{"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/create-position-ids-from-input-ids","entry":"create_position_ids_from_input_ids","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":41,"n_papers_ran":30,"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":16,"n_samples_ran":8,"n_samples_fingerprinted":6,"n_places":43,"n_places_pointer_only":11,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":5,"ran_fixture":0,"ran":3,"unverified":8},"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":"2411.11919","paper":"/paper/vl-uncertainty-detecting-hallucination-in","title":"VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimation","date":"2024-11-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JT-Sun/Filtering-WoRA","path":"models/xroberta.py","file_url":"https://github.com/JT-Sun/Filtering-WoRA/blob/HEAD/models/xroberta.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":"38f46ef4e03fee1c","mcp_get_code":{"code_sha256":"38f46ef4e03fee1c"}},{"arxiv_id":"2411.07404","paper":"/paper/controllable-context-sensitivity-and-the-knob","title":"Controllable Context Sensitivity and the Knob Behind It","date":"2024-11-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kdu4108/context-vs-prior-finetuning","path":"model_utils/mi_utils.py","file_url":"https://github.com/kdu4108/context-vs-prior-finetuning/blob/HEAD/model_utils/mi_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"640aef5d8b077b96","mcp_get_code":{"code_sha256":"640aef5d8b077b96"}},{"arxiv_id":"2410.06554","paper":"/paper/the-accuracy-paradox-in-rlhf-when-better","title":"The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models","date":"2024-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"EIT-NLP/AccuracyParadox-RLHF","path":"reward_modeling/my_longformer.py","file_url":"https://github.com/EIT-NLP/AccuracyParadox-RLHF/blob/HEAD/reward_modeling/my_longformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ce0ed06559b93e81","mcp_get_code":{"code_sha256":"ce0ed06559b93e81"}},{"arxiv_id":"2409.10927","paper":"/paper/propulsion-steering-llm-with-tiny-fine-tuning","title":"Propulsion: Steering LLM with Tiny Fine-Tuning","date":"2024-09-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Kowsher/Propulsion","path":"Src/LM/roberta.py","file_url":"https://github.com/Kowsher/Propulsion/blob/HEAD/Src/LM/roberta.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"38f46ef4e03fee1c","mcp_get_code":{"code_sha256":"38f46ef4e03fee1c"}},{"arxiv_id":"2409.01193","paper":"/paper/clibe-detecting-dynamic-backdoors-in","title":"CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models","date":"2024-09-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"raytsang123/clibe","path":"discriminative_backdoors/detection/modeling_roberta.py","file_url":"https://github.com/raytsang123/clibe/blob/HEAD/discriminative_backdoors/detection/modeling_roberta.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":"38f46ef4e03fee1c","mcp_get_code":{"code_sha256":"38f46ef4e03fee1c"}},{"arxiv_id":"2408.12928","paper":"/paper/pargo-bridging-vision-language-with-partial","title":"ParGo: Bridging Vision-Language with Partial and Global Views","date":"2024-08-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bytedance/pargo","path":"pargo/backbone/language/xlm_roberta.py","file_url":"https://github.com/bytedance/pargo/blob/HEAD/pargo/backbone/language/xlm_roberta.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"38f46ef4e03fee1c","mcp_get_code":{"code_sha256":"38f46ef4e03fee1c"}},{"arxiv_id":"2406.16030","paper":"/paper/zero-shot-cross-lingual-ner-using-phonemic","title":"Zero-Shot Cross-Lingual NER Using Phonemic Representations for Low-Resource Languages","date":"2024-06-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Gabriel819/zeroshot_ner","path":"model/xphonebert.py","file_url":"https://github.com/Gabriel819/zeroshot_ner/blob/HEAD/model/xphonebert.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":"d4903874fdec3763","mcp_get_code":{"code_sha256":"d4903874fdec3763"}},{"arxiv_id":"2405.15551","paper":"/paper/thinking-forward-memory-efficient-federated","title":"Thinking Forward: Memory-Efficient Federated Finetuning of Language Models","date":"2024-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Astuary/Spry","path":"models/mezo_modeling_roberta.py","file_url":"https://github.com/Astuary/Spry/blob/HEAD/models/mezo_modeling_roberta.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"38f46ef4e03fee1c","mcp_get_code":{"code_sha256":"38f46ef4e03fee1c"}},{"arxiv_id":"2403.06754","paper":"/paper/alarm-align-language-models-via-hierarchical","title":"ALaRM: Align Language Models via Hierarchical Rewards Modeling","date":"2024-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"halfrot/ALaRM","path":"long-form-QA/my_longformer.py","file_url":"https://github.com/halfrot/ALaRM/blob/HEAD/long-form-QA/my_longformer.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":"ce0ed06559b93e81","mcp_get_code":{"code_sha256":"ce0ed06559b93e81"}},{"arxiv_id":"2401.13478","paper":"/paper/scimmir-benchmarking-scientific-multi-modal","title":"SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval","date":"2024-01-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wusiwei0410/scimmir","path":"src/LLM_models/My_kosmos2.py","file_url":"https://github.com/wusiwei0410/scimmir/blob/HEAD/src/LLM_models/My_kosmos2.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"38f46ef4e03fee1c","mcp_get_code":{"code_sha256":"38f46ef4e03fee1c"}},{"arxiv_id":"2311.18259","paper":"/paper/ego-exo4d-understanding-skilled-human","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","date":"2023-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/EgoVLPv2","path":"EgoVLPv2/model/roberta.py","file_url":"https://github.com/facebookresearch/EgoVLPv2/blob/HEAD/EgoVLPv2/model/roberta.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":"da1c54dffed5d60c","mcp_get_code":{"code_sha256":"da1c54dffed5d60c"}},{"arxiv_id":"2307.08941","paper":"/paper/ntk-approximating-mlp-fusion-for-efficient","title":"MLP Fusion: Towards Efficient Fine-tuning of Dense and Mixture-of-Experts Language Models","date":"2023-07-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"weitianxin/MLP_Fusion","path":"models/roberta/modeling_roberta.py","file_url":"https://github.com/weitianxin/MLP_Fusion/blob/HEAD/models/roberta/modeling_roberta.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"38f46ef4e03fee1c","mcp_get_code":{"code_sha256":"38f46ef4e03fee1c"}},{"arxiv_id":"2307.08941","paper":"/paper/ntk-approximating-mlp-fusion-for-efficient","title":"MLP Fusion: Towards Efficient Fine-tuning of Dense and Mixture-of-Experts Language Models","date":"2023-07-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"weitianxin/MLP_Fusion","path":"models/roberta/modeling_flax_roberta.py","file_url":"https://github.com/weitianxin/MLP_Fusion/blob/HEAD/models/roberta/modeling_flax_roberta.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6697ea7953dcb4c6","mcp_get_code":{"code_sha256":"6697ea7953dcb4c6"}},{"arxiv_id":"2306.14893","paper":"/paper/longcoder-a-long-range-pre-trained-language","title":"LongCoder: A Long-Range Pre-trained Language Model for Code Completion","date":"2023-06-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/codebert","path":"LongCoder/longcoder.py","file_url":"https://github.com/microsoft/codebert/blob/HEAD/LongCoder/longcoder.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":"da1c54dffed5d60c","mcp_get_code":{"code_sha256":"da1c54dffed5d60c"}},{"arxiv_id":"2305.16307","paper":"/paper/indictrans2-towards-high-quality-and","title":"IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages","date":"2023-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ai4bharat/indictrans2","path":"huggingface_interface/modeling_indictrans.py","file_url":"https://github.com/ai4bharat/indictrans2/blob/HEAD/huggingface_interface/modeling_indictrans.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":"336749dd7d699ef6","mcp_get_code":{"code_sha256":"336749dd7d699ef6"}},{"arxiv_id":"2305.14695","paper":"/paper/a-causal-view-of-entity-bias-in-large","title":"A Causal View of Entity Bias in (Large) Language Models","date":"2023-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"luka-group/causal-view-of-entity-bias","path":"roberta.py","file_url":"https://github.com/luka-group/causal-view-of-entity-bias/blob/HEAD/roberta.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":"2e2109ff964bfb9c","mcp_get_code":{"code_sha256":"2e2109ff964bfb9c"}},{"arxiv_id":"2305.13731","paper":"/paper/text-is-all-you-need-learning-language","title":"Text Is All You Need: Learning Language Representations for Sequential Recommendation","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aaronheee/recformer","path":"recformer/models.py","file_url":"https://github.com/aaronheee/recformer/blob/HEAD/recformer/models.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":"6e4b78022b53cbdb","mcp_get_code":{"code_sha256":"6e4b78022b53cbdb"}},{"arxiv_id":"2305.00593","paper":"/paper/reliable-gradient-free-and-likelihood-free","title":"Reliable Gradient-free and Likelihood-free Prompt Tuning","date":"2023-04-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"maohaos2/SBI_LLM","path":"models/modeling_roberta.py","file_url":"https://github.com/maohaos2/SBI_LLM/blob/HEAD/models/modeling_roberta.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bbfc47d976ee7225","mcp_get_code":{"code_sha256":"bbfc47d976ee7225"}},{"arxiv_id":"2303.17395","paper":"/paper/wavcaps-a-chatgpt-assisted-weakly-labelled","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","date":"2023-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gzhu06/cacophony","path":"src/caco/text_models/roberta_text_model.py","file_url":"https://github.com/gzhu06/cacophony/blob/HEAD/src/caco/text_models/roberta_text_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"12a1bb1ff6ec7d06","mcp_get_code":{"code_sha256":"12a1bb1ff6ec7d06"}},{"arxiv_id":"2211.15029","paper":"/paper/diffusionbert-improving-generative-masked","title":"DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models","date":"2022-11-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hzfinfdu/diffusion-bert","path":"models/modeling_roberta.py","file_url":"https://github.com/hzfinfdu/diffusion-bert/blob/HEAD/models/modeling_roberta.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":"38f46ef4e03fee1c","mcp_get_code":{"code_sha256":"38f46ef4e03fee1c"}},{"arxiv_id":"2210.04135","paper":"/paper/volta-vision-language-transformer-with-weakly","title":"VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignment","date":"2022-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ShramanPramanick/VoLTA","path":"Pre-training/roberta.py","file_url":"https://github.com/ShramanPramanick/VoLTA/blob/HEAD/Pre-training/roberta.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":"da1c54dffed5d60c","mcp_get_code":{"code_sha256":"da1c54dffed5d60c"}},{"arxiv_id":"2209.14279","paper":"/paper/causal-proxy-models-for-concept-based-model","title":"Causal Proxy Models for Concept-Based Model Explanations","date":"2022-09-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"frankaging/causal-proxy-model","path":"models/modelings_roberta.py","file_url":"https://github.com/frankaging/causal-proxy-model/blob/HEAD/models/modelings_roberta.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"38f46ef4e03fee1c","mcp_get_code":{"code_sha256":"38f46ef4e03fee1c"}},{"arxiv_id":"2205.06435","paper":"/paper/tie-topological-information-enhanced","title":"TIE: Topological Information Enhanced Structural Reading Comprehension on Web Pages","date":"2022-05-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"x-lance/tie","path":"markuplmft/models/markuplm/modeling_markuplm.py","file_url":"https://github.com/x-lance/tie/blob/HEAD/markuplmft/models/markuplm/modeling_markuplm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"38f46ef4e03fee1c","mcp_get_code":{"code_sha256":"38f46ef4e03fee1c"}},{"arxiv_id":"2204.10298","paper":"/paper/diffcse-difference-based-contrastive-learning","title":"DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings","date":"2022-04-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"voidism/diffcse","path":"modeling_roberta.py","file_url":"https://github.com/voidism/diffcse/blob/HEAD/modeling_roberta.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":"d4903874fdec3763","mcp_get_code":{"code_sha256":"d4903874fdec3763"}},{"arxiv_id":"2204.05999","paper":"/paper/incoder-a-generative-model-for-code-infilling","title":"InCoder: A Generative Model for Code Infilling and Synthesis","date":"2022-04-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eth-sri/sven","path":"sven/model.py","file_url":"https://github.com/eth-sri/sven/blob/HEAD/sven/model.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":"336749dd7d699ef6","mcp_get_code":{"code_sha256":"336749dd7d699ef6"}},{"arxiv_id":"2202.13669","paper":"/paper/lilt-a-simple-yet-effective-language","title":"LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding","date":"2022-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jpWang/LiLT","path":"LiLTfinetune/models/LiLTRobertaLike/modeling_LiLTRobertaLike.py","file_url":"https://github.com/jpWang/LiLT/blob/HEAD/LiLTfinetune/models/LiLTRobertaLike/modeling_LiLTRobertaLike.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":"da1c54dffed5d60c","mcp_get_code":{"code_sha256":"da1c54dffed5d60c"}},{"arxiv_id":"2202.08005","paper":"/paper/should-you-mask-15-in-masked-language","title":"Should You Mask 15% in Masked Language Modeling?","date":"2022-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-nlp/dinkytrain","path":"huggingface/modeling_roberta_prelayernorm.py","file_url":"https://github.com/princeton-nlp/dinkytrain/blob/HEAD/huggingface/modeling_roberta_prelayernorm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"38f46ef4e03fee1c","mcp_get_code":{"code_sha256":"38f46ef4e03fee1c"}},{"arxiv_id":"2202.07962","paper":"/paper/revisiting-parameter-efficient-tuning-are-we","title":"Revisiting Parameter-Efficient Tuning: Are We Really There Yet?","date":"2022-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"guanzhchen/petuning","path":"model/roberta/modeling_roberta.py","file_url":"https://github.com/guanzhchen/petuning/blob/HEAD/model/roberta/modeling_roberta.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"38f46ef4e03fee1c","mcp_get_code":{"code_sha256":"38f46ef4e03fee1c"}},{"arxiv_id":"2202.07962","paper":"/paper/revisiting-parameter-efficient-tuning-are-we","title":"Revisiting Parameter-Efficient Tuning: Are We Really There Yet?","date":"2022-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"guanzhchen/petuning","path":"model/roberta/modeling_flax_roberta.py","file_url":"https://github.com/guanzhchen/petuning/blob/HEAD/model/roberta/modeling_flax_roberta.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6697ea7953dcb4c6","mcp_get_code":{"code_sha256":"6697ea7953dcb4c6"}},{"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/embeddings.py","file_url":"https://github.com/e-bug/volta/blob/HEAD/volta/embeddings.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":"d4903874fdec3763","mcp_get_code":{"code_sha256":"d4903874fdec3763"}},{"arxiv_id":"2201.03514","paper":"/paper/black-box-tuning-for-language-model-as-a","title":"Black-Box Tuning for Language-Model-as-a-Service","date":"2022-01-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jubgjf/plmtuningcompetition","path":"models/deep_modeling_roberta.py","file_url":"https://github.com/jubgjf/plmtuningcompetition/blob/HEAD/models/deep_modeling_roberta.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":"bbfc47d976ee7225","mcp_get_code":{"code_sha256":"bbfc47d976ee7225"}},{"arxiv_id":"2107.14035","paper":"/paper/prototransformer-a-meta-learning-approach-to","title":"ProtoTransformer: A Meta-Learning Approach to Providing Student Feedback","date":"2021-07-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mhw32/prototransformer-public","path":"src/models/monkeypatch.py","file_url":"https://github.com/mhw32/prototransformer-public/blob/HEAD/src/models/monkeypatch.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3976dab6c53b60b0","mcp_get_code":{"code_sha256":"3976dab6c53b60b0"}},{"arxiv_id":"2107.00910","paper":"/paper/learned-token-pruning-for-transformers","title":"Learned Token Pruning for Transformers","date":"2021-07-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kssteven418/ltp","path":"src/transformers/models/ltp/modeling_ltp.py","file_url":"https://github.com/kssteven418/ltp/blob/HEAD/src/transformers/models/ltp/modeling_ltp.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":"83995d570ba89e6d","mcp_get_code":{"code_sha256":"83995d570ba89e6d"}},{"arxiv_id":"2104.08247","paper":"/paper/what-to-pre-train-on-efficient-intermediate","title":"What to Pre-Train on? Efficient Intermediate Task Selection","date":"2021-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adapter-hub/efficient-task-transfer","path":"task_selection/modeling/modeling_roberta.py","file_url":"https://github.com/adapter-hub/efficient-task-transfer/blob/HEAD/task_selection/modeling/modeling_roberta.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bbfc47d976ee7225","mcp_get_code":{"code_sha256":"bbfc47d976ee7225"}},{"arxiv_id":"2005.00796","paper":"/paper/a-simple-language-model-for-task-oriented","title":"A Simple Language Model for Task-Oriented Dialogue","date":"2020-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/simpletod","path":"models/modeling_utils.py","file_url":"https://github.com/salesforce/simpletod/blob/HEAD/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":"d4f3546f2ecff417","mcp_get_code":{"code_sha256":"d4f3546f2ecff417"}},{"arxiv_id":"aaai_33874","paper":null,"title":"arXiv:aaai_33874","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"txsun1997/Black-Box-Tuning","path":"models/deep_modeling_roberta.py","file_url":"https://github.com/txsun1997/Black-Box-Tuning/blob/HEAD/models/deep_modeling_roberta.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bbfc47d976ee7225","mcp_get_code":{"code_sha256":"bbfc47d976ee7225"}},{"arxiv_id":"aaai_29850","paper":null,"title":"arXiv:aaai_29850","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"ozyyshr/FocalReasoner","path":"modeling_roberta_svo_graph.py","file_url":"https://github.com/ozyyshr/FocalReasoner/blob/HEAD/modeling_roberta_svo_graph.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":"da1c54dffed5d60c","mcp_get_code":{"code_sha256":"da1c54dffed5d60c"}},{"arxiv_id":"2024.findings-emnlp.286","paper":null,"title":"arXiv:2024.findings-emnlp.286","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"kgarg8/Stanceformer","path":"roberta/modeling_roberta.py","file_url":"https://github.com/kgarg8/Stanceformer/blob/HEAD/roberta/modeling_roberta.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"38f46ef4e03fee1c","mcp_get_code":{"code_sha256":"38f46ef4e03fee1c"}},{"arxiv_id":"2024.findings-acl.164","paper":null,"title":"arXiv:2024.findings-acl.164","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"potter-Zhang/Selective-Prefix-Tuning","path":"model/roberta_select.py","file_url":"https://github.com/potter-Zhang/Selective-Prefix-Tuning/blob/HEAD/model/roberta_select.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":"38f46ef4e03fee1c","mcp_get_code":{"code_sha256":"38f46ef4e03fee1c"}},{"arxiv_id":"2023.findings-emnlp.107","paper":null,"title":"arXiv:2023.findings-emnlp.107","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"chenxn2020/GOSE","path":"GOSEfinetune/models/LiLTRobertaLike/modeling_LiLTRobertaLike.py","file_url":"https://github.com/chenxn2020/GOSE/blob/HEAD/GOSEfinetune/models/LiLTRobertaLike/modeling_LiLTRobertaLike.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":"da1c54dffed5d60c","mcp_get_code":{"code_sha256":"da1c54dffed5d60c"}},{"arxiv_id":"2023.acl-long.264","paper":null,"title":"arXiv:2023.acl-long.264","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"DAMO-NLP-SG/MVCR","path":"src/modeling_vaeroberta.py","file_url":"https://github.com/DAMO-NLP-SG/MVCR/blob/HEAD/src/modeling_vaeroberta.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"5ba2b30d6672d2b0","mcp_get_code":{"code_sha256":"5ba2b30d6672d2b0"}},{"arxiv_id":"2023.acl-long.182","paper":null,"title":"arXiv:2023.acl-long.182","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Yuanhy1997/HyPe","path":"hype_modeling_roberta.py","file_url":"https://github.com/Yuanhy1997/HyPe/blob/HEAD/hype_modeling_roberta.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"38f46ef4e03fee1c","mcp_get_code":{"code_sha256":"38f46ef4e03fee1c"}},{"arxiv_id":"2021.emnlp-main.154","paper":null,"title":"arXiv:2021.emnlp-main.154","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Hazelsuko07/TextHide","path":"transformers_hide/modeling_roberta.py","file_url":"https://github.com/Hazelsuko07/TextHide/blob/HEAD/transformers_hide/modeling_roberta.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5b2390deea2200c9","mcp_get_code":{"code_sha256":"5b2390deea2200c9"}}]}