{"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/convert-to-unicode","entry":"convert_to_unicode","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":40,"n_papers_ran":36,"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":10,"n_samples_ran":1,"n_samples_fingerprinted":1,"n_places":45,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":0,"unverified":9},"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":"2601.03549","paper":"/paper/arxiv-2601-03549","title":"FEA-SLT: A Gloss-Free End-to-End Framework for Facial-Expression-Aware Sign Language Translation","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"google-research/bleurt","path":"bleurt/lib/bert_tokenization.py","file_url":"https://github.com/google-research/bleurt/blob/HEAD/bleurt/lib/bert_tokenization.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"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":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"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_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"arxiv_id":"2309.07311","paper":"/paper/sudden-drops-in-the-loss-syntax-acquisition","title":"Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs","date":"2023-09-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"angie-chen55/sudden-drops-in-the-loss","path":"extract_attention_pt.py","file_url":"https://github.com/angie-chen55/sudden-drops-in-the-loss/blob/HEAD/extract_attention_pt.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"arxiv_id":"2303.13716","paper":"/paper/recogs-how-incidental-details-of-a-logical","title":"ReCOGS: How Incidental Details of a Logical Form Overshadow an Evaluation of Semantic Interpretation","date":"2023-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"frankaging/recogs","path":"utils/cogs_utils.py","file_url":"https://github.com/frankaging/recogs/blob/HEAD/utils/cogs_utils.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":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"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_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"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":"01922c511206a241","mcp_get_code":{"code_sha256":"01922c511206a241"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"arxiv_id":"2007.00808","paper":"/paper/approximate-nearest-neighbor-negative","title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval","date":"2020-07-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/ANCE","path":"model/SEED_Encoder/tokenization_seed_encoder.py","file_url":"https://github.com/microsoft/ANCE/blob/HEAD/model/SEED_Encoder/tokenization_seed_encoder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e8a98cc72991f258","mcp_get_code":{"code_sha256":"e8a98cc72991f258"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"arxiv_id":"2004.11579","paper":"/paper/probabilistically-masked-language-model","title":"Probabilistically Masked Language Model Capable of Autoregressive Generation in Arbitrary Word Order","date":"2020-04-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huawei-noah/Pretrained-Language-Model","path":"PMLM/interactive_conditional_samples_sincos_acrostic.py","file_url":"https://github.com/huawei-noah/Pretrained-Language-Model/blob/HEAD/PMLM/interactive_conditional_samples_sincos_acrostic.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"arxiv_id":"2003.09772","paper":"/paper/invariant-rationalization","title":"Invariant Rationalization","date":"2020-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"code-terminator/invariant_rationalization","path":"imdb.py","file_url":"https://github.com/code-terminator/invariant_rationalization/blob/HEAD/imdb.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5049398bdcfb5fa7","mcp_get_code":{"code_sha256":"5049398bdcfb5fa7"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"arxiv_id":"1904.09223","paper":"/paper/ernie-enhanced-representation-through","title":"ERNIE: Enhanced Representation through Knowledge Integration","date":"2019-04-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lyqcom/emotect","path":"src/reader.py","file_url":"https://github.com/lyqcom/emotect/blob/HEAD/src/reader.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":"01f2dd1d4afbd7c9","mcp_get_code":{"code_sha256":"01f2dd1d4afbd7c9"}},{"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_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"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_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"arxiv_id":"1901.04085","paper":"/paper/passage-re-ranking-with-bert","title":"Passage Re-ranking with BERT","date":"2019-01-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nyu-dl/dl4marco-bert","path":"tokenization.py","file_url":"https://github.com/nyu-dl/dl4marco-bert/blob/HEAD/tokenization.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"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":"ef47b227c080ca7a","mcp_get_code":{"code_sha256":"ef47b227c080ca7a"}},{"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":"4874ae2953f3aeab","mcp_get_code":{"code_sha256":"4874ae2953f3aeab"}},{"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":"0953802ea4dc83a7","mcp_get_code":{"code_sha256":"0953802ea4dc83a7"}},{"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":"e2bfbb357751d986","mcp_get_code":{"code_sha256":"e2bfbb357751d986"}},{"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":"595d45bc07678f87","mcp_get_code":{"code_sha256":"595d45bc07678f87"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"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_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1923fc05163d207d","mcp_get_code":{"code_sha256":"1923fc05163d207d"}}]}