{"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/load-vocab","entry":"load_vocab","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":107,"n_papers_ran":45,"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":55,"n_samples_ran":14,"n_samples_fingerprinted":0,"n_places":118,"n_places_pointer_only":11,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":7,"ran_fixture":0,"ran":6,"unverified":41},"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":"2608.02939","paper":"/paper/arxiv-2608-02939","title":"Federated generative event models for tokenized electronic health records","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"bbj-lab/coreopsis","path":"recipes/analyze-site-data.py","file_url":"https://github.com/bbj-lab/coreopsis/blob/HEAD/recipes/analyze-site-data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d2c193ef453aefa3","mcp_get_code":{"code_sha256":"d2c193ef453aefa3"}},{"arxiv_id":"2601.15771","paper":"/paper/arxiv-2601-15771","title":"Rethinking Drug-Drug Interaction Modeling as Generalizable Relation Learning","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"SZU-ADDG/GenRel-DDI","path":"model.py","file_url":"https://github.com/SZU-ADDG/GenRel-DDI/blob/HEAD/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8c1c03859eece728","mcp_get_code":{"code_sha256":"8c1c03859eece728"}},{"arxiv_id":"2505.13027","paper":"/paper/unpacking-positional-encoding-in-transformers","title":"Unpacking Positional Encoding in Transformers: A Spectral Analysis of Content-Position Coupling","date":"2025-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Qihuai27/Deposit-Pattern-Research","path":"dis_gen/1_data_preparation/data-gen.py","file_url":"https://github.com/Qihuai27/Deposit-Pattern-Research/blob/HEAD/dis_gen/1_data_preparation/data-gen.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4f79bf4713e7fbec","mcp_get_code":{"code_sha256":"4f79bf4713e7fbec"}},{"arxiv_id":"2412.06141","paper":"/paper/mmedpo-aligning-medical-vision-language","title":"MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization","date":"2024-12-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aiming-lab/mmedpo","path":"curation/Sample_Zero-Shot_Grounding_RSNA/models/tokenization_bert.py","file_url":"https://github.com/aiming-lab/mmedpo/blob/HEAD/curation/Sample_Zero-Shot_Grounding_RSNA/models/tokenization_bert.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e7fbc7a74a3457c7","mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"arxiv_id":"2411.15245","paper":"/paper/anytext2-visual-text-generation-and-editing","title":"AnyText2: Visual Text Generation and Editing With Customizable Attributes","date":"2024-11-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tyxsspa/anytext2","path":"bert_tokenizer.py","file_url":"https://github.com/tyxsspa/anytext2/blob/HEAD/bert_tokenizer.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":"aaf1cb2c01043065","mcp_get_code":{"code_sha256":"aaf1cb2c01043065"}},{"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/tokenization_bert.py","file_url":"https://github.com/JT-Sun/Filtering-WoRA/blob/HEAD/models/tokenization_bert.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e7fbc7a74a3457c7","mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"arxiv_id":"2411.02669","paper":"/paper/semantic-aligned-adversarial-evolution","title":"Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack","date":"2024-11-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiaxiaojunqaq/sa-aet","path":"models/tokenization_bert.py","file_url":"https://github.com/jiaxiaojunqaq/sa-aet/blob/HEAD/models/tokenization_bert.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e7fbc7a74a3457c7","mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"arxiv_id":"2409.12191","paper":"/paper/qwen2-vl-enhancing-vision-language-model-s","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","date":"2024-09-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MindCode-4/code-4","path":"prophetnet/tokenization_prophetnet.py","file_url":"https://github.com/MindCode-4/code-4/blob/HEAD/prophetnet/tokenization_prophetnet.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e7fbc7a74a3457c7","mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"arxiv_id":"2408.11853","paper":"/paper/pymarian-fast-neural-machine-translation-and","title":"PyMarian: Fast Neural Machine Translation and Evaluation in Python","date":"2024-08-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OpenNMT/CTranslate2","path":"python/ctranslate2/converters/marian.py","file_url":"https://github.com/OpenNMT/CTranslate2/blob/HEAD/python/ctranslate2/converters/marian.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"241f78b9e78ef2ea","mcp_get_code":{"code_sha256":"241f78b9e78ef2ea"}},{"arxiv_id":"2406.19232","paper":"/paper/rublimp-russian-benchmark-of-linguistic","title":"RuBLiMP: Russian Benchmark of Linguistic Minimal Pairs","date":"2024-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RussianNLP/RuBLiMP","path":"src/utils/data_loaders.py","file_url":"https://github.com/RussianNLP/RuBLiMP/blob/HEAD/src/utils/data_loaders.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":"dbe2a14f4e641a48","mcp_get_code":{"code_sha256":"dbe2a14f4e641a48"}},{"arxiv_id":"2406.05491","paper":"/paper/one-perturbation-is-enough-on-generating","title":"One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models","date":"2024-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ffhibnese/cpgc_vlp_universal_attacks","path":"models/tokenization_bert.py","file_url":"https://github.com/ffhibnese/cpgc_vlp_universal_attacks/blob/HEAD/models/tokenization_bert.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e7fbc7a74a3457c7","mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"arxiv_id":"2404.19287","paper":"/paper/revisiting-the-adversarial-robustness-of","title":"Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective","date":"2024-04-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ellezwq/mmcoa","path":"models/tokenization_bert.py","file_url":"https://github.com/ellezwq/mmcoa/blob/HEAD/models/tokenization_bert.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e7fbc7a74a3457c7","mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"arxiv_id":"2402.14789","paper":"/paper/self-guided-masked-autoencoders-for-domain","title":"Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning","date":"2024-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"johnathan-xie/sma","path":"src/transformers/models/sma/tokenization_sma.py","file_url":"https://github.com/johnathan-xie/sma/blob/HEAD/src/transformers/models/sma/tokenization_sma.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e7fbc7a74a3457c7","mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"arxiv_id":"2312.11038","paper":"/paper/unichest-conquer-and-divide-pre-training-for","title":"UniChest: Conquer-and-Divide Pre-training for Multi-Source Chest X-Ray Classification","date":"2023-12-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"elfenreigen/unichest","path":"models/tokenization_bert.py","file_url":"https://github.com/elfenreigen/unichest/blob/HEAD/models/tokenization_bert.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e7fbc7a74a3457c7","mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"arxiv_id":"2312.02249","paper":"/paper/recursive-visual-programming","title":"Recursive Visual Programming","date":"2023-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"para-lost/rvp","path":"base_models/tcl/tcl_tokenization_bert.py","file_url":"https://github.com/para-lost/rvp/blob/HEAD/base_models/tcl/tcl_tokenization_bert.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e7fbc7a74a3457c7","mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"arxiv_id":"2311.03054","paper":"/paper/anytext-multilingual-visual-text-generation","title":"AnyText: Multilingual Visual Text Generation And Editing","date":"2023-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tyxsspa/anytext","path":"bert_tokenizer.py","file_url":"https://github.com/tyxsspa/anytext/blob/HEAD/bert_tokenizer.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":"aaf1cb2c01043065","mcp_get_code":{"code_sha256":"aaf1cb2c01043065"}},{"arxiv_id":"2310.18738","paper":"/paper/tlm-token-level-masking-for-transformers","title":"TLM: Token-Level Masking for Transformers","date":"2023-10-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"blcuicall/CCL2022-CLTC","path":"baselines/track2/tokenization.py","file_url":"https://github.com/blcuicall/CCL2022-CLTC/blob/HEAD/baselines/track2/tokenization.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"deb4d1793cf3ba73","mcp_get_code":{"code_sha256":"deb4d1793cf3ba73"}},{"arxiv_id":"2309.14763","paper":"/paper/conpet-continual-parameter-efficient-tuning","title":"ConPET: Continual Parameter-Efficient Tuning for Large Language Models","date":"2023-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"raincleared-song/conpet","path":"bmt_models/bee_tokenizer.py","file_url":"https://github.com/raincleared-song/conpet/blob/HEAD/bmt_models/bee_tokenizer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8b48cf849a2af11c","mcp_get_code":{"code_sha256":"8b48cf849a2af11c"}},{"arxiv_id":"2309.01017","paper":"/paper/contrastive-grouping-with-transformer-for-1","title":"Contrastive Grouping with Transformer for Referring Image Segmentation","date":"2023-09-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"toneyaya/cgformer","path":"bert/tokenization_bert.py","file_url":"https://github.com/toneyaya/cgformer/blob/HEAD/bert/tokenization_bert.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e7fbc7a74a3457c7","mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"arxiv_id":"2308.12038","paper":"/paper/large-multilingual-models-pivot-zero-shot","title":"Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages","date":"2023-08-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openbmb/viscpm","path":"VisCPM/cpm_tokenizers/bee.py","file_url":"https://github.com/openbmb/viscpm/blob/HEAD/VisCPM/cpm_tokenizers/bee.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"83504f51b50ea9e6","mcp_get_code":{"code_sha256":"83504f51b50ea9e6"}},{"arxiv_id":"2307.14878","paper":"/paper/mesed-a-multi-modal-entity-set-expansion","title":"MESED: A Multi-modal Entity Set Expansion Dataset with Fine-grained Semantic Classes and Hard Negative Entities","date":"2023-07-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thukelab/mesed","path":"utils.py","file_url":"https://github.com/thukelab/mesed/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"83911c412016bbe8","mcp_get_code":{"code_sha256":"83911c412016bbe8"}},{"arxiv_id":"2307.14061","paper":"/paper/set-level-guidance-attack-boosting","title":"Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models","date":"2023-07-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Zoky-2020/Set-level_Guidance_Attack","path":"models/tokenization_bert.py","file_url":"https://github.com/Zoky-2020/Set-level_Guidance_Attack/blob/HEAD/models/tokenization_bert.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e7fbc7a74a3457c7","mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"arxiv_id":"2306.04362","paper":"/paper/youku-mplug-a-10-million-large-scale-chinese","title":"Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Dataset for Pre-training and Benchmarks","date":"2023-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"x-plug/youku-mplug","path":"models/tokenization_mplug.py","file_url":"https://github.com/x-plug/youku-mplug/blob/HEAD/models/tokenization_mplug.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e7fbc7a74a3457c7","mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"arxiv_id":"2306.02898","paper":"/paper/towards-unified-text-based-person-retrieval-a","title":"Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark","date":"2023-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Shuyu-XJTU/APTM","path":"models/tokenization_bert.py","file_url":"https://github.com/Shuyu-XJTU/APTM/blob/HEAD/models/tokenization_bert.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e7fbc7a74a3457c7","mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"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_tokenizer.py","file_url":"https://github.com/TXH-mercury/VALOR/blob/HEAD/model/bert_tokenizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fb95c4b13cdf89a2","mcp_get_code":{"code_sha256":"fb95c4b13cdf89a2"}},{"arxiv_id":"2305.13653","paper":"/paper/rasa-relation-and-sensitivity-aware","title":"RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Flame-Chasers/RaSa","path":"models/tokenization_bert.py","file_url":"https://github.com/Flame-Chasers/RaSa/blob/HEAD/models/tokenization_bert.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e7fbc7a74a3457c7","mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"arxiv_id":"2305.02519","paper":"/paper/anetqa-a-large-scale-benchmark-for-fine","title":"ANetQA: A Large-scale Benchmark for Fine-grained Compositional Reasoning over Untrimmed Videos","date":"2023-05-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MILVLG/anetqa-code","path":"hcrn/DataLoader.py","file_url":"https://github.com/MILVLG/anetqa-code/blob/HEAD/hcrn/DataLoader.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":"4eb168a439e7658b","mcp_get_code":{"code_sha256":"4eb168a439e7658b"}},{"arxiv_id":"2303.10323","paper":"/paper/dynamic-graph-enhanced-contrastive-learning","title":"Dynamic Graph Enhanced Contrastive Learning for Chest X-ray Report Generation","date":"2023-03-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mlii0117/dcl","path":"models/tokenization_bert.py","file_url":"https://github.com/mlii0117/dcl/blob/HEAD/models/tokenization_bert.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e7fbc7a74a3457c7","mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"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":"tokenization.py","file_url":"https://github.com/google-research/bert/blob/HEAD/tokenization.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":"ff83ccc8b0b6462d","mcp_get_code":{"code_sha256":"ff83ccc8b0b6462d"}},{"arxiv_id":"2302.00402","paper":"/paper/mplug-2-a-modularized-multi-modal-foundation","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","date":"2023-02-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"X-PLUG/mPLUG-2","path":"models/tokenization_bert.py","file_url":"https://github.com/X-PLUG/mPLUG-2/blob/HEAD/models/tokenization_bert.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e7fbc7a74a3457c7","mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"arxiv_id":"2211.13594","paper":"/paper/self-supervised-vision-language-pretraining","title":"Self-supervised vision-language pretraining for Medical visual question answering","date":"2022-11-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pengfeiliheu/m2i2","path":"models/tokenization_bert.py","file_url":"https://github.com/pengfeiliheu/m2i2/blob/HEAD/models/tokenization_bert.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e7fbc7a74a3457c7","mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"arxiv_id":"2211.03779","paper":"/paper/cripp-vqa-counterfactual-reasoning-about","title":"CRIPP-VQA: Counterfactual Reasoning about Implicit Physical Properties via Video Question Answering","date":"2022-11-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thaolmk54/hcrn-videoqa","path":"DataLoader.py","file_url":"https://github.com/thaolmk54/hcrn-videoqa/blob/HEAD/DataLoader.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":"4eb168a439e7658b","mcp_get_code":{"code_sha256":"4eb168a439e7658b"}},{"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/bert_tokenizer.py","file_url":"https://github.com/ofa-sys/chinese-clip/blob/HEAD/cn_clip/clip/bert_tokenizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aaf1cb2c01043065","mcp_get_code":{"code_sha256":"aaf1cb2c01043065"}},{"arxiv_id":"2210.10678","paper":"/paper/towards-realistic-low-resource-relation","title":"Towards Realistic Low-resource Relation Extraction: A Benchmark with Empirical Baseline Study","date":"2022-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zjunlp/KnowPrompt","path":"models/bert/tokenization_bert.py","file_url":"https://github.com/zjunlp/KnowPrompt/blob/HEAD/models/bert/tokenization_bert.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e7fbc7a74a3457c7","mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"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/tokenization.py","file_url":"https://github.com/dzh19990407/ppmn/blob/HEAD/models/tokenization.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":"a4e183f24a5ad1a7","mcp_get_code":{"code_sha256":"a4e183f24a5ad1a7"}},{"arxiv_id":"2207.05333","paper":"/paper/idea-increasing-text-diversity-via-online","title":"IDEA: Increasing Text Diversity via Online Multi-Label Recognition for Vision-Language Pre-training","date":"2022-07-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xinyu1205/idea-pytorch","path":"models/tokenization_bert.py","file_url":"https://github.com/xinyu1205/idea-pytorch/blob/HEAD/models/tokenization_bert.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e7fbc7a74a3457c7","mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"arxiv_id":"2205.11169","paper":"/paper/pevl-position-enhanced-pre-training-and","title":"PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models","date":"2022-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thunlp/PEVL","path":"models/tokenization_bert.py","file_url":"https://github.com/thunlp/PEVL/blob/HEAD/models/tokenization_bert.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e7fbc7a74a3457c7","mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"arxiv_id":"2203.09313","paper":"/paper/eva2-0-investigating-open-domain-chinese","title":"EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training","date":"2022-03-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-coai/EVA","path":"src/tokenization_eva.py","file_url":"https://github.com/thu-coai/EVA/blob/HEAD/src/tokenization_eva.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"deb4d1793cf3ba73","mcp_get_code":{"code_sha256":"deb4d1793cf3ba73"}},{"arxiv_id":"2111.09543","paper":"/paper/debertav3-improving-deberta-using-electra","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","date":"2021-11-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/DeBERTa","path":"DeBERTa/deberta/cache_utils.py","file_url":"https://github.com/microsoft/DeBERTa/blob/HEAD/DeBERTa/deberta/cache_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"82c76e446399db0c","mcp_get_code":{"code_sha256":"82c76e446399db0c"}},{"arxiv_id":"2111.09452","paper":"/paper/towards-open-vocabulary-object-detection","title":"Open Vocabulary Object Detection with Pseudo Bounding-Box Labels","date":"2021-11-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/pb-ovd","path":"ALBEF/models/tokenization_bert.py","file_url":"https://github.com/salesforce/pb-ovd/blob/HEAD/ALBEF/models/tokenization_bert.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"e7fbc7a74a3457c7","mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"arxiv_id":"2109.08008","paper":"/paper/the-niutrans-system-for-wngt-2020-efficiency-1","title":"The NiuTrans System for WNGT 2020 Efficiency Task","date":"2021-09-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NiuTrans/NiuTrans.NMT","path":"tools/PrepareParallelData.py","file_url":"https://github.com/NiuTrans/NiuTrans.NMT/blob/HEAD/tools/PrepareParallelData.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5535dc12255780ab","mcp_get_code":{"code_sha256":"5535dc12255780ab"}},{"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":"models/BERT/tokenization.py","file_url":"https://github.com/blacknoodle/tucore-gcn/blob/HEAD/models/BERT/tokenization.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"91bbcb76dbd7d974","mcp_get_code":{"code_sha256":"91bbcb76dbd7d974"}},{"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/tokenization.py","file_url":"https://github.com/shubham-gupta-iitr/mmmlX/blob/HEAD/pytorch_pretrained_bert/tokenization.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":"232295eeb04a142e","mcp_get_code":{"code_sha256":"232295eeb04a142e"}},{"arxiv_id":"2108.04539","paper":"/paper/bros-a-layout-aware-pre-trained-language","title":"BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents","date":"2021-08-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"clovaai/bros","path":"bros/tokenization_bros.py","file_url":"https://github.com/clovaai/bros/blob/HEAD/bros/tokenization_bros.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e7fbc7a74a3457c7","mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"arxiv_id":"2108.02170","paper":"/paper/curriculum-learning-for-language-modeling","title":"Curriculum learning for language modeling","date":"2021-08-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"spacemanidol/CurriculumLearningForLanguageModels","path":"bin/make_vocab_based_curriculum.py","file_url":"https://github.com/spacemanidol/CurriculumLearningForLanguageModels/blob/HEAD/bin/make_vocab_based_curriculum.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"637b815724dea79d","mcp_get_code":{"code_sha256":"637b815724dea79d"}},{"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/tokenization.py","file_url":"https://github.com/cbluebenchmark/cblue/blob/HEAD/cblue/models/zen/tokenization.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":"a4e183f24a5ad1a7","mcp_get_code":{"code_sha256":"a4e183f24a5ad1a7"}},{"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/tokenization.py","file_url":"https://github.com/tbs17/MathBERT/blob/HEAD/mathbert/tokenization.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"ff83ccc8b0b6462d","mcp_get_code":{"code_sha256":"ff83ccc8b0b6462d"}},{"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/tokenization.py","file_url":"https://github.com/Albert-Ma/PROP/blob/HEAD/pytorch_pretrain_bert/tokenization.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":"a4e183f24a5ad1a7","mcp_get_code":{"code_sha256":"a4e183f24a5ad1a7"}},{"arxiv_id":"2104.07242","paper":"/paper/designing-a-minimal-retrieve-and-read-system","title":"Designing a Minimal Retrieve-and-Read System for Open-Domain Question Answering","date":"2021-04-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"clovaai/minimal-rnr-qa","path":"playground/workspace/minimal_rnr/tfserving/bert_tokenizer/tokenization_bert.py","file_url":"https://github.com/clovaai/minimal-rnr-qa/blob/HEAD/playground/workspace/minimal_rnr/tfserving/bert_tokenizer/tokenization_bert.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e7fbc7a74a3457c7","mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"arxiv_id":"2012.14913","paper":"/paper/transformer-feed-forward-layers-are-key-value","title":"Transformer Feed-Forward Layers Are Key-Value Memories","date":"2020-12-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mega002/ff-layers","path":"analysis/key_value_agreement.py","file_url":"https://github.com/mega002/ff-layers/blob/HEAD/analysis/key_value_agreement.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"906ed5859e0c2204","mcp_get_code":{"code_sha256":"906ed5859e0c2204"}},{"arxiv_id":"2010.12777","paper":"/paper/improving-multilingual-models-with-language","title":"Improving Multilingual Models with Language-Clustered Vocabularies","date":"2020-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"afshinrahimi/mmner","path":"config.py","file_url":"https://github.com/afshinrahimi/mmner/blob/HEAD/config.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":"b1e144bdab6449a6","mcp_get_code":{"code_sha256":"b1e144bdab6449a6"}},{"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/tokenizer.py","file_url":"https://github.com/microsoft/TUTA_table_understanding/blob/HEAD/tuta/tokenizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c6f97c063d30a371","mcp_get_code":{"code_sha256":"c6f97c063d30a371"}},{"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/tokenization.py","file_url":"https://github.com/IMPLabUniPr/BERT-for-ABSA/blob/HEAD/src/tokenization.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":"a4e183f24a5ad1a7","mcp_get_code":{"code_sha256":"a4e183f24a5ad1a7"}},{"arxiv_id":"2010.11655","paper":"/paper/deep-reinforcement-learning-with-stacked","title":"Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YunqiuXu/SHA-KG","path":"env.py","file_url":"https://github.com/YunqiuXu/SHA-KG/blob/HEAD/env.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ba9616834d32858b","mcp_get_code":{"code_sha256":"ba9616834d32858b"}},{"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/tokenization.py","file_url":"https://github.com/lemmonation/abnet/blob/HEAD/bert/tokenization.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a4e183f24a5ad1a7","mcp_get_code":{"code_sha256":"a4e183f24a5ad1a7"}},{"arxiv_id":"2010.01653","paper":"/paper/an-empirical-study-on-large-scale-multi-label","title":"An Empirical Study on Large-Scale Multi-Label Text Classification Including Few and Zero-Shot Labels","date":"2020-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iliaschalkidis/lmtc-eurlex57k","path":"neural_networks/layers/bert_tokenization.py","file_url":"https://github.com/iliaschalkidis/lmtc-eurlex57k/blob/HEAD/neural_networks/layers/bert_tokenization.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":"ff83ccc8b0b6462d","mcp_get_code":{"code_sha256":"ff83ccc8b0b6462d"}},{"arxiv_id":"2009.05387","paper":"/paper/indonlu-benchmark-and-resources-for","title":"IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding","date":"2020-09-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"indobenchmark/indonlu","path":"utils/functions.py","file_url":"https://github.com/indobenchmark/indonlu/blob/HEAD/utils/functions.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":"4384e3778f7c4a96","mcp_get_code":{"code_sha256":"4384e3778f7c4a96"}},{"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/tokenization_bert.py","file_url":"https://github.com/TAMU-VITA/BERT-Tickets/blob/HEAD/transformers-master/src/transformers/tokenization_bert.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e7fbc7a74a3457c7","mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"arxiv_id":"2007.08095","paper":"/paper/synthesize-execute-and-debug-learning-to","title":"Synthesize, Execute and Debug: Learning to Repair for Neural Program Synthesis","date":"2020-07-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sunblaze-ucb/SED","path":"program_synthesis/datasets/data.py","file_url":"https://github.com/sunblaze-ucb/SED/blob/HEAD/program_synthesis/datasets/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3d825f33d60f08a3","mcp_get_code":{"code_sha256":"3d825f33d60f08a3"}},{"arxiv_id":"2007.00398","paper":"/paper/docvqa-a-dataset-for-vqa-on-document-images","title":"DocVQA: A Dataset for VQA on Document Images","date":"2020-07-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"anisha2102/docvqa","path":"tokenization.py","file_url":"https://github.com/anisha2102/docvqa/blob/HEAD/tokenization.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ff83ccc8b0b6462d","mcp_get_code":{"code_sha256":"ff83ccc8b0b6462d"}},{"arxiv_id":"2006.07409","paper":"/paper/how-to-avoid-being-eaten-by-a-grue-structured","title":"How to Avoid Being Eaten by a Grue: Structured Exploration Strategies for Textual Worlds","date":"2020-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rajammanabrolu/Q-BERT","path":"qbert/env.py","file_url":"https://github.com/rajammanabrolu/Q-BERT/blob/HEAD/qbert/env.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ba9616834d32858b","mcp_get_code":{"code_sha256":"ba9616834d32858b"}},{"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/tokenization_bert.py","file_url":"https://github.com/uds-lsv/bert-stable-fine-tuning/blob/HEAD/src/transformers/tokenization_bert.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e7fbc7a74a3457c7","mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"arxiv_id":"2006.01563","paper":"/paper/exploring-cross-sentence-contexts-for-named","title":"Exploring Cross-sentence Contexts for Named Entity Recognition with BERT","date":"2020-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jouniluoma/bert-ner-cmv","path":"bert_tokenization.py","file_url":"https://github.com/jouniluoma/bert-ner-cmv/blob/HEAD/bert_tokenization.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"30b05f2a415dd132","mcp_get_code":{"code_sha256":"30b05f2a415dd132"}},{"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/tokenization.py","file_url":"https://github.com/wluper/retrograph/blob/HEAD/retrograph/modeling/tokenization.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":"ff83ccc8b0b6462d","mcp_get_code":{"code_sha256":"ff83ccc8b0b6462d"}},{"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/tokenization.py","file_url":"https://github.com/juntaoy/biaffine-ner/blob/HEAD/extract_bert_features/tokenization.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":"ff83ccc8b0b6462d","mcp_get_code":{"code_sha256":"ff83ccc8b0b6462d"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a87406334d83c277","mcp_get_code":{"code_sha256":"a87406334d83c277"}},{"arxiv_id":"2004.09297","paper":"/paper/mpnet-masked-and-permuted-pre-training-for","title":"MPNet: Masked and Permuted Pre-training for Language Understanding","date":"2020-04-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"michael-wzhu/mpnet_zh","path":"src/tokenization_bert.py","file_url":"https://github.com/michael-wzhu/mpnet_zh/blob/HEAD/src/tokenization_bert.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"e7fbc7a74a3457c7","mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"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/tokenization.py","file_url":"https://github.com/allenai/sledgehammer/blob/HEAD/allennlp_overrides/pytorch_pretrained_bert/tokenization.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":"a4e183f24a5ad1a7","mcp_get_code":{"code_sha256":"a4e183f24a5ad1a7"}},{"arxiv_id":"2004.03762","paper":"/paper/generating-narrative-text-in-a-switching","title":"Generating Narrative Text in a Switching Dynamical System","date":"2020-04-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"StonyBrookNLP/SLDS-Stories","path":"data_utils.py","file_url":"https://github.com/StonyBrookNLP/SLDS-Stories/blob/HEAD/data_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a127d4e3ccc2f275","mcp_get_code":{"code_sha256":"a127d4e3ccc2f275"}},{"arxiv_id":"2003.02645","paper":"/paper/200302645","title":"SentenceMIM: A Latent Variable Language Model","date":"2020-02-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seraphlabs-ca/SentenceMIM-demo","path":"auxiliary.py","file_url":"https://github.com/seraphlabs-ca/SentenceMIM-demo/blob/HEAD/auxiliary.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"21afa721a457190d","mcp_get_code":{"code_sha256":"21afa721a457190d"}},{"arxiv_id":"1911.03070","paper":"/paper/interactive-refinement-of-cross-lingual-word","title":"Interactive Refinement of Cross-Lingual Word Embeddings","date":"2019-11-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"forest-snow/clime-ui","path":"interface/load.py","file_url":"https://github.com/forest-snow/clime-ui/blob/HEAD/interface/load.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"357bd3b78248ba9a","mcp_get_code":{"code_sha256":"357bd3b78248ba9a"}},{"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":"tokenization.py","file_url":"https://github.com/helloeve/bert-co-matching/blob/HEAD/tokenization.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":"ff83ccc8b0b6462d","mcp_get_code":{"code_sha256":"ff83ccc8b0b6462d"}},{"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/tokenization.py","file_url":"https://github.com/Holldean/BERT-Pruning/blob/HEAD/bert/tokenization.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":"ff83ccc8b0b6462d","mcp_get_code":{"code_sha256":"ff83ccc8b0b6462d"}},{"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":"kpe/bert-for-tf2","path":"bert/tokenization/bert_tokenization.py","file_url":"https://github.com/kpe/bert-for-tf2/blob/HEAD/bert/tokenization/bert_tokenization.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"30b05f2a415dd132","mcp_get_code":{"code_sha256":"30b05f2a415dd132"}},{"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/bert_new","path":"src/model/BERT/tokenization_bert.py","file_url":"https://github.com/Soikonomou/bert_new/blob/HEAD/src/model/BERT/tokenization_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":"659f3761c1dc81fa","mcp_get_code":{"code_sha256":"659f3761c1dc81fa"}},{"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":"tokenization.py","file_url":"https://github.com/Arthurizijar/Bert_Airport/blob/HEAD/tokenization.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":"ff83ccc8b0b6462d","mcp_get_code":{"code_sha256":"ff83ccc8b0b6462d"}},{"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":"Maz101/Bert","path":"tokenization.py","file_url":"https://github.com/Maz101/Bert/blob/HEAD/tokenization.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":"30b05f2a415dd132","mcp_get_code":{"code_sha256":"30b05f2a415dd132"}},{"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":"coronazap/bert_client","path":"tokenization.py","file_url":"https://github.com/coronazap/bert_client/blob/HEAD/tokenization.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":"21c6f1a7ac31a2bd","mcp_get_code":{"code_sha256":"21c6f1a7ac31a2bd"}},{"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":"tokenization.py","file_url":"https://github.com/uwnlp/denspi/blob/HEAD/tokenization.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":"c8956ce86812a6c2","mcp_get_code":{"code_sha256":"c8956ce86812a6c2"}},{"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/tokenization.py","file_url":"https://github.com/yongjie-lin/bert-opensesame/blob/HEAD/pytorch_pretrained_bert/tokenization.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":"fb95c4b13cdf89a2","mcp_get_code":{"code_sha256":"fb95c4b13cdf89a2"}},{"arxiv_id":"1905.11286","paper":"/paper/stochastic-gradient-methods-with-layer-wise","title":"Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks","date":"2019-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NVIDIA/OpenSeq2Seq","path":"ctc_decoder_with_lm/ctc-test.py","file_url":"https://github.com/NVIDIA/OpenSeq2Seq/blob/HEAD/ctc_decoder_with_lm/ctc-test.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":"00c6b131afd785b5","mcp_get_code":{"code_sha256":"00c6b131afd785b5"}},{"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":"tokenization.py","file_url":"https://github.com/AdeDZY/SIGIR19-BERT-IR/blob/HEAD/tokenization.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":"ff83ccc8b0b6462d","mcp_get_code":{"code_sha256":"ff83ccc8b0b6462d"}},{"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":"tokenization.py","file_url":"https://github.com/HSLCY/ABSA-BERT-pair/blob/HEAD/tokenization.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"deb4d1793cf3ba73","mcp_get_code":{"code_sha256":"deb4d1793cf3ba73"}},{"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":"mangushev/intent_slot","path":"assistant/functions/intent_slot/preprocessor/tokenization.py","file_url":"https://github.com/mangushev/intent_slot/blob/HEAD/assistant/functions/intent_slot/preprocessor/tokenization.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"deb4d1793cf3ba73","mcp_get_code":{"code_sha256":"deb4d1793cf3ba73"}},{"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":"tokenization.py","file_url":"https://github.com/helloeve/mre-in-one-pass/blob/HEAD/tokenization.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":"ff83ccc8b0b6462d","mcp_get_code":{"code_sha256":"ff83ccc8b0b6462d"}},{"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/tokenization.py","file_url":"https://github.com/dmis-lab/bern/blob/HEAD/biobert_ner/tokenization.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":"ff83ccc8b0b6462d","mcp_get_code":{"code_sha256":"ff83ccc8b0b6462d"}},{"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":"IBM/MAX-Text-Sentiment-Classifier","path":"core/bert/tokenization.py","file_url":"https://github.com/IBM/MAX-Text-Sentiment-Classifier/blob/HEAD/core/bert/tokenization.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d0e80220bcbf4ae0","mcp_get_code":{"code_sha256":"d0e80220bcbf4ae0"}},{"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":"1wy/bert","path":"tokenization.py","file_url":"https://github.com/1wy/bert/blob/HEAD/tokenization.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":"ff83ccc8b0b6462d","mcp_get_code":{"code_sha256":"ff83ccc8b0b6462d"}},{"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/tokenization_bert.py","file_url":"https://github.com/lonePatient/Bert-Multi-Label-Text-Classification/blob/HEAD/pybert/model/albert/tokenization_bert.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"659f3761c1dc81fa","mcp_get_code":{"code_sha256":"659f3761c1dc81fa"}},{"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":"IBM/MAX-Question-Answering","path":"core/tokenization.py","file_url":"https://github.com/IBM/MAX-Question-Answering/blob/HEAD/core/tokenization.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":"97438b663cee62b4","mcp_get_code":{"code_sha256":"97438b663cee62b4"}},{"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":"MaZhiyuanBUAA/bert-tf1.4.0","path":"tokenization.py","file_url":"https://github.com/MaZhiyuanBUAA/bert-tf1.4.0/blob/HEAD/tokenization.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":"85608a0993acae75","mcp_get_code":{"code_sha256":"85608a0993acae75"}},{"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":"guoyaohua/BERT-Chinese-Annotation","path":"tokenization.py","file_url":"https://github.com/guoyaohua/BERT-Chinese-Annotation/blob/HEAD/tokenization.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":"cfdf5fac37771edf","mcp_get_code":{"code_sha256":"cfdf5fac37771edf"}},{"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":"meizi1114/bert","path":"tokenization.py","file_url":"https://github.com/meizi1114/bert/blob/HEAD/tokenization.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":"71806f38591c80b6","mcp_get_code":{"code_sha256":"71806f38591c80b6"}},{"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":"tyxr/bert","path":"tokenization.py","file_url":"https://github.com/tyxr/bert/blob/HEAD/tokenization.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":"b67ad78f40e86899","mcp_get_code":{"code_sha256":"b67ad78f40e86899"}},{"arxiv_id":"1807.03168","paper":"/paper/naps-natural-program-synthesis-dataset","title":"NAPS: Natural Program Synthesis Dataset","date":"2018-07-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nearai/program_synthesis","path":"program_synthesis/algolisp/dataset/data.py","file_url":"https://github.com/nearai/program_synthesis/blob/HEAD/program_synthesis/algolisp/dataset/data.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":"711c950a814e87b1","mcp_get_code":{"code_sha256":"711c950a814e87b1"}},{"arxiv_id":"1806.01822","paper":"/paper/relational-recurrent-neural-networks","title":"Relational recurrent neural networks","date":"2018-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cheonbok94/Pytorch-Relational-Recurrent-Neural-networks","path":"utils/data.py","file_url":"https://github.com/cheonbok94/Pytorch-Relational-Recurrent-Neural-networks/blob/HEAD/utils/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"508cfb82d084f33d","mcp_get_code":{"code_sha256":"508cfb82d084f33d"}},{"arxiv_id":"1803.05268","paper":"/paper/transparency-by-design-closing-the-gap","title":"Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning","date":"2018-03-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"davidmascharka/tbd-nets","path":"utils/clevr.py","file_url":"https://github.com/davidmascharka/tbd-nets/blob/HEAD/utils/clevr.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ba3c072b123cf122","mcp_get_code":{"code_sha256":"ba3c072b123cf122"}},{"arxiv_id":"1710.08969","paper":"/paper/efficiently-trainable-text-to-speech-system","title":"Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attention","date":"2017-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CSTR-Edinburgh/ophelia","path":"data_load.py","file_url":"https://github.com/CSTR-Edinburgh/ophelia/blob/HEAD/data_load.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":"ed89c632018002ae","mcp_get_code":{"code_sha256":"ed89c632018002ae"}},{"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":"Kyubyong/transformer","path":"model.py","file_url":"https://github.com/Kyubyong/transformer/blob/HEAD/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"eea349e2e1aa954c","mcp_get_code":{"code_sha256":"eea349e2e1aa954c"}},{"arxiv_id":"1609.08144","paper":"/paper/googles-neural-machine-translation-system","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","date":"2016-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/BlingFire","path":"ldbsrc/bert_base_tok/tokenization.py","file_url":"https://github.com/microsoft/BlingFire/blob/HEAD/ldbsrc/bert_base_tok/tokenization.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ff83ccc8b0b6462d","mcp_get_code":{"code_sha256":"ff83ccc8b0b6462d"}},{"arxiv_id":"1603.01360","paper":"/paper/neural-architectures-for-named-entity","title":"Neural Architectures for Named Entity Recognition","date":"2016-03-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IBM/MAX-Named-Entity-Tagger","path":"core/utils.py","file_url":"https://github.com/IBM/MAX-Named-Entity-Tagger/blob/HEAD/core/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":"a0562f49c954c62c","mcp_get_code":{"code_sha256":"a0562f49c954c62c"}},{"arxiv_id":"1603.01354","paper":"/paper/end-to-end-sequence-labeling-via-bi","title":"End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF","date":"2016-03-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"monologg/korean-ner-pytorch","path":"utils.py","file_url":"https://github.com/monologg/korean-ner-pytorch/blob/HEAD/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":"7a25966763d63ede","mcp_get_code":{"code_sha256":"7a25966763d63ede"}},{"arxiv_id":"1508.01211","paper":"/paper/listen-attend-and-spell","title":"Listen, Attend and Spell","date":"2015-08-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WindQAQ/listen-attend-and-spell","path":"utils/vocab_utils.py","file_url":"https://github.com/WindQAQ/listen-attend-and-spell/blob/HEAD/utils/vocab_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":"75776719b114cdb1","mcp_get_code":{"code_sha256":"75776719b114cdb1"}},{"arxiv_id":"1506.08909","paper":"/paper/the-ubuntu-dialogue-corpus-a-large-dataset-1","title":"The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems","date":"2015-06-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dennybritz/chatbot-retrieval","path":"models/helpers.py","file_url":"https://github.com/dennybritz/chatbot-retrieval/blob/HEAD/models/helpers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d90e90d3ea78789a","mcp_get_code":{"code_sha256":"d90e90d3ea78789a"}},{"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/tokenization.py","file_url":"https://github.com/yschoi-nisp/AI-Grand-Challenge-2020/blob/HEAD/pytorch_pretrained_bert/tokenization.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fb95c4b13cdf89a2","mcp_get_code":{"code_sha256":"fb95c4b13cdf89a2"}},{"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/tokenization_morp.py","file_url":"https://github.com/yschoi-nisp/AI-Grand-Challenge-2020/blob/HEAD/pytorch_pretrained_bert/tokenization_morp.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"90d3ee4851872058","mcp_get_code":{"code_sha256":"90d3ee4851872058"}},{"arxiv_id":"aaai_6453","paper":null,"title":"arXiv:aaai_6453","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"siat-nlp/TransDG","path":"src/utils/data_loader.py","file_url":"https://github.com/siat-nlp/TransDG/blob/HEAD/src/utils/data_loader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b2a79364e5c3e474","mcp_get_code":{"code_sha256":"b2a79364e5c3e474"}},{"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/tokenization.py","file_url":"https://github.com/airsplay/LXMERT/blob/HEAD/src/lxrt/tokenization.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a4e183f24a5ad1a7","mcp_get_code":{"code_sha256":"a4e183f24a5ad1a7"}},{"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/tokenization.py","file_url":"https://github.com/TianyuGoGO/XPNG/blob/HEAD/models/tokenization.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":"a4e183f24a5ad1a7","mcp_get_code":{"code_sha256":"a4e183f24a5ad1a7"}},{"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/util/tokenization.py","file_url":"https://github.com/frankaging/Quasi-Attention-ABSA/blob/HEAD/code/util/tokenization.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"97e01db27f6a6fd2","mcp_get_code":{"code_sha256":"97e01db27f6a6fd2"}},{"arxiv_id":"2025.findings-emnlp.1385","paper":null,"title":"arXiv:2025.findings-emnlp.1385","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"bowen-upenn/ControlText","path":"bert_tokenizer.py","file_url":"https://github.com/bowen-upenn/ControlText/blob/HEAD/bert_tokenizer.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":"aaf1cb2c01043065","mcp_get_code":{"code_sha256":"aaf1cb2c01043065"}},{"arxiv_id":"2024.naacl-long.343","paper":null,"title":"arXiv:2024.naacl-long.343","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"king-yyf/CMeKG_tools","path":"utils.py","file_url":"https://github.com/king-yyf/CMeKG_tools/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":"e89bd2800d81e207","mcp_get_code":{"code_sha256":"e89bd2800d81e207"}},{"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/tokenization.py","file_url":"https://github.com/kamigaito/SLAHAN/blob/HEAD/bert/tokenization.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ff83ccc8b0b6462d","mcp_get_code":{"code_sha256":"ff83ccc8b0b6462d"}},{"arxiv_id":"2024.findings-acl.148","paper":null,"title":"arXiv:2024.findings-acl.148","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"HillZhang1999/MuCGEC","path":"models/seq2edit-based-CGEC/tokenization.py","file_url":"https://github.com/HillZhang1999/MuCGEC/blob/HEAD/models/seq2edit-based-CGEC/tokenization.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":"deb4d1793cf3ba73","mcp_get_code":{"code_sha256":"deb4d1793cf3ba73"}},{"arxiv_id":"2023.findings-emnlp.268","paper":null,"title":"arXiv:2023.findings-emnlp.268","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"YuxiXie/ECHo","path":"ToM_CoT_reasoning/utils.py","file_url":"https://github.com/YuxiXie/ECHo/blob/HEAD/ToM_CoT_reasoning/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"57b68f1e175c5abb","mcp_get_code":{"code_sha256":"57b68f1e175c5abb"}},{"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/tokenization.py","file_url":"https://github.com/juntaoy/dali-bridging/blob/HEAD/extract_bert_features/tokenization.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":"ff83ccc8b0b6462d","mcp_get_code":{"code_sha256":"ff83ccc8b0b6462d"}},{"arxiv_id":"2021.findings-acl.216","paper":null,"title":"arXiv:2021.findings-acl.216","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"destwang/DCN","path":"transformers/tokenization_dcn.py","file_url":"https://github.com/destwang/DCN/blob/HEAD/transformers/tokenization_dcn.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e7fbc7a74a3457c7","mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"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/tokenization.py","file_url":"https://github.com/hyounghk/NDH-FULL/blob/HEAD/tasks/NDH_full/tokenization.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a4e183f24a5ad1a7","mcp_get_code":{"code_sha256":"a4e183f24a5ad1a7"}}]}