":"2023-12-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lilujunai/auto-prox-aaai24","path":"pycls/models/auto/autoformer_subnet.py","file_url":"https://github.com/lilujunai/auto-prox-aaai24/blob/HEAD/pycls/models/auto/autoformer_subnet.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"08a5be1ffa0676e3","mcp_get_code":{"code_sha256":"08a5be1ffa0676e3"}},{"arxiv_id":"2312.02010","paper":"/paper/towards-learning-a-generalist-model-for","title":"Towards Learning a Generalist Model for Embodied Navigation","date":"2023-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zd11024/NaviLLM","path":"models/vln_bert.py","file_url":"https://github.com/zd11024/NaviLLM/blob/HEAD/models/vln_bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c2f0705ed8e6f7e6","mcp_get_code":{"code_sha256":"c2f0705ed8e6f7e6"}},{"arxiv_id":"2311.02816","paper":"/paper/apgl4sr-a-generic-framework-with-adaptive-and","title":"APGL4SR: A Generic Framework with Adaptive and Personalized Global Collaborative Information in Sequential Recommendation","date":"2023-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"graph-team/apgl4sr","path":"src/modules.py","file_url":"https://github.com/graph-team/apgl4sr/blob/HEAD/src/modules.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fbd63a1fd03f517c","mcp_get_code":{"code_sha256":"fbd63a1fd03f517c"}},{"arxiv_id":"2310.20138","paper":"/paper/depn-detecting-and-editing-privacy-neurons-in","title":"DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models","date":"2023-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"flamewei123/DEPN","path":"src/custom_bert.py","file_url":"https://github.com/flamewei123/DEPN/blob/HEAD/src/custom_bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"56a9ab06b860b180","mcp_get_code":{"code_sha256":"56a9ab06b860b180"}},{"arxiv_id":"2310.18339","paper":"/paper/moelora-an-moe-based-parameter-efficient-fine","title":"When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applications","date":"2023-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"applied-machine-learning-lab/moelora-peft","path":"resources/modeling_chatglm.py","file_url":"https://github.com/applied-machine-learning-lab/moelora-peft/blob/HEAD/resources/modeling_chatglm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"43c9688838aff8b2","mcp_get_code":{"code_sha256":"43c9688838aff8b2"}},{"arxiv_id":"2310.16898","paper":"/paper/mcuformer-deploying-vision-tranformers-on-1","title":"MCUFormer: Deploying Vision Transformers on Microcontrollers with Limited Memory","date":"2023-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liangyn22/mcuformer","path":"model/supernet_transformer.py","file_url":"https://github.com/liangyn22/mcuformer/blob/HEAD/model/supernet_transformer.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"08a5be1ffa0676e3","mcp_get_code":{"code_sha256":"08a5be1ffa0676e3"}},{"arxiv_id":"2310.16579","paper":"/paper/wsdms-debunk-fake-news-via-weakly-supervised","title":"WSDMS: Debunk Fake News via Weakly Supervised Detection of Misinforming Sentences with Contextualized Social Wisdom","date":"2023-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HKBUNLP/WSDMS-EMNLP2023","path":"bert_model.py","file_url":"https://github.com/HKBUNLP/WSDMS-EMNLP2023/blob/HEAD/bert_model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2310.14318","paper":"/paper/intent-contrastive-learning-with-cross","title":"Intent Contrastive Learning with Cross Subsequences for Sequential Recommendation","date":"2023-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qinhsiu/icsrec","path":"src/modules.py","file_url":"https://github.com/qinhsiu/icsrec/blob/HEAD/src/modules.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fbd63a1fd03f517c","mcp_get_code":{"code_sha256":"fbd63a1fd03f517c"}},{"arxiv_id":"2310.14079","paper":"/paper/to-copy-or-not-to-copy-that-is-a-critical","title":"To Copy, or not to Copy; That is a Critical Issue of the Output Softmax Layer in Neural Sequential Recommenders","date":"2023-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iesl/softmax_cpr_recommend","path":"recbole/model/sequential_recommender/sasrec.py","file_url":"https://github.com/iesl/softmax_cpr_recommend/blob/HEAD/recbole/model/sequential_recommender/sasrec.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d9dcfb510a5e2690","mcp_get_code":{"code_sha256":"d9dcfb510a5e2690"}},{"arxiv_id":"2310.12864","paper":"/paper/the-locality-and-symmetry-of-positional","title":"The Locality and Symmetry of Positional Encodings","date":"2023-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tigerchen52/locality_symmetry","path":"experiments/model/attenuated.py","file_url":"https://github.com/tigerchen52/locality_symmetry/blob/HEAD/experiments/model/attenuated.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"CC0-1.0","inline_ok":true,"code_sha256_prefix":"62e7409a816626ac","mcp_get_code":{"code_sha256":"62e7409a816626ac"}},{"arxiv_id":"2310.06259","paper":"/paper/cross-modal-cognitive-consensus-guided-audio","title":"Cross-modal Cognitive Consensus guided Audio-Visual Segmentation","date":"2023-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhaofengshi/avs-c3n","path":"C3N_beats/avs_scripts/avs_ms3/beats/modules.py","file_url":"https://github.com/zhaofengshi/avs-c3n/blob/HEAD/C3N_beats/avs_scripts/avs_ms3/beats/modules.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f30ebf4e48b7e2d7","mcp_get_code":{"code_sha256":"f30ebf4e48b7e2d7"}},{"arxiv_id":"2310.03502","paper":"/paper/kandinsky-an-improved-text-to-image-synthesis","title":"Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion","date":"2023-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deep-floyd/IF","path":"deepfloyd_if/model/nn.py","file_url":"https://github.com/deep-floyd/IF/blob/HEAD/deepfloyd_if/model/nn.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f51cf2cbd3e598d8","mcp_get_code":{"code_sha256":"f51cf2cbd3e598d8"}},{"arxiv_id":"2310.02556","paper":"/paper/nola-networks-as-linear-combination-of-low","title":"NOLA: Compressing LoRA using Linear Combination of Random Basis","date":"2023-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"UCDvision/NOLA","path":"gpt/examples/NLG/src/model_nola.py","file_url":"https://github.com/UCDvision/NOLA/blob/HEAD/gpt/examples/NLG/src/model_nola.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"2310.03032","paper":"/paper/graph-enhanced-optimizers-for-structure-aware","title":"Graph-enhanced Optimizers for Structure-aware Recommendation Embedding Evolution","date":"2023-09-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MTandHJ/SEvo","path":"STOSA/modules.py","file_url":"https://github.com/MTandHJ/SEvo/blob/HEAD/STOSA/modules.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e4b72241dc704f7f","mcp_get_code":{"code_sha256":"e4b72241dc704f7f"}},{"arxiv_id":"2309.17352","paper":"/paper/improving-audio-captioning-models-with-fine","title":"Improving Audio Captioning Models with Fine-grained Audio Features, Text Embedding Supervision, and LLM Mix-up Augmentation","date":null,"month_inferred_from_arxiv_id":"2023-09","title_source":"archive","repo":"slseanwu/beats-conformer-bart-audio-captioner","path":"model/modules.py","file_url":"https://github.com/slseanwu/beats-conformer-bart-audio-captioner/blob/HEAD/model/modules.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f30ebf4e48b7e2d7","mcp_get_code":{"code_sha256":"f30ebf4e48b7e2d7"}},{"arxiv_id":"2309.17093","paper":"/paper/prototype-based-aleatoric-uncertainty-1","title":"Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval","date":"2023-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leolee99/PAU","path":"modules/until_module.py","file_url":"https://github.com/leolee99/PAU/blob/HEAD/modules/until_module.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"50e1ffed03f484ec","mcp_get_code":{"code_sha256":"50e1ffed03f484ec"}},{"arxiv_id":"2309.16429","paper":"/paper/diverse-and-aligned-audio-to-video-generation","title":"Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation","date":"2023-09-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"guyyariv/TempoTokens","path":"modules/beats/modules.py","file_url":"https://github.com/guyyariv/TempoTokens/blob/HEAD/modules/beats/modules.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f30ebf4e48b7e2d7","mcp_get_code":{"code_sha256":"f30ebf4e48b7e2d7"}},{"arxiv_id":"2309.06363","paper":"/paper/2309-06363","title":"Learning to Predict Concept Ordering for Common Sense Generation","date":"2023-09-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tianhuizhang/concept_ordering","path":"bert-gen/s2s_ft/modeling_decoding.py","file_url":"https://github.com/tianhuizhang/concept_ordering/blob/HEAD/bert-gen/s2s_ft/modeling_decoding.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"40e9fee2e0b7e278","mcp_get_code":{"code_sha256":"40e9fee2e0b7e278"}},{"arxiv_id":"2308.13853","paper":"/paper/beyond-one-to-one-rethinking-the-referring","title":"Beyond One-to-One: Rethinking the Referring Image Segmentation","date":"2023-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"toggle1995/RIS-DMMI","path":"bert/modeling.py","file_url":"https://github.com/toggle1995/RIS-DMMI/blob/HEAD/bert/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d08f324f950148de","mcp_get_code":{"code_sha256":"d08f324f950148de"}},{"arxiv_id":"2308.10873","paper":"/paper/spikingbert-distilling-bert-to-train-spiking","title":"SpikingBERT: Distilling BERT to Train Spiking Language Models Using Implicit Differentiation","date":"2023-08-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"neurocomplab-psu/spikingbert","path":"transformer/modeling.py","file_url":"https://github.com/neurocomplab-psu/spikingbert/blob/HEAD/transformer/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2308.07037","paper":"/paper/bayesian-flow-networks","title":"Bayesian Flow Networks","date":"2023-08-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nnaisense/bayesian-flow-networks","path":"networks/transformer.py","file_url":"https://github.com/nnaisense/bayesian-flow-networks/blob/HEAD/networks/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b17ebf2b2ef1cb60","mcp_get_code":{"code_sha256":"b17ebf2b2ef1cb60"}},{"arxiv_id":"2308.07026","paper":"/paper/advclip-downstream-agnostic-adversarial","title":"AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning","date":"2023-08-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cgcl-codes/advclip","path":"utils/model.py","file_url":"https://github.com/cgcl-codes/advclip/blob/HEAD/utils/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c2f0705ed8e6f7e6","mcp_get_code":{"code_sha256":"c2f0705ed8e6f7e6"}},{"arxiv_id":"2308.04758","paper":"/paper/bird-s-eye-view-scene-graph-for-vision","title":"Bird's-Eye-View Scene Graph for Vision-Language Navigation","date":"2023-08-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"defaultrui/bev-scene-graph","path":"bsg_vln/map_nav_src/models/vilmodel_bev.py","file_url":"https://github.com/defaultrui/bev-scene-graph/blob/HEAD/bsg_vln/map_nav_src/models/vilmodel_bev.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2307.13528","paper":"/paper/factool-factuality-detection-in-generative-ai","title":"FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios","date":"2023-07-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"freedomintelligence/sdak","path":"code/src/modeling_chatglm_med.py","file_url":"https://github.com/freedomintelligence/sdak/blob/HEAD/code/src/modeling_chatglm_med.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"43c9688838aff8b2","mcp_get_code":{"code_sha256":"43c9688838aff8b2"}},{"arxiv_id":"2307.11984","paper":"/paper/learning-vision-and-language-navigation-from","title":"Learning Vision-and-Language Navigation from YouTube Videos","date":"2023-07-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jeremylinky/youtube-vln","path":"vilbert/vilbert.py","file_url":"https://github.com/jeremylinky/youtube-vln/blob/HEAD/vilbert/vilbert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2306.11641","paper":"/paper/salsa-verde-a-machine-learning-attack-on","title":"SALSA VERDE: a machine learning attack on Learning With Errors with sparse small secrets","date":null,"month_inferred_from_arxiv_id":"2023-06","title_source":"archive","repo":"facebookresearch/verde","path":"src/train/model/transformer.py","file_url":"https://github.com/facebookresearch/verde/blob/HEAD/src/train/model/transformer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"f6ed858344bb92c7","mcp_get_code":{"code_sha256":"f6ed858344bb92c7"}},{"arxiv_id":"2305.18500","paper":"/paper/vast-a-vision-audio-subtitle-text-omni-1","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","date":"2023-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TXH-mercury/VALOR","path":"model/transformer.py","file_url":"https://github.com/TXH-mercury/VALOR/blob/HEAD/model/transformer.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2305.18500","paper":"/paper/vast-a-vision-audio-subtitle-text-omni-1","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","date":"2023-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TXH-mercury/VALOR","path":"model/bert.py","file_url":"https://github.com/TXH-mercury/VALOR/blob/HEAD/model/bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"40e9fee2e0b7e278","mcp_get_code":{"code_sha256":"40e9fee2e0b7e278"}},{"arxiv_id":"2305.16986","paper":"/paper/navgpt-explicit-reasoning-in-vision-and","title":"NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models","date":"2023-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2305.14007","paper":"/paper/when-does-aggregating-multiple-skills-with","title":"When Does Aggregating Multiple Skills with Multi-Task Learning Work? A Case Study in Financial NLP","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"EdisonNi-hku/MTL4Finance","path":"code/models/modeling_task_embeddings.py","file_url":"https://github.com/EdisonNi-hku/MTL4Finance/blob/HEAD/code/models/modeling_task_embeddings.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"211753ba29188d4e","mcp_get_code":{"code_sha256":"211753ba29188d4e"}},{"arxiv_id":"2305.14007","paper":"/paper/when-does-aggregating-multiple-skills-with","title":"When Does Aggregating Multiple Skills with Multi-Task Learning Work? A Case Study in Financial NLP","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"EdisonNi-hku/MTL4Finance","path":"code/models/models_pal.py","file_url":"https://github.com/EdisonNi-hku/MTL4Finance/blob/HEAD/code/models/models_pal.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6e821c762a936642","mcp_get_code":{"code_sha256":"6e821c762a936642"}},{"arxiv_id":"2305.13050","paper":"/paper/audiotoken-adaptation-of-text-conditioned-1","title":"AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation","date":"2023-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"guyyariv/AudioToken","path":"modules/BEATs/modules.py","file_url":"https://github.com/guyyariv/AudioToken/blob/HEAD/modules/BEATs/modules.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f30ebf4e48b7e2d7","mcp_get_code":{"code_sha256":"f30ebf4e48b7e2d7"}},{"arxiv_id":"2305.12218","paper":"/paper/text-video-retrieval-with-disentangled","title":"Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment","date":"2023-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jpthu17/DiCoSA","path":"tvr/models/until_module.py","file_url":"https://github.com/jpthu17/DiCoSA/blob/HEAD/tvr/models/until_module.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"50e1ffed03f484ec","mcp_get_code":{"code_sha256":"50e1ffed03f484ec"}},{"arxiv_id":"2305.11435","paper":"/paper/syllable-discovery-and-cross-lingual","title":"Syllable Discovery and Cross-Lingual Generalization in a Visually Grounded, Self-Supervised Speech Model","date":"2023-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jasonppy/syllable-discovery","path":"models/utils.py","file_url":"https://github.com/jasonppy/syllable-discovery/blob/HEAD/models/utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"c2f0705ed8e6f7e6","mcp_get_code":{"code_sha256":"c2f0705ed8e6f7e6"}},{"arxiv_id":"2305.01938","paper":"/paper/doc2soargraph-discrete-reasoning-over","title":"Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text Documents via Semantic-Oriented Hierarchical Graphs","date":"2023-05-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fengbinzhu/doc2soargraph","path":"etr/model/tree_model.py","file_url":"https://github.com/fengbinzhu/doc2soargraph/blob/HEAD/etr/model/tree_model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"56a9ab06b860b180","mcp_get_code":{"code_sha256":"56a9ab06b860b180"}},{"arxiv_id":"2304.08382","paper":"/paper/melt-mutual-enhancement-of-long-tailed-user","title":"MELT: Mutual Enhancement of Long-Tailed User and Item for Sequential Recommendation","date":"2023-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rlqja1107/melt","path":"models/MELT_FMLP.py","file_url":"https://github.com/rlqja1107/melt/blob/HEAD/models/MELT_FMLP.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"56a9ab06b860b180","mcp_get_code":{"code_sha256":"56a9ab06b860b180"}},{"arxiv_id":"2304.07763","paper":"/paper/meta-optimized-contrastive-learning-for","title":"Meta-optimized Contrastive Learning for Sequential Recommendation","date":"2023-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qinhsiu/mclrec","path":"recbole/model/extractors.py","file_url":"https://github.com/qinhsiu/mclrec/blob/HEAD/recbole/model/extractors.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eb13ab048d49bf28","mcp_get_code":{"code_sha256":"eb13ab048d49bf28"}},{"arxiv_id":"2303.12341","paper":"/paper/easydgl-encode-train-and-interpret-for","title":"EasyDGL: Encode, Train and Interpret for Continuous-time Dynamic Graph Learning","date":"2023-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cchao0116/EasyDGL","path":"src/model/EasyDGL.py","file_url":"https://github.com/cchao0116/EasyDGL/blob/HEAD/src/model/EasyDGL.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"54425d58028099f9","mcp_get_code":{"code_sha256":"54425d58028099f9"}},{"arxiv_id":"2303.12341","paper":"/paper/easydgl-encode-train-and-interpret-for","title":"EasyDGL: Encode, Train and Interpret for Continuous-time Dynamic Graph Learning","date":"2023-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cchao0116/EasyDGL","path":"src/model/GREC.py","file_url":"https://github.com/cchao0116/EasyDGL/blob/HEAD/src/model/GREC.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"31a88827333397cd","mcp_get_code":{"code_sha256":"31a88827333397cd"}},{"arxiv_id":"2303.11921","paper":"/paper/context-de-confounded-emotion-recognition","title":"Context De-confounded Emotion Recognition","date":"2023-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"d9dcfb510a5e2690","mcp_get_code":{"code_sha256":"d9dcfb510a5e2690"}},{"arxiv_id":"2302.11812","paper":"/paper/teacher-intervention-improving-convergence-of","title":"Teacher Intervention: Improving Convergence of Quantization Aware Training for Ultra-Low Precision Transformers","date":"2023-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2302.05574","paper":"/paper/napss-paragraph-level-medical-text","title":"NapSS: Paragraph-level Medical Text Simplification via Narrative Prompting and Sentence-matching Summarization","date":"2023-02-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/bert","path":"modeling.py","file_url":"https://github.com/google-research/bert/blob/HEAD/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d08f324f950148de","mcp_get_code":{"code_sha256":"d08f324f950148de"}},{"arxiv_id":"2301.13338","paper":"/paper/continuous-spatiotemporal-transformers","title":"Continuous Spatiotemporal Transformers","date":"2023-01-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vandijklab/cst","path":"continuous_transformer/ContSpaceTime.py","file_url":"https://github.com/vandijklab/cst/blob/HEAD/continuous_transformer/ContSpaceTime.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"62e7409a816626ac","mcp_get_code":{"code_sha256":"62e7409a816626ac"}},{"arxiv_id":"2301.00746","paper":"/paper/naq-leveraging-narrations-as-queries-to","title":"NaQ: Leveraging Narrations as Queries to Supervise Episodic Memory","date":"2023-01-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"srama2512/NaQ","path":"ReLER/ms_cm/bert_layers.py","file_url":"https://github.com/srama2512/NaQ/blob/HEAD/ReLER/ms_cm/bert_layers.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3c06d11eadebd504","mcp_get_code":{"code_sha256":"3c06d11eadebd504"}},{"arxiv_id":"2301.00184","paper":"/paper/cap4video-what-can-auxiliary-captions-do-for","title":"Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?","date":"2022-12-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"whwu95/Cap4Video","path":"modules/until_module.py","file_url":"https://github.com/whwu95/Cap4Video/blob/HEAD/modules/until_module.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"50e1ffed03f484ec","mcp_get_code":{"code_sha256":"50e1ffed03f484ec"}},{"arxiv_id":"2212.09058","paper":"/paper/beats-audio-pre-training-with-acoustic","title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","date":"2022-12-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"phuriches/genrepasd","path":"beats/modules.py","file_url":"https://github.com/phuriches/genrepasd/blob/HEAD/beats/modules.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f30ebf4e48b7e2d7","mcp_get_code":{"code_sha256":"f30ebf4e48b7e2d7"}},{"arxiv_id":"2212.06817","paper":"/paper/rt-1-robotics-transformer-for-real-world","title":"RT-1: Robotics Transformer for Real-World Control at Scale","date":"2022-12-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/robotics_transformer","path":"tokenizers/token_learner.py","file_url":"https://github.com/google-research/robotics_transformer/blob/HEAD/tokenizers/token_learner.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b4f4f969a90d69b8","mcp_get_code":{"code_sha256":"b4f4f969a90d69b8"}},{"arxiv_id":"2212.03506","paper":"/paper/wider-closer-mixture-of-short-channel","title":"WIDER & CLOSER: Mixture of Short-channel Distillers for Zero-shot Cross-lingual Named Entity Recognition","date":"2022-12-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mckysse/msd","path":"transformers/modeling_gpt2.py","file_url":"https://github.com/mckysse/msd/blob/HEAD/transformers/modeling_gpt2.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"2212.03506","paper":"/paper/wider-closer-mixture-of-short-channel","title":"WIDER & CLOSER: Mixture of Short-channel Distillers for Zero-shot Cross-lingual Named Entity Recognition","date":"2022-12-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mckysse/msd","path":"transformers/modeling_bert.py","file_url":"https://github.com/mckysse/msd/blob/HEAD/transformers/modeling_bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"211753ba29188d4e","mcp_get_code":{"code_sha256":"211753ba29188d4e"}},{"arxiv_id":"2212.03506","paper":"/paper/wider-closer-mixture-of-short-channel","title":"WIDER & CLOSER: Mixture of Short-channel Distillers for Zero-shot Cross-lingual Named Entity Recognition","date":"2022-12-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mckysse/msd","path":"transformers/modeling_tf_bert.py","file_url":"https://github.com/mckysse/msd/blob/HEAD/transformers/modeling_tf_bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9bc31d06256e1691","mcp_get_code":{"code_sha256":"9bc31d06256e1691"}},{"arxiv_id":"2212.03506","paper":"/paper/wider-closer-mixture-of-short-channel","title":"WIDER & CLOSER: Mixture of Short-channel Distillers for Zero-shot Cross-lingual Named Entity Recognition","date":"2022-12-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mckysse/msd","path":"transformers/modeling_distilbert.py","file_url":"https://github.com/mckysse/msd/blob/HEAD/transformers/modeling_distilbert.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"69c6d14de8190cfb","mcp_get_code":{"code_sha256":"69c6d14de8190cfb"}},{"arxiv_id":"2211.13308","paper":"/paper/scirepeval-a-multi-format-benchmark-for","title":"SciRepEval: A Multi-Format Benchmark for Scientific Document Representations","date":"2022-11-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"allenai/scirepeval","path":"bert_pals.py","file_url":"https://github.com/allenai/scirepeval/blob/HEAD/bert_pals.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"40e9fee2e0b7e278","mcp_get_code":{"code_sha256":"40e9fee2e0b7e278"}},{"arxiv_id":"2211.09892","paper":"/paper/summarizing-community-based-question-answer","title":"Summarizing Community-based Question-Answer Pairs","date":"2022-11-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nlpyang/BertSum","path":"src/models/neural.py","file_url":"https://github.com/nlpyang/BertSum/blob/HEAD/src/models/neural.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"2211.07950","paper":"/paper/breakpoint-transformers-for-modeling-and","title":"Breakpoint Transformers for Modeling and Tracking Intermediate Beliefs","date":"2022-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"a43d18e9c8836542","mcp_get_code":{"code_sha256":"a43d18e9c8836542"}},{"arxiv_id":"2211.01335","paper":"/paper/chinese-clip-contrastive-vision-language","title":"Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese","date":"2022-11-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ofa-sys/chinese-clip","path":"cn_clip/clip/modeling_bert.py","file_url":"https://github.com/ofa-sys/chinese-clip/blob/HEAD/cn_clip/clip/modeling_bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"211753ba29188d4e","mcp_get_code":{"code_sha256":"211753ba29188d4e"}},{"arxiv_id":"2210.17016","paper":"/paper/wespeaker-a-research-and-production-oriented","title":"Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkit","date":null,"month_inferred_from_arxiv_id":"2022-10","title_source":"archive","repo":"BUTSpeechFIT/wespeaker_ssl_public","path":"wespeaker/models/ssl/modules.py","file_url":"https://github.com/BUTSpeechFIT/wespeaker_ssl_public/blob/HEAD/wespeaker/models/ssl/modules.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f30ebf4e48b7e2d7","mcp_get_code":{"code_sha256":"f30ebf4e48b7e2d7"}},{"arxiv_id":"2210.12765","paper":"/paper/multi-objective-gflownets","title":"Multi-Objective GFlowNets","date":"2022-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"samuelstanton/lambo","path":"lambo/models/shared_elements.py","file_url":"https://github.com/samuelstanton/lambo/blob/HEAD/lambo/models/shared_elements.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"daf4ea3f44ecdf49","mcp_get_code":{"code_sha256":"daf4ea3f44ecdf49"}},{"arxiv_id":"2210.12582","paper":"/paper/language-model-pre-training-with-sparse","title":"Language Model Pre-Training with Sparse Latent Typing","date":"2022-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"renll/sparselt","path":"model.py","file_url":"https://github.com/renll/sparselt/blob/HEAD/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d9dcfb510a5e2690","mcp_get_code":{"code_sha256":"d9dcfb510a5e2690"}},{"arxiv_id":"2210.10276","paper":"/paper/clip-driven-fine-grained-text-image-person-re","title":"CLIP-Driven Fine-grained Text-Image Person Re-identification","date":"2022-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shuanglinyan/CFine","path":"models/model.py","file_url":"https://github.com/shuanglinyan/CFine/blob/HEAD/models/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9d64df741b029314","mcp_get_code":{"code_sha256":"9d64df741b029314"}},{"arxiv_id":"2210.10276","paper":"/paper/clip-driven-fine-grained-text-image-person-re","title":"CLIP-Driven Fine-grained Text-Image Person Re-identification","date":"2022-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shuanglinyan/CFine","path":"models/modeling.py","file_url":"https://github.com/shuanglinyan/CFine/blob/HEAD/models/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"56a9ab06b860b180","mcp_get_code":{"code_sha256":"56a9ab06b860b180"}},{"arxiv_id":"2210.09338","paper":"/paper/deep-bidirectional-language-knowledge-graph","title":"Deep Bidirectional Language-Knowledge Graph Pretraining","date":"2022-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"michiyasunaga/dragon","path":"utils/layers.py","file_url":"https://github.com/michiyasunaga/dragon/blob/HEAD/utils/layers.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b75e9c793d2a286a","mcp_get_code":{"code_sha256":"b75e9c793d2a286a"}},{"arxiv_id":"2210.08714","paper":"/paper/selective-query-guided-debiasing-network-for","title":"Selective Query-guided Debiasing for Video Corpus Moment Retrieval","date":"2022-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dbstjswo505/SQuiDNet","path":"model/squidnet.py","file_url":"https://github.com/dbstjswo505/SQuiDNet/blob/HEAD/model/squidnet.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"29af270e862dd867","mcp_get_code":{"code_sha256":"29af270e862dd867"}},{"arxiv_id":"2210.08465","paper":"/paper/character-centric-story-visualization-via","title":"Character-Centric Story Visualization via Visual Planning and Token Alignment","date":"2022-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adymaharana/VLCStoryGan","path":"vlcgan/model.py","file_url":"https://github.com/adymaharana/VLCStoryGan/blob/HEAD/vlcgan/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a3abf3fe697fabd0","mcp_get_code":{"code_sha256":"a3abf3fe697fabd0"}},{"arxiv_id":"2210.02414","paper":"/paper/glm-130b-an-open-bilingual-pre-trained-model","title":"GLM-130B: An Open Bilingual Pre-trained Model","date":"2022-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jackaduma/ChatGLM-LoRA-RLHF-PyTorch","path":"models/modeling_chatglm.py","file_url":"https://github.com/jackaduma/ChatGLM-LoRA-RLHF-PyTorch/blob/HEAD/models/modeling_chatglm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"43c9688838aff8b2","mcp_get_code":{"code_sha256":"43c9688838aff8b2"}},{"arxiv_id":"2208.08984","paper":"/paper/open-vocabulary-panoptic-segmentation-with","title":"Open-Vocabulary Universal Image Segmentation with MaskCLIP","date":"2022-08-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mlpc-ucsd/MaskCLIP","path":"maskclip/modeling/maskclip.py","file_url":"https://github.com/mlpc-ucsd/MaskCLIP/blob/HEAD/maskclip/modeling/maskclip.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"08eccabe0923b8c0","mcp_get_code":{"code_sha256":"08eccabe0923b8c0"}},{"arxiv_id":"2208.05647","paper":"/paper/ppmn-pixel-phrase-matching-network-for-one","title":"PPMN: Pixel-Phrase Matching Network for One-Stage Panoptic Narrative Grounding","date":"2022-08-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dzh19990407/ppmn","path":"models/modeling.py","file_url":"https://github.com/dzh19990407/ppmn/blob/HEAD/models/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2207.08625","paper":"/paper/unifying-event-detection-and-captioning-as","title":"Unifying Event Detection and Captioning as Sequence Generation via Pre-Training","date":"2022-07-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"QiQAng/UEDVC","path":"modules/transformer.py","file_url":"https://github.com/QiQAng/UEDVC/blob/HEAD/modules/transformer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8c106eab341fc5d3","mcp_get_code":{"code_sha256":"8c106eab341fc5d3"}},{"arxiv_id":"2207.00383","paper":"/paper/reler-zju-alibaba-submission-to-the-ego4d","title":"ReLER@ZJU-Alibaba Submission to the Ego4D Natural Language Queries Challenge 2022","date":"2022-07-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nnnnai/ego4d_nlq_2022_1st_place_solution","path":"ms_cm/bert_layers.py","file_url":"https://github.com/nnnnai/ego4d_nlq_2022_1st_place_solution/blob/HEAD/ms_cm/bert_layers.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c2f0705ed8e6f7e6","mcp_get_code":{"code_sha256":"c2f0705ed8e6f7e6"}},{"arxiv_id":"2206.06583","paper":"/paper/exploring-evolution-based-free-protein","title":"Exploring evolution-aware & -free protein language models as protein function predictors","date":"2022-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"elttaes/revisiting-plms","path":"ESM-1b_Pretrain/esm/modules.py","file_url":"https://github.com/elttaes/revisiting-plms/blob/HEAD/ESM-1b_Pretrain/esm/modules.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2e7bd6c4ccd1ed68","mcp_get_code":{"code_sha256":"2e7bd6c4ccd1ed68"}},{"arxiv_id":"2206.04910","paper":"/paper/nagphormer-neighborhood-aggregation-graph","title":"NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs","date":"2022-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JHL-HUST/NAGphormer","path":"model.py","file_url":"https://github.com/JHL-HUST/NAGphormer/blob/HEAD/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"344a09e8f735a6b3","mcp_get_code":{"code_sha256":"344a09e8f735a6b3"}},{"arxiv_id":"2206.04673","paper":"/paper/neural-prompt-search","title":"Neural Prompt Search","date":"2022-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZhangYuanhan-AI/NOAH","path":"model/supernet_transformer_prompt.py","file_url":"https://github.com/ZhangYuanhan-AI/NOAH/blob/HEAD/model/supernet_transformer_prompt.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"08a5be1ffa0676e3","mcp_get_code":{"code_sha256":"08a5be1ffa0676e3"}},{"arxiv_id":"2205.13016","paper":"/paper/bit-robustly-binarized-multi-distilled","title":"BiT: Robustly Binarized Multi-distilled Transformer","date":"2022-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/bit","path":"transformer/modeling_bert_quant.py","file_url":"https://github.com/facebookresearch/bit/blob/HEAD/transformer/modeling_bert_quant.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"2d588601e8e99f5d","mcp_get_code":{"code_sha256":"2d588601e8e99f5d"}},{"arxiv_id":"2205.01068","paper":"/paper/opt-open-pre-trained-transformer-language","title":"OPT: Open Pre-trained Transformer Language Models","date":"2022-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/metaseq","path":"metaseq/modules/activation_functions.py","file_url":"https://github.com/facebookresearch/metaseq/blob/HEAD/metaseq/modules/activation_functions.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"04b65716e8591ed3","mcp_get_code":{"code_sha256":"04b65716e8591ed3"}},{"arxiv_id":"2205.00274","paper":"/paper/clues-before-answers-generation-enhanced","title":"Clues Before Answers: Generation-Enhanced Multiple-Choice QA","date":"2022-04-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nju-websoft/GenMC","path":"model/modeling_genmc.py","file_url":"https://github.com/nju-websoft/GenMC/blob/HEAD/model/modeling_genmc.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a8eafe3c0d1e9892","mcp_get_code":{"code_sha256":"a8eafe3c0d1e9892"}},{"arxiv_id":"2204.03339","paper":"/paper/boosting-self-supervised-embeddings-for","title":"Boosting Self-Supervised Embeddings for Speech Enhancement","date":"2022-04-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"khhungg/BSSE-SE","path":"models/modules.py","file_url":"https://github.com/khhungg/BSSE-SE/blob/HEAD/models/modules.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f30ebf4e48b7e2d7","mcp_get_code":{"code_sha256":"f30ebf4e48b7e2d7"}},{"arxiv_id":"2204.02152","paper":"/paper/utmos-utokyo-sarulab-system-for-voicemos","title":"UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022","date":null,"month_inferred_from_arxiv_id":"2022-04","title_source":"archive","repo":"sarulab-speech/utmos22","path":"strong/modules.py","file_url":"https://github.com/sarulab-speech/utmos22/blob/HEAD/strong/modules.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f30ebf4e48b7e2d7","mcp_get_code":{"code_sha256":"f30ebf4e48b7e2d7"}},{"arxiv_id":"2203.15685","paper":"/paper/envedit-environment-editing-for-vision-and","title":"EnvEdit: Environment Editing for Vision-and-Language Navigation","date":"2022-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jialuli-luka/envedit","path":"hamt_src/models/vilmodel_cmt.py","file_url":"https://github.com/jialuli-luka/envedit/blob/HEAD/hamt_src/models/vilmodel_cmt.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2203.15508","paper":"/paper/improving-contrastive-learning-with-model","title":"Improving Contrastive Learning with Model Augmentation","date":"2022-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/srma","path":"src/modules.py","file_url":"https://github.com/salesforce/srma/blob/HEAD/src/modules.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"fbd63a1fd03f517c","mcp_get_code":{"code_sha256":"fbd63a1fd03f517c"}},{"arxiv_id":"2203.14278","paper":"/paper/strubert-structure-aware-bert-for-table","title":"StruBERT: Structure-aware BERT for Table Search and Matching","date":"2022-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"medtray/StruBERT","path":"table_matching_model.py","file_url":"https://github.com/medtray/StruBERT/blob/HEAD/table_matching_model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c2f0705ed8e6f7e6","mcp_get_code":{"code_sha256":"c2f0705ed8e6f7e6"}},{"arxiv_id":"2203.13131","paper":"/paper/make-a-scene-scene-based-text-to-image","title":"Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors","date":"2022-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CasualGANPapers/Make-A-Scene","path":"models/transformer.py","file_url":"https://github.com/CasualGANPapers/Make-A-Scene/blob/HEAD/models/transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d60ff4b7f07480e1","mcp_get_code":{"code_sha256":"d60ff4b7f07480e1"}},{"arxiv_id":"2203.11591","paper":"/paper/hop-history-and-order-aware-pre-training-for","title":"HOP: History-and-Order Aware Pre-training for Vision-and-Language Navigation","date":"2022-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yanyuanqiao/hop-vln","path":"tasks/pretrain/vilmodel.py","file_url":"https://github.com/yanyuanqiao/hop-vln/blob/HEAD/tasks/pretrain/vilmodel.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2203.11431","paper":"/paper/task-guided-disentangled-tuning-for","title":"Task-guided Disentangled Tuning for Pretrained Language Models","date":"2022-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lemon0830/TDT","path":"TDT/transformers/modeling_bert.py","file_url":"https://github.com/lemon0830/TDT/blob/HEAD/TDT/transformers/modeling_bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"211753ba29188d4e","mcp_get_code":{"code_sha256":"211753ba29188d4e"}},{"arxiv_id":"2203.10541","paper":"/paper/unsupervised-domain-adaptation-for-nighttime","title":"Unsupervised Domain Adaptation for Nighttime Aerial Tracking","date":"2022-03-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vision4robotics/UDAT","path":"UDAT/BAN/siamban/models/trans_discriminator.py","file_url":"https://github.com/vision4robotics/UDAT/blob/HEAD/UDAT/BAN/siamban/models/trans_discriminator.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"6a9faa89f4d1a831","mcp_get_code":{"code_sha256":"6a9faa89f4d1a831"}},{"arxiv_id":"2203.09101","paper":"/paper/relationprompt-leveraging-prompts-to-generate","title":"RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction","date":"2022-03-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"declare-lab/hyperred","path":"modeling.py","file_url":"https://github.com/declare-lab/hyperred/blob/HEAD/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e650dcdf9e8a559f","mcp_get_code":{"code_sha256":"e650dcdf9e8a559f"}},{"arxiv_id":"2203.07111","paper":"/paper/disentangled-representation-learning-for-text","title":"Disentangled Representation Learning for Text-Video Retrieval","date":"2022-03-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"foolwood/DRL","path":"tvr/models/until_module.py","file_url":"https://github.com/foolwood/DRL/blob/HEAD/tvr/models/until_module.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"50e1ffed03f484ec","mcp_get_code":{"code_sha256":"50e1ffed03f484ec"}},{"arxiv_id":"2203.00867","paper":"/paper/incremental-transformer-structure-enhanced","title":"Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding","date":"2022-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DQiaole/ZITS_inpainting","path":"src/models/TSR_model.py","file_url":"https://github.com/DQiaole/ZITS_inpainting/blob/HEAD/src/models/TSR_model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"50e1ffed03f484ec","mcp_get_code":{"code_sha256":"50e1ffed03f484ec"}},{"arxiv_id":"2202.12210","paper":"/paper/bertvision-a-parameter-efficient-approach-for","title":"BERTVision -- A Parameter-Efficient Approach for Question Answering","date":"2022-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cbenge509/bertvision","path":"code/tensorflow/utils/model_zoo.py","file_url":"https://github.com/cbenge509/bertvision/blob/HEAD/code/tensorflow/utils/model_zoo.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0457b90c74c215e4","mcp_get_code":{"code_sha256":"0457b90c74c215e4"}},{"arxiv_id":"2202.12210","paper":"/paper/bertvision-a-parameter-efficient-approach-for","title":"BERTVision -- A Parameter-Efficient Approach for Question Answering","date":"2022-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cbenge509/bertvision","path":"code/tensorflow/utils/model_zoo_torch.py","file_url":"https://github.com/cbenge509/bertvision/blob/HEAD/code/tensorflow/utils/model_zoo_torch.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"785b0c7e04819aac","mcp_get_code":{"code_sha256":"785b0c7e04819aac"}},{"arxiv_id":"2202.11929","paper":"/paper/word-segmentation-on-discovered-phone-units","title":"Word Segmentation on Discovered Phone Units with Dynamic Programming and Self-Supervised Scoring","date":"2022-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jasonppy/word-discovery","path":"models/utils.py","file_url":"https://github.com/jasonppy/word-discovery/blob/HEAD/models/utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"c2f0705ed8e6f7e6","mcp_get_code":{"code_sha256":"c2f0705ed8e6f7e6"}},{"arxiv_id":"2202.11705","paper":"/paper/cold-decoding-energy-based-constrained-text","title":"COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics","date":"2022-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qkaren/COLD_decoding","path":"GPT2ForwardBackward/modeling_opengpt2.py","file_url":"https://github.com/qkaren/COLD_decoding/blob/HEAD/GPT2ForwardBackward/modeling_opengpt2.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4fce6cee9a3fe85d","mcp_get_code":{"code_sha256":"4fce6cee9a3fe85d"}},{"arxiv_id":"2202.10710","paper":"/paper/incorporating-constituent-syntax-for","title":"Incorporating Constituent Syntax for Coreference Resolution","date":"2022-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mandarjoshi90/coref","path":"bert/modeling.py","file_url":"https://github.com/mandarjoshi90/coref/blob/HEAD/bert/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ecab128238ebf253","mcp_get_code":{"code_sha256":"ecab128238ebf253"}},{"arxiv_id":"2202.04298","paper":"/paper/image-difference-captioning-with-pre-training","title":"Image Difference Captioning with Pre-training and Contrastive Learning","date":"2022-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"56a9ab06b860b180","mcp_get_code":{"code_sha256":"56a9ab06b860b180"}},{"arxiv_id":"2202.02519","paper":"/paper/intent-contrastive-learning-for-sequential","title":"Intent Contrastive Learning for Sequential Recommendation","date":"2022-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/iclrec","path":"src/modules.py","file_url":"https://github.com/salesforce/iclrec/blob/HEAD/src/modules.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"fbd63a1fd03f517c","mcp_get_code":{"code_sha256":"fbd63a1fd03f517c"}},{"arxiv_id":"2201.11732","paper":"/paper/iglue-a-benchmark-for-transfer-learning","title":"IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages","date":"2022-01-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"e-bug/volta","path":"volta/encoders.py","file_url":"https://github.com/e-bug/volta/blob/HEAD/volta/encoders.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2201.11732","paper":"/paper/iglue-a-benchmark-for-transfer-learning","title":"IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages","date":"2022-01-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"e-bug/volta","path":"volta/m3p_transformer.py","file_url":"https://github.com/e-bug/volta/blob/HEAD/volta/m3p_transformer.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"66c21a3911091d29","mcp_get_code":{"code_sha256":"66c21a3911091d29"}},{"arxiv_id":"2201.06885","paper":"/paper/mining-fine-grained-semantics-via-graph","title":"Evidence-aware Fake News Detection with Graph Neural Networks","date":"2022-01-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CRIPAC-DIG/GET","path":"pytorch_transformers/modeling_gpt2.py","file_url":"https://github.com/CRIPAC-DIG/GET/blob/HEAD/pytorch_transformers/modeling_gpt2.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"2201.06885","paper":"/paper/mining-fine-grained-semantics-via-graph","title":"Evidence-aware Fake News Detection with Graph Neural Networks","date":"2022-01-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CRIPAC-DIG/GET","path":"pytorch_transformers/modeling_bert.py","file_url":"https://github.com/CRIPAC-DIG/GET/blob/HEAD/pytorch_transformers/modeling_bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2201.06885","paper":"/paper/mining-fine-grained-semantics-via-graph","title":"Evidence-aware Fake News Detection with Graph Neural Networks","date":"2022-01-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CRIPAC-DIG/GET","path":"pytorch_transformers/modeling_distilbert.py","file_url":"https://github.com/CRIPAC-DIG/GET/blob/HEAD/pytorch_transformers/modeling_distilbert.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"69c6d14de8190cfb","mcp_get_code":{"code_sha256":"69c6d14de8190cfb"}},{"arxiv_id":"2112.06714","paper":"/paper/learning-semantic-aligned-feature","title":"Learning Semantic-Aligned Feature Representation for Text-based Person Search","date":"2021-12-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"reallsp/SAF","path":"models/model.py","file_url":"https://github.com/reallsp/SAF/blob/HEAD/models/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9d64df741b029314","mcp_get_code":{"code_sha256":"9d64df741b029314"}},{"arxiv_id":"2111.02194","paper":"/paper/learning-implicit-sentiment-in-aspect-based","title":"Learning Implicit Sentiment in Aspect-based Sentiment Analysis with Supervised Contrastive Pre-Training","date":"2021-11-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Tribleave/SCAPT-ABSA","path":"model/module/misc.py","file_url":"https://github.com/Tribleave/SCAPT-ABSA/blob/HEAD/model/module/misc.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"2110.07592","paper":"/paper/speech-toxicity-analysis-a-new-spoken","title":"DeToxy: A Large-Scale Multimodal Dataset for Toxicity Classification in Spoken Utterances","date":"2021-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2110.02526","paper":"/paper/coarse-to-fine-reasoning-for-visual-question","title":"Coarse-to-Fine Reasoning for Visual Question Answering","date":"2021-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aioz-ai/crf_vqa","path":"lxrt/modeling.py","file_url":"https://github.com/aioz-ai/crf_vqa/blob/HEAD/lxrt/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2110.15064","paper":"/paper/towards-fine-grained-reasoning-for-fake-news","title":"Towards Fine-Grained Reasoning for Fake News Detection","date":"2021-09-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Ahren09/FinerFact","path":"kgat/bert_model.py","file_url":"https://github.com/Ahren09/FinerFact/blob/HEAD/kgat/bert_model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2109.15107","paper":"/paper/crossaug-a-contrastive-data-augmentation","title":"CrossAug: A Contrastive Data Augmentation Method for Debiasing Fact Verification Models","date":"2021-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"minwhoo/crossaug","path":"modeling_bert.py","file_url":"https://github.com/minwhoo/crossaug/blob/HEAD/modeling_bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2109.12072","paper":"/paper/sd-qa-spoken-dialectal-question-answering-for","title":"SD-QA: Spoken Dialectal Question Answering for the Real World","date":"2021-09-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ffaisal93/sd-qa","path":"baselines/tydiqa/baseline/bert/modeling.py","file_url":"https://github.com/ffaisal93/sd-qa/blob/HEAD/baselines/tydiqa/baseline/bert/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"51d3bc0cfa6415a3","mcp_get_code":{"code_sha256":"51d3bc0cfa6415a3"}},{"arxiv_id":"2109.06480","paper":"/paper/logic-level-evidence-retrieval-and-graph","title":"Logic-level Evidence Retrieval and Graph-based Verification Network for Table-based Fact Verification","date":"2021-09-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qshi95/lergv","path":"modeling_gnn.py","file_url":"https://github.com/qshi95/lergv/blob/HEAD/modeling_gnn.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b75e9c793d2a286a","mcp_get_code":{"code_sha256":"b75e9c793d2a286a"}},{"arxiv_id":"2109.04008","paper":"/paper/graph-based-network-with-contextualized","title":"Graph Based Network with Contextualized Representations of Turns in Dialogue","date":"2021-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"blacknoodle/tucore-gcn","path":"pre-trained_model/modeling.py","file_url":"https://github.com/blacknoodle/tucore-gcn/blob/HEAD/pre-trained_model/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"40e9fee2e0b7e278","mcp_get_code":{"code_sha256":"40e9fee2e0b7e278"}},{"arxiv_id":"2109.00590","paper":"/paper/webqa-multihop-and-multimodal-qa","title":"WebQA: Multihop and Multimodal QA","date":"2021-09-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shubham-gupta-iitr/mmmlX","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/shubham-gupta-iitr/mmmlX/blob/HEAD/pytorch_pretrained_bert/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"db8040436dc60177","mcp_get_code":{"code_sha256":"db8040436dc60177"}},{"arxiv_id":"2108.09105","paper":"/paper/airbert-in-domain-pretraining-for-vision-and","title":"Airbert: In-domain Pretraining for Vision-and-Language Navigation","date":"2021-08-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"airbert-vln/airbert","path":"vilbert/vilbert.py","file_url":"https://github.com/airbert-vln/airbert/blob/HEAD/vilbert/vilbert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2106.14019","paper":"/paper/umic-an-unreferenced-metric-for-image","title":"UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning","date":"2021-06-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hwanheelee1993/UMIC","path":"model/ce.py","file_url":"https://github.com/hwanheelee1993/UMIC/blob/HEAD/model/ce.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c2f0705ed8e6f7e6","mcp_get_code":{"code_sha256":"c2f0705ed8e6f7e6"}},{"arxiv_id":"2106.11310","paper":"/paper/towards-long-form-video-understanding-1","title":"Towards Long-Form Video Understanding","date":"2021-06-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chaoyuaw/lvu","path":"src/models/modeling_bert.py","file_url":"https://github.com/chaoyuaw/lvu/blob/HEAD/src/models/modeling_bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"211753ba29188d4e","mcp_get_code":{"code_sha256":"211753ba29188d4e"}},{"arxiv_id":"2106.08087","paper":"/paper/cblue-a-chinese-biomedical-language","title":"CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark","date":"2021-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cbluebenchmark/cblue","path":"cblue/models/zen/modeling.py","file_url":"https://github.com/cbluebenchmark/cblue/blob/HEAD/cblue/models/zen/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2106.07340","paper":"/paper/mathbert-a-pre-trained-language-model-for","title":"MathBERT: A Pre-trained Language Model for General NLP Tasks in Mathematics Education","date":"2021-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tbs17/MathBERT","path":"mathbert/modeling.py","file_url":"https://github.com/tbs17/MathBERT/blob/HEAD/mathbert/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"d08f324f950148de","mcp_get_code":{"code_sha256":"d08f324f950148de"}},{"arxiv_id":"2106.04632","paper":"/paper/value-a-multi-task-benchmark-for-video-and","title":"VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation","date":"2021-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VALUE-Leaderboard/StarterCode","path":"model/layers.py","file_url":"https://github.com/VALUE-Leaderboard/StarterCode/blob/HEAD/model/layers.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"29af270e862dd867","mcp_get_code":{"code_sha256":"29af270e862dd867"}},{"arxiv_id":"2106.02636","paper":"/paper/merlot-multimodal-neural-script-knowledge","title":"MERLOT: Multimodal Neural Script Knowledge Models","date":"2021-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rowanz/merlot","path":"utils/model_utils.py","file_url":"https://github.com/rowanz/merlot/blob/HEAD/utils/model_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e1cd654e2fac4f34","mcp_get_code":{"code_sha256":"e1cd654e2fac4f34"}},{"arxiv_id":"2106.02584","paper":"/paper/self-attention-between-datapoints-going","title":"Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning","date":"2021-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"oatml-markslab/proteinnpt","path":"proteinnpt/utils/esm/modules.py","file_url":"https://github.com/oatml-markslab/proteinnpt/blob/HEAD/proteinnpt/utils/esm/modules.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2e7bd6c4ccd1ed68","mcp_get_code":{"code_sha256":"2e7bd6c4ccd1ed68"}},{"arxiv_id":"2106.00420","paper":"/paper/dialogue-oriented-pre-training","title":"Dialogue-oriented Pre-training","date":"2021-06-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xyease/Dialog-PrLM","path":"src/transformers/activations_tf.py","file_url":"https://github.com/xyease/Dialog-PrLM/blob/HEAD/src/transformers/activations_tf.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"14a1c81ea568d152","mcp_get_code":{"code_sha256":"14a1c81ea568d152"}},{"arxiv_id":"2105.12002","paper":"/paper/super-tickets-in-pre-trained-language-models","title":"Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization","date":"2021-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cliang1453/super-structured-lottery-tickets","path":"module/modeling_bert.py","file_url":"https://github.com/cliang1453/super-structured-lottery-tickets/blob/HEAD/module/modeling_bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"211753ba29188d4e","mcp_get_code":{"code_sha256":"211753ba29188d4e"}},{"arxiv_id":"2105.10188","paper":"/paper/semantic-representation-for-dialogue-modeling","title":"Semantic Representation for Dialogue Modeling","date":"2021-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"muyeby/AMR-Dialogue","path":"DialogRE/bert/modeling.py","file_url":"https://github.com/muyeby/AMR-Dialogue/blob/HEAD/DialogRE/bert/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"40e9fee2e0b7e278","mcp_get_code":{"code_sha256":"40e9fee2e0b7e278"}},{"arxiv_id":"2105.03761","paper":"/paper/e-vil-a-dataset-and-benchmark-for-natural","title":"e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks","date":"2021-05-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"maximek3/e-ViL","path":"src/modeling.py","file_url":"https://github.com/maximek3/e-ViL/blob/HEAD/src/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3c06d11eadebd504","mcp_get_code":{"code_sha256":"3c06d11eadebd504"}},{"arxiv_id":"2105.02605","paper":"/paper/graphformers-gnn-nested-language-models-for","title":"GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph","date":"2021-05-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/GraphFormers","path":"src/models/tnlrv3/modeling_decoding.py","file_url":"https://github.com/microsoft/GraphFormers/blob/HEAD/src/models/tnlrv3/modeling_decoding.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"40e9fee2e0b7e278","mcp_get_code":{"code_sha256":"40e9fee2e0b7e278"}},{"arxiv_id":"2104.09791","paper":"/paper/b-prop-bootstrapped-pre-training-with","title":"B-PROP: Bootstrapped Pre-training with Representative Words Prediction for Ad-hoc Retrieval","date":"2021-04-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Albert-Ma/PROP","path":"pytorch_pretrain_bert/modeling.py","file_url":"https://github.com/Albert-Ma/PROP/blob/HEAD/pytorch_pretrain_bert/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2104.08400","paper":"/paper/structure-aware-abstractive-conversation","title":"Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs","date":"2021-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GT-SALT/Structure-Aware-BART","path":"transformers/src/transformers/activations_tf.py","file_url":"https://github.com/GT-SALT/Structure-Aware-BART/blob/HEAD/transformers/src/transformers/activations_tf.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"14a1c81ea568d152","mcp_get_code":{"code_sha256":"14a1c81ea568d152"}},{"arxiv_id":"2104.06378","paper":"/paper/qa-gnn-reasoning-with-language-models-and","title":"QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering","date":"2021-04-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"michiyasunaga/qagnn","path":"utils/layers.py","file_url":"https://github.com/michiyasunaga/qagnn/blob/HEAD/utils/layers.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b75e9c793d2a286a","mcp_get_code":{"code_sha256":"b75e9c793d2a286a"}},{"arxiv_id":"2104.04039","paper":"/paper/plug-and-blend-a-framework-for-controllable","title":"Plug-and-Blend: A Framework for Controllable Story Generation with Blended Control Codes","date":"2021-03-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xxbidiao/plug-and-blend","path":"gedi_helpers/modeling_gpt2.py","file_url":"https://github.com/xxbidiao/plug-and-blend/blob/HEAD/gedi_helpers/modeling_gpt2.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"2103.16110","paper":"/paper/kaleido-bert-vision-language-pre-training-on","title":"Kaleido-BERT: Vision-Language Pre-training on Fashion Domain","date":"2021-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mczhuge/Kaleido-BERT","path":"easytransfer/layers/activations.py","file_url":"https://github.com/mczhuge/Kaleido-BERT/blob/HEAD/easytransfer/layers/activations.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9bc31d06256e1691","mcp_get_code":{"code_sha256":"9bc31d06256e1691"}},{"arxiv_id":"2103.12235","paper":"/paper/mitigating-false-negative-contexts-in-multi","title":"Mitigating False-Negative Contexts in Multi-document Question Answering with Retrieval Marginalization","date":"2021-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"niansong1996/retrieval_marginalization","path":"rranm_modules/neural_modules/numnet_utils.py","file_url":"https://github.com/niansong1996/retrieval_marginalization/blob/HEAD/rranm_modules/neural_modules/numnet_utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"56a9ab06b860b180","mcp_get_code":{"code_sha256":"56a9ab06b860b180"}},{"arxiv_id":"2102.10407","paper":"/paper/visualgpt-data-efficient-image-captioning-by","title":"VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning","date":"2021-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"d9dcfb510a5e2690","mcp_get_code":{"code_sha256":"d9dcfb510a5e2690"}},{"arxiv_id":"2102.07074","paper":"/paper/transgan-two-transformers-can-make-one-strong","title":"TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up","date":"2021-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hungtrankhanh/CS5260_project","path":"models/TransGAN_8_8_1.py","file_url":"https://github.com/hungtrankhanh/CS5260_project/blob/HEAD/models/TransGAN_8_8_1.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"6a9faa89f4d1a831","mcp_get_code":{"code_sha256":"6a9faa89f4d1a831"}},{"arxiv_id":"2012.15701","paper":"/paper/binarybert-pushing-the-limit-of-bert","title":"BinaryBERT: Pushing the Limit of BERT Quantization","date":"2020-12-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2011.01513","paper":"/paper/charbert-character-aware-pre-trained-language","title":"CharBERT: Character-aware Pre-trained Language Model","date":"2020-11-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wtma/CharBERT","path":"modeling/modeling_bert.py","file_url":"https://github.com/wtma/CharBERT/blob/HEAD/modeling/modeling_bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"211753ba29188d4e","mcp_get_code":{"code_sha256":"211753ba29188d4e"}},{"arxiv_id":"2010.12537","paper":"/paper/structure-aware-pre-training-for-table","title":"TUTA: Tree-based Transformers for Generally Structured Table Pre-training","date":"2020-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/TUTA_table_understanding","path":"tuta/model/act_funcs.py","file_url":"https://github.com/microsoft/TUTA_table_understanding/blob/HEAD/tuta/model/act_funcs.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3663ddf34e3b4012","mcp_get_code":{"code_sha256":"3663ddf34e3b4012"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kamalkraj/Vision-Transformer","path":"model.py","file_url":"https://github.com/kamalkraj/Vision-Transformer/blob/HEAD/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a3ebed4aa179cd7f","mcp_get_code":{"code_sha256":"a3ebed4aa179cd7f"}},{"arxiv_id":"2010.11731","paper":"/paper/improving-bert-performance-for-aspect-based","title":"Improving BERT Performance for Aspect-Based Sentiment Analysis","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IMPLabUniPr/BERT-for-ABSA","path":"src/modeling.py","file_url":"https://github.com/IMPLabUniPr/BERT-for-ABSA/blob/HEAD/src/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2010.10392","paper":"/paper/characterbert-reconciling-elmo-and-bert-for","title":"CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters","date":"2020-10-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IMPLabUniPr/UniParma-at-semeval-2021-task-5","path":"transformers/modeling_bert.py","file_url":"https://github.com/IMPLabUniPr/UniParma-at-semeval-2021-task-5/blob/HEAD/transformers/modeling_bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"211753ba29188d4e","mcp_get_code":{"code_sha256":"211753ba29188d4e"}},{"arxiv_id":"2010.08210","paper":"/paper/coarse-to-fine-pre-training-for-named-entity","title":"Coarse-to-Fine Pre-training for Named Entity Recognition","date":"2020-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"9d64df741b029314","mcp_get_code":{"code_sha256":"9d64df741b029314"}},{"arxiv_id":"2010.07717","paper":"/paper/wasserstein-distance-regularized-sequence","title":"Wasserstein Distance Regularized Sequence Representation for Text Matching in Asymmetrical Domains","date":"2020-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RUC-WSM/WD-Match","path":"src/model.py","file_url":"https://github.com/RUC-WSM/WD-Match/blob/HEAD/src/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"83960d2d866210b0","mcp_get_code":{"code_sha256":"83960d2d866210b0"}},{"arxiv_id":"2010.06138","paper":"/paper/incorporating-bert-into-parallel-sequence","title":"Incorporating BERT into Parallel Sequence Decoding with Adapters","date":"2020-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lemmonation/abnet","path":"bert/modeling.py","file_url":"https://github.com/lemmonation/abnet/blob/HEAD/bert/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2010.05607","paper":"/paper/the-elephant-in-the-interpretability-room-why","title":"The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?","date":"2020-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jessevig/bertviz","path":"bertviz/transformers_neuron_view/modeling_bert.py","file_url":"https://github.com/jessevig/bertviz/blob/HEAD/bertviz/transformers_neuron_view/modeling_bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2010.03017","paper":"/paper/on-negative-interference-in-multilingual","title":"On Negative Interference in Multilingual Models: Findings and A Meta-Learning Treatment","date":"2020-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iedwardwangi/MetaAdapter","path":"src/model/transformer.py","file_url":"https://github.com/iedwardwangi/MetaAdapter/blob/HEAD/src/model/transformer.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"66c21a3911091d29","mcp_get_code":{"code_sha256":"66c21a3911091d29"}},{"arxiv_id":"2009.14786","paper":"/paper/measuring-systematic-generalization-in-neural","title":"Measuring Systematic Generalization in Neural Proof Generation with Transformers","date":"2020-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NicolasAG/SGinPG","path":"src/model.py","file_url":"https://github.com/NicolasAG/SGinPG/blob/HEAD/src/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"a43d18e9c8836542","mcp_get_code":{"code_sha256":"a43d18e9c8836542"}},{"arxiv_id":"2009.06978","paper":"/paper/dialogue-response-ranking-training-with-large","title":"Dialogue Response Ranking Training with Large-Scale Human Feedback Data","date":"2020-09-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"golsun/dialogrpt","path":"src/transformers19/modeling_gpt2.py","file_url":"https://github.com/golsun/dialogrpt/blob/HEAD/src/transformers19/modeling_gpt2.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"2009.06367","paper":"/paper/gedi-generative-discriminator-guided-sequence","title":"GeDi: Generative Discriminator Guided Sequence Generation","date":"2020-09-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/GeDi","path":"modeling_gpt2.py","file_url":"https://github.com/salesforce/GeDi/blob/HEAD/modeling_gpt2.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"2008.01059","paper":"/paper/improving-one-stage-visual-grounding-by","title":"Improving One-stage Visual Grounding by Recursive Sub-query Construction","date":"2020-08-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zyang-ur/ReSC","path":"model/modulation.py","file_url":"https://github.com/zyang-ur/ReSC/blob/HEAD/model/modulation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"2007.12223","paper":"/paper/the-lottery-ticket-hypothesis-for-pre-trained","title":"The Lottery Ticket Hypothesis for Pre-trained BERT Networks","date":"2020-07-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TAMU-VITA/BERT-Tickets","path":"transformers-master/src/transformers/modeling_tf_bert.py","file_url":"https://github.com/TAMU-VITA/BERT-Tickets/blob/HEAD/transformers-master/src/transformers/modeling_tf_bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9bc31d06256e1691","mcp_get_code":{"code_sha256":"9bc31d06256e1691"}},{"arxiv_id":"2007.10639","paper":"/paper/multi-modal-transformer-for-video-retrieval","title":"Multi-modal Transformer for Video Retrieval","date":"2020-07-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gabeur/mmt","path":"model/bert.py","file_url":"https://github.com/gabeur/mmt/blob/HEAD/model/bert.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2fd42cf688d23870","mcp_get_code":{"code_sha256":"2fd42cf688d23870"}},{"arxiv_id":"2007.06028","paper":"/paper/tera-self-supervised-learning-of-transformer","title":"TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech","date":"2020-07-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Pandade1997/tera_asvproof","path":"transformer/model.py","file_url":"https://github.com/Pandade1997/tera_asvproof/blob/HEAD/transformer/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2007.05611","paper":"/paper/deep-contextual-clinical-prediction-with","title":"Deep Contextual Clinical Prediction with Reverse Distillation","date":"2020-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"clinicalml/omop-learn","path":"src/omop_learn/models/transformer.py","file_url":"https://github.com/clinicalml/omop-learn/blob/HEAD/src/omop_learn/models/transformer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"2007.05611","paper":"/paper/deep-contextual-clinical-prediction-with","title":"Deep Contextual Clinical Prediction with Reverse Distillation","date":"2020-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"clinicalml/omop-learn","path":"src/omop_learn/models/visit_transformer.py","file_url":"https://github.com/clinicalml/omop-learn/blob/HEAD/src/omop_learn/models/visit_transformer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d9dcfb510a5e2690","mcp_get_code":{"code_sha256":"d9dcfb510a5e2690"}},{"arxiv_id":"2007.02439","paper":"/paper/pretrained-generalized-autoregressive-model","title":"Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Clusters for Extreme Multi-label Text Classification","date":"2020-07-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huiyegit/APLC_XLNet","path":"code/pytorch_transformers/modeling_xlnet.py","file_url":"https://github.com/huiyegit/APLC_XLNet/blob/HEAD/code/pytorch_transformers/modeling_xlnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b05b2bb38c0e4e72","mcp_get_code":{"code_sha256":"b05b2bb38c0e4e72"}},{"arxiv_id":"2006.06195","paper":"/paper/large-scale-adversarial-training-for-vision","title":"Large-Scale Adversarial Training for Vision-and-Language Representation Learning","date":"2020-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhegan27/VILLA","path":"model/layer.py","file_url":"https://github.com/zhegan27/VILLA/blob/HEAD/model/layer.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2006.04884","paper":"/paper/on-the-stability-of-fine-tuning-bert","title":"On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines","date":"2020-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uds-lsv/bert-stable-fine-tuning","path":"src/transformers/modeling_tf_bert.py","file_url":"https://github.com/uds-lsv/bert-stable-fine-tuning/blob/HEAD/src/transformers/modeling_tf_bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9bc31d06256e1691","mcp_get_code":{"code_sha256":"9bc31d06256e1691"}},{"arxiv_id":"2006.04558","paper":"/paper/fastspeech-2-fast-and-high-quality-end-to-end","title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","date":"2020-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dathudeptrai/TensorflowTTS","path":"tensorflow_tts/models/fastspeech2.py","file_url":"https://github.com/dathudeptrai/TensorflowTTS/blob/HEAD/tensorflow_tts/models/fastspeech2.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7013e9a8259233a5","mcp_get_code":{"code_sha256":"7013e9a8259233a5"}},{"arxiv_id":"2006.00751","paper":"/paper/evaluation-of-cnn-based-automatic-music","title":"Evaluation of CNN-based Automatic Music Tagging Models","date":null,"month_inferred_from_arxiv_id":"2020-06","title_source":"archive","repo":"minzwon/sota-music-tagging-models","path":"training/attention_modules.py","file_url":"https://github.com/minzwon/sota-music-tagging-models/blob/HEAD/training/attention_modules.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2006.00555","paper":"/paper/transferring-inductive-biases-through","title":"Transferring Inductive Biases through Knowledge Distillation","date":"2020-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"samiraabnar/Reflect","path":"tf2_models/common_layers.py","file_url":"https://github.com/samiraabnar/Reflect/blob/HEAD/tf2_models/common_layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"47451fbef579f4fc","mcp_get_code":{"code_sha256":"47451fbef579f4fc"}},{"arxiv_id":"2005.11787","paper":"/paper/common-sense-or-world-knowledge-investigating","title":"Common Sense or World Knowledge? Investigating Adapter-Based Knowledge Injection into Pretrained Transformers","date":"2020-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wluper/retrograph","path":"retrograph/modeling/modeling.py","file_url":"https://github.com/wluper/retrograph/blob/HEAD/retrograph/modeling/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ecab128238ebf253","mcp_get_code":{"code_sha256":"ecab128238ebf253"}},{"arxiv_id":"2005.07150","paper":"/paper/named-entity-recognition-as-dependency","title":"Named Entity Recognition as Dependency Parsing","date":"2020-05-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"juntaoy/biaffine-ner","path":"extract_bert_features/modeling.py","file_url":"https://github.com/juntaoy/biaffine-ner/blob/HEAD/extract_bert_features/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"6558b9f62bb65244","mcp_get_code":{"code_sha256":"6558b9f62bb65244"}},{"arxiv_id":"2005.02439","paper":"/paper/contextualizing-hate-speech-classifiers-with","title":"Contextualizing Hate Speech Classifiers with Post-hoc Explanation","date":"2020-05-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"owaisCS/TestHateSpeech","path":"bert/modeling_gpt2.py","file_url":"https://github.com/owaisCS/TestHateSpeech/blob/HEAD/bert/modeling_gpt2.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"2005.02439","paper":"/paper/contextualizing-hate-speech-classifiers-with","title":"Contextualizing Hate Speech Classifiers with Post-hoc Explanation","date":"2020-05-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"owaisCS/TestHateSpeech","path":"bert/modeling.py","file_url":"https://github.com/owaisCS/TestHateSpeech/blob/HEAD/bert/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2005.00770","paper":"/paper/exploring-and-predicting-transferability","title":"Exploring and Predicting Transferability across NLP Tasks","date":"2020-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tuvuumass/task-transferability","path":"transformers/modeling_task_embeddings.py","file_url":"https://github.com/tuvuumass/task-transferability/blob/HEAD/transformers/modeling_task_embeddings.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"211753ba29188d4e","mcp_get_code":{"code_sha256":"211753ba29188d4e"}},{"arxiv_id":"2005.00697","paper":"/paper/deformer-decomposing-pre-trained-transformers","title":"DeFormer: Decomposing Pre-trained Transformers for Faster Question Answering","date":"2020-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"StonyBrookNLP/deformer","path":"models/layers/transformer.py","file_url":"https://github.com/StonyBrookNLP/deformer/blob/HEAD/models/layers/transformer.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aa3f814034078dc9","mcp_get_code":{"code_sha256":"aa3f814034078dc9"}},{"arxiv_id":"2005.00558","paper":"/paper/pointer-constrained-text-generation-via","title":"POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training","date":"2020-05-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dreasysnail/POINTER","path":"pytorch_transformers/modeling_gpt2.py","file_url":"https://github.com/dreasysnail/POINTER/blob/HEAD/pytorch_transformers/modeling_gpt2.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"2005.00558","paper":"/paper/pointer-constrained-text-generation-via","title":"POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training","date":"2020-05-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dreasysnail/POINTER","path":"pytorch_transformers/modeling_bert.py","file_url":"https://github.com/dreasysnail/POINTER/blob/HEAD/pytorch_transformers/modeling_bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2005.00200","paper":"/paper/hero-hierarchical-encoder-for-video-language","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","date":"2020-05-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"linjieli222/HERO","path":"model/layers.py","file_url":"https://github.com/linjieli222/HERO/blob/HEAD/model/layers.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"29af270e862dd867","mcp_get_code":{"code_sha256":"29af270e862dd867"}},{"arxiv_id":"2004.13922","paper":"/paper/revisiting-pre-trained-models-for-chinese","title":"Revisiting Pre-Trained Models for Chinese Natural Language Processing","date":"2020-04-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ymcui/Chinese-PreTrained-XLNet","path":"src/modeling.py","file_url":"https://github.com/ymcui/Chinese-PreTrained-XLNet/blob/HEAD/src/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d08f324f950148de","mcp_get_code":{"code_sha256":"d08f324f950148de"}},{"arxiv_id":"2004.13922","paper":"/paper/revisiting-pre-trained-models-for-chinese","title":"Revisiting Pre-Trained Models for Chinese Natural Language Processing","date":"2020-04-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ymcui/Chinese-ELECTRA","path":"model/modeling.py","file_url":"https://github.com/ymcui/Chinese-ELECTRA/blob/HEAD/model/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9c6c6f379ebe0c8e","mcp_get_code":{"code_sha256":"9c6c6f379ebe0c8e"}},{"arxiv_id":"2004.11579","paper":"/paper/probabilistically-masked-language-model","title":"Probabilistically Masked Language Model Capable of Autoregressive Generation in Arbitrary Word Order","date":"2020-04-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huawei-noah/Pretrained-Language-Model","path":"PMLM/interactive_conditional_samples_sincos_acrostic.py","file_url":"https://github.com/huawei-noah/Pretrained-Language-Model/blob/HEAD/PMLM/interactive_conditional_samples_sincos_acrostic.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"44fc0426bec46486","mcp_get_code":{"code_sha256":"44fc0426bec46486"}},{"arxiv_id":"2004.11579","paper":"/paper/probabilistically-masked-language-model","title":"Probabilistically Masked Language Model Capable of Autoregressive Generation in Arbitrary Word Order","date":"2020-04-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"m-hahn/PMLM","path":"modeling.py","file_url":"https://github.com/m-hahn/PMLM/blob/HEAD/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d08f324f950148de","mcp_get_code":{"code_sha256":"d08f324f950148de"}},{"arxiv_id":"2004.09424","paper":"/paper/a-review-based-transformer-model-for","title":"Learning a Fine-Grained Review-based Transformer Model for Personalized Product Search","date":"2020-04-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kepingbi/ProdSearch","path":"models/neural.py","file_url":"https://github.com/kepingbi/ProdSearch/blob/HEAD/models/neural.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"2004.08022","paper":"/paper/rigid-formats-controlled-text-generation","title":"SongNet: Rigid Formats Controlled Text Generation","date":"2020-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shibing624/textgen","path":"textgen/language_modeling/songnet_model.py","file_url":"https://github.com/shibing624/textgen/blob/HEAD/textgen/language_modeling/songnet_model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2214122297c45b69","mcp_get_code":{"code_sha256":"2214122297c45b69"}},{"arxiv_id":"2004.08022","paper":"/paper/rigid-formats-controlled-text-generation","title":"SongNet: Rigid Formats Controlled Text Generation","date":"2020-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lipiji/SongNet","path":"utils.py","file_url":"https://github.com/lipiji/SongNet/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"71825b171fd640d8","mcp_get_code":{"code_sha256":"71825b171fd640d8"}},{"arxiv_id":"2004.07453","paper":"/paper/the-right-tool-for-the-job-matching-model-and","title":"The Right Tool for the Job: Matching Model and Instance Complexities","date":"2020-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"allenai/sledgehammer","path":"allennlp_overrides/pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/allenai/sledgehammer/blob/HEAD/allennlp_overrides/pytorch_pretrained_bert/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2004.06165","paper":"/paper/oscar-object-semantics-aligned-pre-training","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","date":"2020-04-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"milvlg/rosita","path":"rosita/modeling/pretrain_tasks/rosita.py","file_url":"https://github.com/milvlg/rosita/blob/HEAD/rosita/modeling/pretrain_tasks/rosita.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8d619e54294fb0b7","mcp_get_code":{"code_sha256":"8d619e54294fb0b7"}},{"arxiv_id":"2004.05707","paper":"/paper/vgcn-bert-augmenting-bert-with-graph","title":"VGCN-BERT: Augmenting BERT with Graph Embedding for Text Classification","date":"2020-04-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Louis-udm/VGCN-BERT","path":"old_version/pytorch_pretrained_bert/modeling_gpt2.py","file_url":"https://github.com/Louis-udm/VGCN-BERT/blob/HEAD/old_version/pytorch_pretrained_bert/modeling_gpt2.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"2004.05707","paper":"/paper/vgcn-bert-augmenting-bert-with-graph","title":"VGCN-BERT: Augmenting BERT with Graph Embedding for Text Classification","date":"2020-04-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Louis-udm/VGCN-BERT","path":"old_version/pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/Louis-udm/VGCN-BERT/blob/HEAD/old_version/pytorch_pretrained_bert/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3c06d11eadebd504","mcp_get_code":{"code_sha256":"3c06d11eadebd504"}},{"arxiv_id":"2004.05234","paper":"/paper/attend-and-decode-4d-fmri-task-state-decoding","title":"Attend and Decode: 4D fMRI Task State Decoding Using Attention Models","date":"2020-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2004.04037","paper":"/paper/dynabert-dynamic-bert-with-adaptive-width-and","title":"DynaBERT: Dynamic BERT with Adaptive Width and Depth","date":"2020-04-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huawei-noah/pretrained-language-model","path":"DynaBERT/transformers/modeling_bert.py","file_url":"https://github.com/huawei-noah/pretrained-language-model/blob/HEAD/DynaBERT/transformers/modeling_bert.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4ac7efa4e6383d65","mcp_get_code":{"code_sha256":"4ac7efa4e6383d65"}},{"arxiv_id":"2004.03829","paper":"/paper/exploring-versatile-generative-language-model","title":"Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning","date":"2020-04-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zlinao/VGLM","path":"pytorch_transformers/modeling_gpt2.py","file_url":"https://github.com/zlinao/VGLM/blob/HEAD/pytorch_transformers/modeling_gpt2.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"2004.03829","paper":"/paper/exploring-versatile-generative-language-model","title":"Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning","date":"2020-04-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zlinao/VGLM","path":"pytorch_transformers/modeling_bert.py","file_url":"https://github.com/zlinao/VGLM/blob/HEAD/pytorch_transformers/modeling_bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2004.03829","paper":"/paper/exploring-versatile-generative-language-model","title":"Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning","date":"2020-04-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zlinao/VGLM","path":"pytorch_transformers/modeling_distilbert.py","file_url":"https://github.com/zlinao/VGLM/blob/HEAD/pytorch_transformers/modeling_distilbert.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"69c6d14de8190cfb","mcp_get_code":{"code_sha256":"69c6d14de8190cfb"}},{"arxiv_id":"2004.02349","paper":"/paper/tapas-weakly-supervised-table-parsing-via-pre","title":"TAPAS: Weakly Supervised Table Parsing via Pre-training","date":"2020-04-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kamalkraj/TAPAS-TF2","path":"tapas/models/tf_utils.py","file_url":"https://github.com/kamalkraj/TAPAS-TF2/blob/HEAD/tapas/models/tf_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"44a49b752068dd08","mcp_get_code":{"code_sha256":"44a49b752068dd08"}},{"arxiv_id":"2002.10345","paper":"/paper/improving-bert-fine-tuning-via-self-ensemble","title":"Improving BERT Fine-Tuning via Self-Ensemble and Self-Distillation","date":"2020-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lonePatient/BERT-SDA","path":"models/transformers/modeling_bert.py","file_url":"https://github.com/lonePatient/BERT-SDA/blob/HEAD/models/transformers/modeling_bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"211753ba29188d4e","mcp_get_code":{"code_sha256":"211753ba29188d4e"}},{"arxiv_id":"2002.04745","paper":"/paper/on-layer-normalization-in-the-transformer-1","title":"On Layer Normalization in the Transformer Architecture","date":"2020-02-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"colorfulscoop/tfdlg","path":"tfdlg/activations.py","file_url":"https://github.com/colorfulscoop/tfdlg/blob/HEAD/tfdlg/activations.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d7b9cc73b75d3829","mcp_get_code":{"code_sha256":"d7b9cc73b75d3829"}},{"arxiv_id":"2002.03184","paper":"/paper/time-aware-large-kernel-convolutions","title":"Time-aware Large Kernel Convolutions","date":"2020-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lioutasb/TaLKConvolutions","path":"talkconv/talkconv_fairseq/talkconv.py","file_url":"https://github.com/lioutasb/TaLKConvolutions/blob/HEAD/talkconv/talkconv_fairseq/talkconv.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bddb1c75a5038e42","mcp_get_code":{"code_sha256":"bddb1c75a5038e42"}},{"arxiv_id":"2002.01808","paper":"/paper/k-adapter-infusing-knowledge-into-pre-trained","title":"K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters","date":"2020-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/K-Adapter","path":"pytorch_transformers/modeling_gpt2.py","file_url":"https://github.com/microsoft/K-Adapter/blob/HEAD/pytorch_transformers/modeling_gpt2.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"2002.01808","paper":"/paper/k-adapter-infusing-knowledge-into-pre-trained","title":"K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters","date":"2020-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/K-Adapter","path":"pytorch_transformers/modeling_bert.py","file_url":"https://github.com/microsoft/K-Adapter/blob/HEAD/pytorch_transformers/modeling_bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2002.01808","paper":"/paper/k-adapter-infusing-knowledge-into-pre-trained","title":"K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters","date":"2020-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/K-Adapter","path":"pytorch_transformers/modeling_distilbert.py","file_url":"https://github.com/microsoft/K-Adapter/blob/HEAD/pytorch_transformers/modeling_distilbert.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"69c6d14de8190cfb","mcp_get_code":{"code_sha256":"69c6d14de8190cfb"}},{"arxiv_id":"2002.00163","paper":"/paper/bridging-text-and-video-a-universal","title":"Bridging Text and Video: A Universal Multimodal Transformer for Video-Audio Scene-Aware Dialog","date":"2020-02-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ictnlp/DSTC8-AVSD","path":"VideoGPT2.py","file_url":"https://github.com/ictnlp/DSTC8-AVSD/blob/HEAD/VideoGPT2.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"2001.09099","paper":"/paper/tvr-a-large-scale-dataset-for-video-subtitle","title":"TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval","date":"2020-01-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jayleicn/TVCaption","path":"baselines/multimodal_transformer/transformer/model.py","file_url":"https://github.com/jayleicn/TVCaption/blob/HEAD/baselines/multimodal_transformer/transformer/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"69e3a274f98c15af","mcp_get_code":{"code_sha256":"69e3a274f98c15af"}},{"arxiv_id":"2001.01565","paper":"/paper/stance-detection-benchmark-how-robust-is-your","title":"Stance Detection Benchmark: How Robust Is Your Stance Detection?","date":"2020-01-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"UKPLab/mdl-stance-robustness","path":"module/common.py","file_url":"https://github.com/UKPLab/mdl-stance-robustness/blob/HEAD/module/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"53ebf6e30980ffe9","mcp_get_code":{"code_sha256":"53ebf6e30980ffe9"}},{"arxiv_id":"1912.02379","paper":"/paper/large-scale-pretraining-for-visual-dialog-a","title":"Large-scale Pretraining for Visual Dialog: A Simple State-of-the-Art Baseline","date":"2019-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vmurahari3/visdial-bert","path":"models/vilbert_dialog.py","file_url":"https://github.com/vmurahari3/visdial-bert/blob/HEAD/models/vilbert_dialog.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"1912.02315","paper":"/paper/12-in-1-multi-task-vision-and-language","title":"12-in-1: Multi-Task Vision and Language Representation Learning","date":"2019-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/vilbert-multi-task","path":"vilbert/basebert.py","file_url":"https://github.com/facebookresearch/vilbert-multi-task/blob/HEAD/vilbert/basebert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"1911.03631","paper":"/paper/hierarchical-graph-network-for-multi-hop","title":"Hierarchical Graph Network for Multi-hop Question Answering","date":"2019-11-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuwfan/HGN","path":"transformers/modeling_bert.py","file_url":"https://github.com/yuwfan/HGN/blob/HEAD/transformers/modeling_bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"211753ba29188d4e","mcp_get_code":{"code_sha256":"211753ba29188d4e"}},{"arxiv_id":"1911.03584","paper":"/paper/on-the-relationship-between-self-attention-1","title":"On the Relationship between Self-Attention and Convolutional Layers","date":"2019-11-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"epfml/attention-cnn","path":"models/bert.py","file_url":"https://github.com/epfml/attention-cnn/blob/HEAD/models/bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"1911.02896","paper":"/paper/contextualized-sparse-representation-with-1","title":"Contextualized Sparse Representations for Real-Time Open-Domain Question Answering","date":"2019-11-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jhyuklee/sparc","path":"modeling.py","file_url":"https://github.com/jhyuklee/sparc/blob/HEAD/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"40e9fee2e0b7e278","mcp_get_code":{"code_sha256":"40e9fee2e0b7e278"}},{"arxiv_id":"1911.02116","paper":"/paper/unsupervised-cross-lingual-representation-1","title":"Unsupervised Cross-lingual Representation Learning at Scale","date":"2019-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"66c21a3911091d29","mcp_get_code":{"code_sha256":"66c21a3911091d29"}},{"arxiv_id":"1911.00720","paper":"/paper/zen-pre-training-chinese-text-encoder","title":"ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations","date":"2019-11-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SVAIGBA/TwASP","path":"pytorch_pretrained_bert/modeling_gpt2.py","file_url":"https://github.com/SVAIGBA/TwASP/blob/HEAD/pytorch_pretrained_bert/modeling_gpt2.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"1911.00720","paper":"/paper/zen-pre-training-chinese-text-encoder","title":"ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations","date":"2019-11-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SVAIGBA/TwASP","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/SVAIGBA/TwASP/blob/HEAD/pytorch_pretrained_bert/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"1910.14520","paper":"/paper/do-multi-hop-readers-dream-of-reasoning","title":"Do Multi-hop Readers Dream of Reasoning Chains?","date":"2019-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"helloeve/bert-co-matching","path":"modeling.py","file_url":"https://github.com/helloeve/bert-co-matching/blob/HEAD/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d08f324f950148de","mcp_get_code":{"code_sha256":"d08f324f950148de"}},{"arxiv_id":"1910.12638","paper":"/paper/mockingjay-unsupervised-speech-representation","title":"Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders","date":"2019-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"samirsahoo007/Audio-and-Speech-Processing","path":"mockingjay/model.py","file_url":"https://github.com/samirsahoo007/Audio-and-Speech-Processing/blob/HEAD/mockingjay/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"1910.09796","paper":"/paper/kernel-graph-attention-network-for-fact","title":"Fine-grained Fact Verification with Kernel Graph Attention Network","date":"2019-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"1910.04732","paper":"/paper/structured-pruning-of-large-language-models","title":"Structured Pruning of Large Language Models","date":"2019-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Holldean/BERT-Pruning","path":"bert/modeling.py","file_url":"https://github.com/Holldean/BERT-Pruning/blob/HEAD/bert/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d08f324f950148de","mcp_get_code":{"code_sha256":"d08f324f950148de"}},{"arxiv_id":"1910.01500","paper":"/paper/mlperf-training-benchmark","title":"MLPerf Training Benchmark","date":"2019-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mlperf/training","path":"retired_benchmarks/bert/modeling.py","file_url":"https://github.com/mlperf/training/blob/HEAD/retired_benchmarks/bert/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"51d3bc0cfa6415a3","mcp_get_code":{"code_sha256":"51d3bc0cfa6415a3"}},{"arxiv_id":"1910.01108","paper":"/paper/distilbert-a-distilled-version-of-bert","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","date":"2019-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mkavim/finetune_bert","path":"finetune/modeling_distilbert.py","file_url":"https://github.com/mkavim/finetune_bert/blob/HEAD/finetune/modeling_distilbert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9bc31d06256e1691","mcp_get_code":{"code_sha256":"9bc31d06256e1691"}},{"arxiv_id":"1909.11942","paper":"/paper/albert-a-lite-bert-for-self-supervised","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","date":"2019-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Soikonomou/albert_final","path":"src/model/ALBERT/modeling_bert.py","file_url":"https://github.com/Soikonomou/albert_final/blob/HEAD/src/model/ALBERT/modeling_bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"211753ba29188d4e","mcp_get_code":{"code_sha256":"211753ba29188d4e"}},{"arxiv_id":"1909.11942","paper":"/paper/albert-a-lite-bert-for-self-supervised","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","date":"2019-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"brightmart/albert_zh","path":"modeling_google.py","file_url":"https://github.com/brightmart/albert_zh/blob/HEAD/modeling_google.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cb61421413d30b87","mcp_get_code":{"code_sha256":"cb61421413d30b87"}},{"arxiv_id":"1909.11942","paper":"/paper/albert-a-lite-bert-for-self-supervised","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","date":"2019-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/ALBERT","path":"modeling.py","file_url":"https://github.com/google-research/ALBERT/blob/HEAD/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"51d3bc0cfa6415a3","mcp_get_code":{"code_sha256":"51d3bc0cfa6415a3"}},{"arxiv_id":"1909.11059","paper":"/paper/unified-vision-language-pre-training-for","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","date":"2019-09-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LuoweiZhou/VLP","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/LuoweiZhou/VLP/blob/HEAD/pytorch_pretrained_bert/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"40e9fee2e0b7e278","mcp_get_code":{"code_sha256":"40e9fee2e0b7e278"}},{"arxiv_id":"1909.08041","paper":"/paper/revealing-the-importance-of-semantic","title":"Revealing the Importance of Semantic Retrieval for Machine Reading at Scale","date":"2019-09-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dujiaxin/semanticRetrievalMRS","path":"src/bert_model_variances/bert_maxout_clf.py","file_url":"https://github.com/dujiaxin/semanticRetrievalMRS/blob/HEAD/src/bert_model_variances/bert_maxout_clf.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"40e9fee2e0b7e278","mcp_get_code":{"code_sha256":"40e9fee2e0b7e278"}},{"arxiv_id":"1909.06356","paper":"/paper/addressing-semantic-drift-in-question","title":"Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering","date":"2019-09-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZhangShiyue/QGforQA","path":"LIB/bert/modeling.py","file_url":"https://github.com/ZhangShiyue/QGforQA/blob/HEAD/LIB/bert/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d08f324f950148de","mcp_get_code":{"code_sha256":"d08f324f950148de"}},{"arxiv_id":"1909.05311","paper":"/paper/graph-based-reasoning-over-heterogeneous","title":"Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering","date":"2019-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DecstionBack/AAAI_2020_CommonsenseQA","path":"pytorch_transformers/modeling_gpt2.py","file_url":"https://github.com/DecstionBack/AAAI_2020_CommonsenseQA/blob/HEAD/pytorch_transformers/modeling_gpt2.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"1909.05311","paper":"/paper/graph-based-reasoning-over-heterogeneous","title":"Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering","date":"2019-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DecstionBack/AAAI_2020_CommonsenseQA","path":"pytorch_transformers/modeling_bert.py","file_url":"https://github.com/DecstionBack/AAAI_2020_CommonsenseQA/blob/HEAD/pytorch_transformers/modeling_bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"1909.05311","paper":"/paper/graph-based-reasoning-over-heterogeneous","title":"Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering","date":"2019-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DecstionBack/AAAI_2020_CommonsenseQA","path":"pytorch_transformers/modeling_xlnet.py","file_url":"https://github.com/DecstionBack/AAAI_2020_CommonsenseQA/blob/HEAD/pytorch_transformers/modeling_xlnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b05b2bb38c0e4e72","mcp_get_code":{"code_sha256":"b05b2bb38c0e4e72"}},{"arxiv_id":"1909.05311","paper":"/paper/graph-based-reasoning-over-heterogeneous","title":"Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering","date":"2019-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DecstionBack/AAAI_2020_CommonsenseQA","path":"pytorch_transformers/modeling_xlm.py","file_url":"https://github.com/DecstionBack/AAAI_2020_CommonsenseQA/blob/HEAD/pytorch_transformers/modeling_xlm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b3c2618f6b7fb60c","mcp_get_code":{"code_sha256":"b3c2618f6b7fb60c"}},{"arxiv_id":"1909.05017","paper":"/paper/question-generation-by-transformers","title":"Question Generation by Transformers","date":"2019-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"artitw/BERT_QA","path":"bert_qa/activations.py","file_url":"https://github.com/artitw/BERT_QA/blob/HEAD/bert_qa/activations.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0194c7c12ff4afda","mcp_get_code":{"code_sha256":"0194c7c12ff4afda"}},{"arxiv_id":"1909.04849","paper":"/paper/a-discrete-hard-em-approach-for-weakly","title":"A Discrete Hard EM Approach for Weakly Supervised Question Answering","date":"2019-09-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shmsw25/qa-hard-em","path":"modeling.py","file_url":"https://github.com/shmsw25/qa-hard-em/blob/HEAD/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"40e9fee2e0b7e278","mcp_get_code":{"code_sha256":"40e9fee2e0b7e278"}},{"arxiv_id":"1909.02209","paper":"/paper/semantics-aware-bert-for-language","title":"Semantics-aware BERT for Language Understanding","date":"2019-09-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cooelf/SemBERT","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/cooelf/SemBERT/blob/HEAD/pytorch_pretrained_bert/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"1909.01187","paper":"/paper/encode-tag-realize-high-precision-text","title":"Encode, Tag, Realize: High-Precision Text Editing","date":"2019-09-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"a414351664/my_git_laser","path":"bert/modeling.py","file_url":"https://github.com/a414351664/my_git_laser/blob/HEAD/bert/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d08f324f950148de","mcp_get_code":{"code_sha256":"d08f324f950148de"}},{"arxiv_id":"1909.00252","paper":"/paper/humor-detection-a-transformer-gets-the-last","title":"Humor Detection: A Transformer Gets the Last Laugh","date":"2019-08-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"1908.09355","paper":"/paper/patient-knowledge-distillation-for-bert-model","title":"Patient Knowledge Distillation for BERT Model Compression","date":"2019-08-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Daniel-H-99/Patient-Knowledge-Distillation","path":"BERT/pytorch_pretrained_bert/modeling_gpt2.py","file_url":"https://github.com/Daniel-H-99/Patient-Knowledge-Distillation/blob/HEAD/BERT/pytorch_pretrained_bert/modeling_gpt2.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"1908.09355","paper":"/paper/patient-knowledge-distillation-for-bert-model","title":"Patient Knowledge Distillation for BERT Model Compression","date":"2019-08-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Daniel-H-99/Patient-Knowledge-Distillation","path":"BERT/pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/Daniel-H-99/Patient-Knowledge-Distillation/blob/HEAD/BERT/pytorch_pretrained_bert/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"1908.08962","paper":"/paper/well-read-students-learn-better-the-impact-of","title":"Well-Read Students Learn Better: On the Importance of Pre-training Compact Models","date":"2019-08-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Arthurizijar/Bert_Airport","path":"modeling.py","file_url":"https://github.com/Arthurizijar/Bert_Airport/blob/HEAD/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d08f324f950148de","mcp_get_code":{"code_sha256":"d08f324f950148de"}},{"arxiv_id":"1908.08345","paper":"/paper/text-summarization-with-pretrained-encoders","title":"Text Summarization with Pretrained Encoders","date":"2019-08-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aikawasho/BertSum","path":"src/models/neural.py","file_url":"https://github.com/aikawasho/BertSum/blob/HEAD/src/models/neural.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"1908.03265","paper":"/paper/on-the-variance-of-the-adaptive-learning-rate","title":"On the Variance of the Adaptive Learning Rate and Beyond","date":"2019-08-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kpe/params-flow","path":"params_flow/activations.py","file_url":"https://github.com/kpe/params-flow/blob/HEAD/params_flow/activations.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e6d5b83d23a4800c","mcp_get_code":{"code_sha256":"e6d5b83d23a4800c"}},{"arxiv_id":"1907.10529","paper":"/paper/spanbert-improving-pre-training-by","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","date":"2019-07-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amore-upf/masked-coreference","path":"bert/modeling.py","file_url":"https://github.com/amore-upf/masked-coreference/blob/HEAD/bert/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ecab128238ebf253","mcp_get_code":{"code_sha256":"ecab128238ebf253"}},{"arxiv_id":"1907.02684","paper":"/paper/head-driven-phrase-structure-grammar-parsing","title":"Head-Driven Phrase Structure Grammar Parsing on Penn Treebank","date":"2019-07-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DoodleJZ/HPSG-Neural-Parser","path":"src_division/pretrained_bert/modeling.py","file_url":"https://github.com/DoodleJZ/HPSG-Neural-Parser/blob/HEAD/src_division/pretrained_bert/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"40e9fee2e0b7e278","mcp_get_code":{"code_sha256":"40e9fee2e0b7e278"}},{"arxiv_id":"1906.08237","paper":"/paper/xlnet-generalized-autoregressive-pretraining","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","date":"2019-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"samwisegamjeee/pytorch-transformers","path":"pytorch_transformers/modeling_gpt2.py","file_url":"https://github.com/samwisegamjeee/pytorch-transformers/blob/HEAD/pytorch_transformers/modeling_gpt2.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"1906.08237","paper":"/paper/xlnet-generalized-autoregressive-pretraining","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","date":"2019-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"samwisegamjeee/pytorch-transformers","path":"pytorch_transformers/modeling_bert.py","file_url":"https://github.com/samwisegamjeee/pytorch-transformers/blob/HEAD/pytorch_transformers/modeling_bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"1906.08237","paper":"/paper/xlnet-generalized-autoregressive-pretraining","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","date":"2019-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"samwisegamjeee/pytorch-transformers","path":"pytorch_transformers/modeling_xlnet.py","file_url":"https://github.com/samwisegamjeee/pytorch-transformers/blob/HEAD/pytorch_transformers/modeling_xlnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b05b2bb38c0e4e72","mcp_get_code":{"code_sha256":"b05b2bb38c0e4e72"}},{"arxiv_id":"1906.08237","paper":"/paper/xlnet-generalized-autoregressive-pretraining","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","date":"2019-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"samwisegamjeee/pytorch-transformers","path":"pytorch_transformers/modeling_xlm.py","file_url":"https://github.com/samwisegamjeee/pytorch-transformers/blob/HEAD/pytorch_transformers/modeling_xlm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b3c2618f6b7fb60c","mcp_get_code":{"code_sha256":"b3c2618f6b7fb60c"}},{"arxiv_id":"1906.08230","paper":"/paper/evaluating-protein-transfer-learning-with","title":"Evaluating Protein Transfer Learning with TAPE","date":"2019-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"songlab-cal/tape","path":"tape/models/modeling_utils.py","file_url":"https://github.com/songlab-cal/tape/blob/HEAD/tape/models/modeling_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"5f49c78bf7533113","mcp_get_code":{"code_sha256":"5f49c78bf7533113"}},{"arxiv_id":"1906.05807","paper":"/paper/real-time-open-domain-question-answering-with","title":"Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index","date":"2019-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uwnlp/denspi","path":"bert.py","file_url":"https://github.com/uwnlp/denspi/blob/HEAD/bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"40e9fee2e0b7e278","mcp_get_code":{"code_sha256":"40e9fee2e0b7e278"}},{"arxiv_id":"1906.05394","paper":"/paper/neural-arabic-question-answering","title":"Neural Arabic Question Answering","date":"2019-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"husseinmozannar/SOQAL","path":"bert/modeling.py","file_url":"https://github.com/husseinmozannar/SOQAL/blob/HEAD/bert/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2c620cc10f52a944","mcp_get_code":{"code_sha256":"2c620cc10f52a944"}},{"arxiv_id":"1906.05317","paper":"/paper/comet-commonsense-transformers-for-automatic","title":"COMET: Commonsense Transformers for Automatic Knowledge Graph Construction","date":"2019-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"atcbosselut/comet-commonsense","path":"src/models/gpt.py","file_url":"https://github.com/atcbosselut/comet-commonsense/blob/HEAD/src/models/gpt.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"1906.03158","paper":"/paper/matching-the-blanks-distributional-similarity","title":"Matching the Blanks: Distributional Similarity for Relation Learning","date":"2019-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction","path":"src/model_utils.py","file_url":"https://github.com/uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction/blob/HEAD/src/model_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4dc5e7239221c929","mcp_get_code":{"code_sha256":"4dc5e7239221c929"}},{"arxiv_id":"1906.02900","paper":"/paper/compositional-questions-do-not-necessitate","title":"Compositional Questions Do Not Necessitate Multi-hop Reasoning","date":"2019-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shmsw25/single-hop-rc","path":"modeling.py","file_url":"https://github.com/shmsw25/single-hop-rc/blob/HEAD/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"40e9fee2e0b7e278","mcp_get_code":{"code_sha256":"40e9fee2e0b7e278"}},{"arxiv_id":"1906.01698","paper":"/paper/open-sesame-getting-inside-berts-linguistic","title":"Open Sesame: Getting Inside BERT's Linguistic Knowledge","date":"2019-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yongjie-lin/bert-opensesame","path":"bertviz/bertviz/pytorch_pretrained_bert/modeling_gpt2.py","file_url":"https://github.com/yongjie-lin/bert-opensesame/blob/HEAD/bertviz/bertviz/pytorch_pretrained_bert/modeling_gpt2.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"1906.01698","paper":"/paper/open-sesame-getting-inside-berts-linguistic","title":"Open Sesame: Getting Inside BERT's Linguistic Knowledge","date":"2019-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yongjie-lin/bert-opensesame","path":"bertviz/bertviz/pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/yongjie-lin/bert-opensesame/blob/HEAD/bertviz/bertviz/pytorch_pretrained_bert/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"1906.01698","paper":"/paper/open-sesame-getting-inside-berts-linguistic","title":"Open Sesame: Getting Inside BERT's Linguistic Knowledge","date":"2019-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yongjie-lin/bert-opensesame","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/yongjie-lin/bert-opensesame/blob/HEAD/pytorch_pretrained_bert/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"40e9fee2e0b7e278","mcp_get_code":{"code_sha256":"40e9fee2e0b7e278"}},{"arxiv_id":"1906.00346","paper":"/paper/190600346","title":"Pre-training of Graph Augmented Transformers for Medication Recommendation","date":"2019-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jshang123/G-Bert","path":"code/bert_models.py","file_url":"https://github.com/jshang123/G-Bert/blob/HEAD/code/bert_models.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"1905.12790","paper":"/paper/a-generalized-framework-of-sequence","title":"A Generalized Framework of Sequence Generation with Application to Undirected Sequence Models","date":"2019-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nyu-dl/dl4mt-seqgen","path":"src/model/transformer.py","file_url":"https://github.com/nyu-dl/dl4mt-seqgen/blob/HEAD/src/model/transformer.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"66c21a3911091d29","mcp_get_code":{"code_sha256":"66c21a3911091d29"}},{"arxiv_id":"1905.12616","paper":"/paper/defending-against-neural-fake-news","title":"Defending Against Neural Fake News","date":"2019-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rowanz/grover","path":"lm/utils.py","file_url":"https://github.com/rowanz/grover/blob/HEAD/lm/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"6558b9f62bb65244","mcp_get_code":{"code_sha256":"6558b9f62bb65244"}},{"arxiv_id":"1905.09217","paper":"/paper/deeper-text-understanding-for-ir-with","title":"Deeper Text Understanding for IR with Contextual Neural Language Modeling","date":"2019-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AdeDZY/SIGIR19-BERT-IR","path":"modeling.py","file_url":"https://github.com/AdeDZY/SIGIR19-BERT-IR/blob/HEAD/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"ecab128238ebf253","mcp_get_code":{"code_sha256":"ecab128238ebf253"}},{"arxiv_id":"1905.05583","paper":"/paper/how-to-fine-tune-bert-for-text-classification","title":"How to Fine-Tune BERT for Text Classification?","date":"2019-05-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GeorgeLuImmortal/Hierarchical-BERT-Model-with-Limited-Labelled-Data","path":"run_hbm.py","file_url":"https://github.com/GeorgeLuImmortal/Hierarchical-BERT-Model-with-Limited-Labelled-Data/blob/HEAD/run_hbm.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"835ff702d75feb5b","mcp_get_code":{"code_sha256":"835ff702d75feb5b"}},{"arxiv_id":"1904.06690","paper":"/paper/bert4rec-sequential-recommendation-with","title":"BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer","date":"2019-04-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FeiSun/BERT4Rec","path":"modeling.py","file_url":"https://github.com/FeiSun/BERT4Rec/blob/HEAD/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"50fd1894a0a439a6","mcp_get_code":{"code_sha256":"50fd1894a0a439a6"}},{"arxiv_id":"1903.09588","paper":"/paper/utilizing-bert-for-aspect-based-sentiment","title":"Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence","date":"2019-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HSLCY/ABSA-BERT-pair","path":"modeling.py","file_url":"https://github.com/HSLCY/ABSA-BERT-pair/blob/HEAD/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"40e9fee2e0b7e278","mcp_get_code":{"code_sha256":"40e9fee2e0b7e278"}},{"arxiv_id":"1902.10909","paper":"/paper/bert-for-joint-intent-classification-and-slot","title":"BERT for Joint Intent Classification and Slot Filling","date":"2019-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alibaba-damo-academy/spokennlp","path":"action-item-detection/script/modeling.py","file_url":"https://github.com/alibaba-damo-academy/spokennlp/blob/HEAD/action-item-detection/script/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d08f324f950148de","mcp_get_code":{"code_sha256":"d08f324f950148de"}},{"arxiv_id":"1902.01069","paper":"/paper/a-comprehensive-exploration-on-wikisql-with","title":"A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualization","date":"2019-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tanmay1618/text_to_sql_bert","path":"modeling_bert.py","file_url":"https://github.com/tanmay1618/text_to_sql_bert/blob/HEAD/modeling_bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"1902.01030","paper":"/paper/extracting-multiple-relations-in-one-pass","title":"Extracting Multiple-Relations in One-Pass with Pre-Trained Transformers","date":"2019-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"helloeve/mre-in-one-pass","path":"modeling.py","file_url":"https://github.com/helloeve/mre-in-one-pass/blob/HEAD/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d08f324f950148de","mcp_get_code":{"code_sha256":"d08f324f950148de"}},{"arxiv_id":"1901.10125","paper":"/paper/glyce-glyph-vectors-for-chinese-character","title":"Glyce: Glyph-vectors for Chinese Character Representations","date":"2019-01-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ShannonAI/glyce","path":"glyce/layers/bert_basic_model.py","file_url":"https://github.com/ShannonAI/glyce/blob/HEAD/glyce/layers/bert_basic_model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"56a9ab06b860b180","mcp_get_code":{"code_sha256":"56a9ab06b860b180"}},{"arxiv_id":"1901.10125","paper":"/paper/glyce-glyph-vectors-for-chinese-character","title":"Glyce: Glyph-vectors for Chinese Character Representations","date":"2019-01-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ShannonAI/glyce","path":"glyce/glyph_cnn_models/glyph_group_cnn.py","file_url":"https://github.com/ShannonAI/glyce/blob/HEAD/glyce/glyph_cnn_models/glyph_group_cnn.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"50e1ffed03f484ec","mcp_get_code":{"code_sha256":"50e1ffed03f484ec"}},{"arxiv_id":"1901.08746","paper":"/paper/biobert-a-pre-trained-biomedical-language","title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","date":"2019-01-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dmis-lab/bern","path":"biobert_ner/modeling.py","file_url":"https://github.com/dmis-lab/bern/blob/HEAD/biobert_ner/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"6558b9f62bb65244","mcp_get_code":{"code_sha256":"6558b9f62bb65244"}},{"arxiv_id":"1901.04085","paper":"/paper/passage-re-ranking-with-bert","title":"Passage Re-ranking with BERT","date":"2019-01-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nyu-dl/dl4marco-bert","path":"modeling.py","file_url":"https://github.com/nyu-dl/dl4marco-bert/blob/HEAD/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"ecab128238ebf253","mcp_get_code":{"code_sha256":"ecab128238ebf253"}},{"arxiv_id":"1811.11357","paper":"/paper/metropolis-hastings-generative-adversarial","title":"Metropolis-Hastings Generative Adversarial Networks","date":"2018-11-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fyumoto/MHGAN","path":"mhgan/ops.py","file_url":"https://github.com/fyumoto/MHGAN/blob/HEAD/mhgan/ops.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f34536b4c0da6083","mcp_get_code":{"code_sha256":"f34536b4c0da6083"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"62e7409a816626ac","mcp_get_code":{"code_sha256":"62e7409a816626ac"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"40e9fee2e0b7e278","mcp_get_code":{"code_sha256":"40e9fee2e0b7e278"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lonePatient/Bert-Multi-Label-Text-Classification","path":"pybert/model/albert/modeling_bert.py","file_url":"https://github.com/lonePatient/Bert-Multi-Label-Text-Classification/blob/HEAD/pybert/model/albert/modeling_bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"211753ba29188d4e","mcp_get_code":{"code_sha256":"211753ba29188d4e"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DeligientSloth/bert-tensorflow","path":"modeling.py","file_url":"https://github.com/DeligientSloth/bert-tensorflow/blob/HEAD/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d08f324f950148de","mcp_get_code":{"code_sha256":"d08f324f950148de"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"h4ste/oscar","path":"modeling.py","file_url":"https://github.com/h4ste/oscar/blob/HEAD/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a9f91ae77954f959","mcp_get_code":{"code_sha256":"a9f91ae77954f959"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qywu/Chinese-GPT","path":"chinese_gpt/gpt_modeling.py","file_url":"https://github.com/qywu/Chinese-GPT/blob/HEAD/chinese_gpt/gpt_modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"409ea40d28f93c7e","mcp_get_code":{"code_sha256":"409ea40d28f93c7e"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Impavidity/relogic","path":"relogic/logickit/inference/modeling.py","file_url":"https://github.com/Impavidity/relogic/blob/HEAD/relogic/logickit/inference/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"90e5e96897d48ebb","mcp_get_code":{"code_sha256":"90e5e96897d48ebb"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yifding/hetseq","path":"hetseq/bert_modeling.py","file_url":"https://github.com/yifding/hetseq/blob/HEAD/hetseq/bert_modeling.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1ada98e81f3ec64a","mcp_get_code":{"code_sha256":"1ada98e81f3ec64a"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eagle705/bert","path":"model/bert.py","file_url":"https://github.com/eagle705/bert/blob/HEAD/model/bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b7b8c4039090713d","mcp_get_code":{"code_sha256":"b7b8c4039090713d"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"re-search/DocProduct","path":"keras_bert/bert.py","file_url":"https://github.com/re-search/DocProduct/blob/HEAD/keras_bert/bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ac6081d51f65bb8c","mcp_get_code":{"code_sha256":"ac6081d51f65bb8c"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TeamLab/bert-gcn-for-paper-citation","path":"modeling.py","file_url":"https://github.com/TeamLab/bert-gcn-for-paper-citation/blob/HEAD/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"71e7e82f26b8d902","mcp_get_code":{"code_sha256":"71e7e82f26b8d902"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Satan012/BERT","path":"modeling.py","file_url":"https://github.com/Satan012/BERT/blob/HEAD/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ecab128238ebf253","mcp_get_code":{"code_sha256":"ecab128238ebf253"}},{"arxiv_id":"1804.05392","paper":"/paper/higher-order-coreference-resolution-with","title":"Higher-order Coreference Resolution with Coarse-to-fine Inference","date":"2018-04-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bkntr/coref-ee","path":"modeling.py","file_url":"https://github.com/bkntr/coref-ee/blob/HEAD/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"6558b9f62bb65244","mcp_get_code":{"code_sha256":"6558b9f62bb65244"}},{"arxiv_id":"1710.10903","paper":"/paper/graph-attention-networks","title":"Graph Attention Networks","date":"2017-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"davidpicard/homm","path":"src/model/network/gnn_layers.py","file_url":"https://github.com/davidpicard/homm/blob/HEAD/src/model/network/gnn_layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5c5300f98cecf9cc","mcp_get_code":{"code_sha256":"5c5300f98cecf9cc"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SCismycat/bert_code_view","path":"modeling.py","file_url":"https://github.com/SCismycat/bert_code_view/blob/HEAD/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ad92fc5681ce9dbd","mcp_get_code":{"code_sha256":"ad92fc5681ce9dbd"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"akanyaani/minGPTF","path":"mingptf/model.py","file_url":"https://github.com/akanyaani/minGPTF/blob/HEAD/mingptf/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b13d3f26a3b10784","mcp_get_code":{"code_sha256":"b13d3f26a3b10784"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"noriyukipy/tfdlg","path":"tfdlg/models.py","file_url":"https://github.com/noriyukipy/tfdlg/blob/HEAD/tfdlg/models.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d7b9cc73b75d3829","mcp_get_code":{"code_sha256":"d7b9cc73b75d3829"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"semicontinuity/nlp","path":"lopuhin_transformer_lm/lm/model.py","file_url":"https://github.com/semicontinuity/nlp/blob/HEAD/lopuhin_transformer_lm/lm/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0e399e430fc4851d","mcp_get_code":{"code_sha256":"0e399e430fc4851d"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"goldenbili/Bert_Test2","path":"modeling.py","file_url":"https://github.com/goldenbili/Bert_Test2/blob/HEAD/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2c620cc10f52a944","mcp_get_code":{"code_sha256":"2c620cc10f52a944"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yydai/bert_test","path":"modeling.py","file_url":"https://github.com/yydai/bert_test/blob/HEAD/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"6558b9f62bb65244","mcp_get_code":{"code_sha256":"6558b9f62bb65244"}},{"arxiv_id":"1606.08415","paper":"/paper/gaussian-error-linear-units-gelus","title":"Gaussian Error Linear Units (GELUs)","date":"2016-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nardeas/MHGAN","path":"mhgan/ops.py","file_url":"https://github.com/nardeas/MHGAN/blob/HEAD/mhgan/ops.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f34536b4c0da6083","mcp_get_code":{"code_sha256":"f34536b4c0da6083"}},{"arxiv_id":"1408.5882","paper":"/paper/convolutional-neural-networks-for-sentence","title":"Convolutional Neural Networks for Sentence Classification","date":"2014-08-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yschoi-nisp/AI-Grand-Challenge-2020","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/yschoi-nisp/AI-Grand-Challenge-2020/blob/HEAD/pytorch_pretrained_bert/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"40e9fee2e0b7e278","mcp_get_code":{"code_sha256":"40e9fee2e0b7e278"}},{"arxiv_id":"aaai_5722","paper":null,"title":"arXiv:aaai_5722","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"microsoft/Distilled-Sentence-Embedding","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/microsoft/Distilled-Sentence-Embedding/blob/HEAD/pytorch_pretrained_bert/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"aaai_32468","paper":null,"title":"arXiv:aaai_32468","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"airsplay/LXMERT","path":"src/lxrt/modeling.py","file_url":"https://github.com/airsplay/LXMERT/blob/HEAD/src/lxrt/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"aaai_29511","paper":null,"title":"arXiv:aaai_29511","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"lilujunai/Auto-Prox-AAAI24","path":"pycls/models/auto/autoformer_subnet.py","file_url":"https://github.com/lilujunai/Auto-Prox-AAAI24/blob/HEAD/pycls/models/auto/autoformer_subnet.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"08a5be1ffa0676e3","mcp_get_code":{"code_sha256":"08a5be1ffa0676e3"}},{"arxiv_id":"aaai_27969","paper":null,"title":"arXiv:aaai_27969","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"TianyuGoGO/XPNG","path":"models/modeling.py","file_url":"https://github.com/TianyuGoGO/XPNG/blob/HEAD/models/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"aaai_26578","paper":null,"title":"arXiv:aaai_26578","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"mlvlab/QAT","path":"utils/layers.py","file_url":"https://github.com/mlvlab/QAT/blob/HEAD/utils/layers.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b75e9c793d2a286a","mcp_get_code":{"code_sha256":"b75e9c793d2a286a"}},{"arxiv_id":"aaai_26528","paper":null,"title":"arXiv:aaai_26528","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"thnkinbtfly/SL2","path":"bert/modeling.py","file_url":"https://github.com/thnkinbtfly/SL2/blob/HEAD/bert/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d08f324f950148de","mcp_get_code":{"code_sha256":"d08f324f950148de"}},{"arxiv_id":"aaai_21674","paper":null,"title":"arXiv:aaai_21674","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"jsonW0/StrokeOrderEmbeddings","path":"glyce/glyce/layers/bert_basic_model.py","file_url":"https://github.com/jsonW0/StrokeOrderEmbeddings/blob/HEAD/glyce/glyce/layers/bert_basic_model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"56a9ab06b860b180","mcp_get_code":{"code_sha256":"56a9ab06b860b180"}},{"arxiv_id":"aaai_21674","paper":null,"title":"arXiv:aaai_21674","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"jsonW0/StrokeOrderEmbeddings","path":"glyce/glyce/glyph_cnn_models/glyph_group_cnn.py","file_url":"https://github.com/jsonW0/StrokeOrderEmbeddings/blob/HEAD/glyce/glyce/glyph_cnn_models/glyph_group_cnn.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"50e1ffed03f484ec","mcp_get_code":{"code_sha256":"50e1ffed03f484ec"}},{"arxiv_id":"aaai_21432","paper":null,"title":"arXiv:aaai_21432","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"microsoft/DialogLM","path":"DialogLM_UniLM/DialogLM/s2s_ft/modeling_decoding.py","file_url":"https://github.com/microsoft/DialogLM/blob/HEAD/DialogLM_UniLM/DialogLM/s2s_ft/modeling_decoding.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"40e9fee2e0b7e278","mcp_get_code":{"code_sha256":"40e9fee2e0b7e278"}},{"arxiv_id":"aaai_17659","paper":null,"title":"arXiv:aaai_17659","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"frankaging/Quasi-Attention-ABSA","path":"code/model/BERT.py","file_url":"https://github.com/frankaging/Quasi-Attention-ABSA/blob/HEAD/code/model/BERT.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"40e9fee2e0b7e278","mcp_get_code":{"code_sha256":"40e9fee2e0b7e278"}},{"arxiv_id":"aaai_16890","paper":null,"title":"arXiv:aaai_16890","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"LUMII-Syslab/RSE","path":"RSE_network.py","file_url":"https://github.com/LUMII-Syslab/RSE/blob/HEAD/RSE_network.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e96cf77a68146f83","mcp_get_code":{"code_sha256":"e96cf77a68146f83"}},{"arxiv_id":"Zheng_Towards_Learning_a_Generalist_Model_for_Embodied_Navigation_CVPR_2024_paper","paper":null,"title":"arXiv:Zheng_Towards_Learning_a_Generalist_Model_for_Embodied_Navigation_CVPR_2024_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"LaVi-Lab/NaviLLM","path":"models/vln_bert.py","file_url":"https://github.com/LaVi-Lab/NaviLLM/blob/HEAD/models/vln_bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c2f0705ed8e6f7e6","mcp_get_code":{"code_sha256":"c2f0705ed8e6f7e6"}},{"arxiv_id":"Yun_Pano-AVQA_Grounded_Audio-Visual_Question_Answering_on_360deg_Videos_ICCV_2021_paper","paper":null,"title":"arXiv:Yun_Pano-AVQA_Grounded_Audio-Visual_Question_Answering_on_360deg_Videos_ICCV_2021_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"hs-yn/PanoAVQA","path":"code/model/attention.py","file_url":"https://github.com/hs-yn/PanoAVQA/blob/HEAD/code/model/attention.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"56a9ab06b860b180","mcp_get_code":{"code_sha256":"56a9ab06b860b180"}},{"arxiv_id":"Yoshiyasu_Deformable_Mesh_Transformer_for_3D_Human_Mesh_Recovery_CVPR_2023_paper","paper":null,"title":"arXiv:Yoshiyasu_Deformable_Mesh_Transformer_for_3D_Human_Mesh_Recovery_CVPR_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"yusukey03012/DeFormer","path":"src/modeling/_gcnn.py","file_url":"https://github.com/yusukey03012/DeFormer/blob/HEAD/src/modeling/_gcnn.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c2f0705ed8e6f7e6","mcp_get_code":{"code_sha256":"c2f0705ed8e6f7e6"}},{"arxiv_id":"Go_Towards_Practical_Plug-and-Play_Diffusion_Models_CVPR_2023_paper","paper":null,"title":"arXiv:Go_Towards_Practical_Plug-and-Play_Diffusion_Models_CVPR_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"riiid/PPAP","path":"deepfloyd_if/model/nn.py","file_url":"https://github.com/riiid/PPAP/blob/HEAD/deepfloyd_if/model/nn.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f51cf2cbd3e598d8","mcp_get_code":{"code_sha256":"f51cf2cbd3e598d8"}},{"arxiv_id":"2025.findings-acl.583","paper":null,"title":"arXiv:2025.findings-acl.583","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"CSHaitao/LexiLaw","path":"src/modeling_chatglm.py","file_url":"https://github.com/CSHaitao/LexiLaw/blob/HEAD/src/modeling_chatglm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"43c9688838aff8b2","mcp_get_code":{"code_sha256":"43c9688838aff8b2"}},{"arxiv_id":"2024.findings-naacl.32","paper":null,"title":"arXiv:2024.findings-naacl.32","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"SnowYJ/sem_syn_separation","path":"optimus_separate_graph_sem_syntax_fuse_gpt2/pytorch_transformers/modeling_gpt2.py","file_url":"https://github.com/SnowYJ/sem_syn_separation/blob/HEAD/optimus_separate_graph_sem_syntax_fuse_gpt2/pytorch_transformers/modeling_gpt2.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"2024.findings-naacl.32","paper":null,"title":"arXiv:2024.findings-naacl.32","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"SnowYJ/sem_syn_separation","path":"optimus_separate_graph_sem_syntax_fuse_gpt2/pytorch_transformers/modeling_bert.py","file_url":"https://github.com/SnowYJ/sem_syn_separation/blob/HEAD/optimus_separate_graph_sem_syntax_fuse_gpt2/pytorch_transformers/modeling_bert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2024.findings-naacl.32","paper":null,"title":"arXiv:2024.findings-naacl.32","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"SnowYJ/sem_syn_separation","path":"optimus_separate_graph_sem_syntax_fuse_gpt2/pytorch_transformers/modeling_distilbert.py","file_url":"https://github.com/SnowYJ/sem_syn_separation/blob/HEAD/optimus_separate_graph_sem_syntax_fuse_gpt2/pytorch_transformers/modeling_distilbert.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"69c6d14de8190cfb","mcp_get_code":{"code_sha256":"69c6d14de8190cfb"}},{"arxiv_id":"2024.findings-acl.532","paper":null,"title":"arXiv:2024.findings-acl.532","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"kamigaito/SLAHAN","path":"bert/modeling.py","file_url":"https://github.com/kamigaito/SLAHAN/blob/HEAD/bert/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ecab128238ebf253","mcp_get_code":{"code_sha256":"ecab128238ebf253"}},{"arxiv_id":"2023.findings-eacl.123","paper":null,"title":"arXiv:2023.findings-eacl.123","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"yuping-wu/EDU-VL","path":"model/transformer_block.py","file_url":"https://github.com/yuping-wu/EDU-VL/blob/HEAD/model/transformer_block.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"2023.findings-acl.805","paper":null,"title":"arXiv:2023.findings-acl.805","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"iesl/Softmax-CPR","path":"src/summarization/dynamic_partition_model.py","file_url":"https://github.com/iesl/Softmax-CPR/blob/HEAD/src/summarization/dynamic_partition_model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d9dcfb510a5e2690","mcp_get_code":{"code_sha256":"d9dcfb510a5e2690"}},{"arxiv_id":"2023.findings-acl.765","paper":null,"title":"arXiv:2023.findings-acl.765","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"qtli/EIB","path":"code/EIB_model/modeling_gpt2.py","file_url":"https://github.com/qtli/EIB/blob/HEAD/code/EIB_model/modeling_gpt2.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"2023.emnlp-main.534","paper":null,"title":"arXiv:2023.emnlp-main.534","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"PreferredAI/superposed-topics","path":"gpt2/model.py","file_url":"https://github.com/PreferredAI/superposed-topics/blob/HEAD/gpt2/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"567f1a49bb4bce15","mcp_get_code":{"code_sha256":"567f1a49bb4bce15"}},{"arxiv_id":"2023.acl-long.693","paper":null,"title":"arXiv:2023.acl-long.693","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"AI4Bharat/IndicBERT","path":"train/modeling.py","file_url":"https://github.com/AI4Bharat/IndicBERT/blob/HEAD/train/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ce6758ab463bc4a8","mcp_get_code":{"code_sha256":"ce6758ab463bc4a8"}},{"arxiv_id":"2022.findings-naacl.131","paper":null,"title":"arXiv:2022.findings-naacl.131","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"RUCAIBox/SAFE","path":"utils/layers.py","file_url":"https://github.com/RUCAIBox/SAFE/blob/HEAD/utils/layers.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b75e9c793d2a286a","mcp_get_code":{"code_sha256":"b75e9c793d2a286a"}},{"arxiv_id":"2022.findings-emnlp.520","paper":null,"title":"arXiv:2022.findings-emnlp.520","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"rajammanabrolu/C2PO","path":"C2PO/src/models/gpt.py","file_url":"https://github.com/rajammanabrolu/C2PO/blob/HEAD/C2PO/src/models/gpt.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8d23fbe2b99b840b","mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"arxiv_id":"2022.findings-emnlp.427","paper":null,"title":"arXiv:2022.findings-emnlp.427","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"kgarg8/FullTextKP","path":"summarization/bert_model.py","file_url":"https://github.com/kgarg8/FullTextKP/blob/HEAD/summarization/bert_model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"40e9fee2e0b7e278","mcp_get_code":{"code_sha256":"40e9fee2e0b7e278"}},{"arxiv_id":"2022.acl-long.56","paper":null,"title":"arXiv:2022.acl-long.56","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"juntaoy/dali-bridging","path":"extract_bert_features/modeling.py","file_url":"https://github.com/juntaoy/dali-bridging/blob/HEAD/extract_bert_features/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"6558b9f62bb65244","mcp_get_code":{"code_sha256":"6558b9f62bb65244"}},{"arxiv_id":"2021.findings-emnlp.347","paper":null,"title":"arXiv:2021.findings-emnlp.347","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"wentinghome/AMG","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/wentinghome/AMG/blob/HEAD/pytorch_pretrained_bert/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"40e9fee2e0b7e278","mcp_get_code":{"code_sha256":"40e9fee2e0b7e278"}},{"arxiv_id":"2021.emnlp-main.518","paper":null,"title":"arXiv:2021.emnlp-main.518","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"hyounghk/NDH-FULL","path":"tasks/NDH_full/modeling.py","file_url":"https://github.com/hyounghk/NDH-FULL/blob/HEAD/tasks/NDH_full/modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"2020.acl-main.192","paper":null,"title":"arXiv:2020.acl-main.192","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"neulab/cmu-multinlp","path":"brat_multitask/modules/bert_modeling.py","file_url":"https://github.com/neulab/cmu-multinlp/blob/HEAD/brat_multitask/modules/bert_modeling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"arxiv_id":"136960462","paper":null,"title":"arXiv:136960462","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"levymsn/CQA-CRCT","path":"CRCT/backbone/vilbert.py","file_url":"https://github.com/levymsn/CQA-CRCT/blob/HEAD/CRCT/backbone/vilbert.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fdc64f4c72036ae4","mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}}]}