{"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/whitespace-tokenize","entry":"whitespace_tokenize","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":49,"n_papers_ran":44,"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":4,"n_samples_ran":2,"n_samples_fingerprinted":2,"n_places":49,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":0,"unverified":2},"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":"2412.20223","paper":"/paper/afrihg-news-headline-generation-for-african","title":"AfriHG: News headline generation for African Languages","date":"2024-12-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dadelani/AfriHG","path":"Multi-Lang-Rouge/tokenizers.py","file_url":"https://github.com/dadelani/AfriHG/blob/HEAD/Multi-Lang-Rouge/tokenizers.py","status":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":"da7295883cd7da14","mcp_get_code":{"code_sha256":"da7295883cd7da14"}},{"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":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"arxiv_id":"2303.12528","paper":"/paper/mega-multilingual-evaluation-of-generative-ai","title":"MEGA: Multilingual Evaluation of Generative AI","date":"2023-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/Multilingual-Evaluation-of-Generative-AI-MEGA","path":"mega/compile_qa_results.py","file_url":"https://github.com/microsoft/Multilingual-Evaluation-of-Generative-AI-MEGA/blob/HEAD/mega/compile_qa_results.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a5f7f44e35526909","mcp_get_code":{"code_sha256":"a5f7f44e35526909"}},{"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":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"arxiv_id":"2205.14135","paper":"/paper/flashattention-fast-and-memory-efficient","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","date":"2022-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/long-range-arena","path":"lra_benchmarks/matching/build_vocab.py","file_url":"https://github.com/google-research/long-range-arena/blob/HEAD/lra_benchmarks/matching/build_vocab.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":"fbeafd410f521a6f","mcp_get_code":{"code_sha256":"fbeafd410f521a6f"}},{"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":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"arxiv_id":"2109.08133","paper":"/paper/phrase-retrieval-learns-passage-retrieval-too","title":"Phrase Retrieval Learns Passage Retrieval, Too","date":"2021-09-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-nlp/DensePhrases","path":"densephrases/utils/data_utils.py","file_url":"https://github.com/princeton-nlp/DensePhrases/blob/HEAD/densephrases/utils/data_utils.py","status":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":"da7295883cd7da14","mcp_get_code":{"code_sha256":"da7295883cd7da14"}},{"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":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"arxiv_id":"1910.07475","paper":"/paper/mlqa-evaluating-cross-lingual-extractive","title":"MLQA: Evaluating Cross-lingual Extractive Question Answering","date":"2019-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/MLQA","path":"mlqa_evaluation_v1.py","file_url":"https://github.com/facebookresearch/MLQA/blob/HEAD/mlqa_evaluation_v1.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"a5f7f44e35526909","mcp_get_code":{"code_sha256":"a5f7f44e35526909"}},{"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":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":"da7295883cd7da14","mcp_get_code":{"code_sha256":"da7295883cd7da14"}},{"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":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":"da7295883cd7da14","mcp_get_code":{"code_sha256":"da7295883cd7da14"}},{"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":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"arxiv_id":"2023.emnlp-main.803","paper":null,"title":"arXiv:2023.emnlp-main.803","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"yisunlp/Anti-CF","path":"utils/mlqa_evaluate.py","file_url":"https://github.com/yisunlp/Anti-CF/blob/HEAD/utils/mlqa_evaluate.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a5f7f44e35526909","mcp_get_code":{"code_sha256":"a5f7f44e35526909"}},{"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":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"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":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cf9ffa02a42184af","mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"arxiv_id":"2021.acl-long.48","paper":null,"title":"arXiv:2021.acl-long.48","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"PluviophileYU/COSY","path":"XQA/src/mlqa_evaluation_v1.py","file_url":"https://github.com/PluviophileYU/COSY/blob/HEAD/XQA/src/mlqa_evaluation_v1.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a5f7f44e35526909","mcp_get_code":{"code_sha256":"a5f7f44e35526909"}}]}