{"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/hf-bucket-url","entry":"hf_bucket_url","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":13,"n_papers_ran":3,"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":1,"n_samples_fingerprinted":1,"n_places":14,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":3},"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":"2402.03216","paper":"/paper/bge-m3-embedding-multi-lingual-multi","title":"BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation","date":"2024-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"terrierteam/pyterrier_dr","path":"pyterrier_dr/_star_tokenizer.py","file_url":"https://github.com/terrierteam/pyterrier_dr/blob/HEAD/pyterrier_dr/_star_tokenizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b2be6c932ce41084","mcp_get_code":{"code_sha256":"b2be6c932ce41084"}},{"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/file_utils.py","file_url":"https://github.com/toneyaya/cgformer/blob/HEAD/bert/file_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"070b5bdeecd71825","mcp_get_code":{"code_sha256":"070b5bdeecd71825"}},{"arxiv_id":"2110.05789","paper":"/paper/learning-discrete-representations-via-1","title":"Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrieval","date":"2021-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jingtaozhan/DRhard","path":"star_tokenizer.py","file_url":"https://github.com/jingtaozhan/DRhard/blob/HEAD/star_tokenizer.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":"b2be6c932ce41084","mcp_get_code":{"code_sha256":"b2be6c932ce41084"}},{"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/file_utils.py","file_url":"https://github.com/princeton-nlp/DensePhrases/blob/HEAD/densephrases/utils/file_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"070b5bdeecd71825","mcp_get_code":{"code_sha256":"070b5bdeecd71825"}},{"arxiv_id":"2106.11310","paper":"/paper/towards-long-form-video-understanding-1","title":"Towards Long-Form Video Understanding","date":"2021-06-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chaoyuaw/lvu","path":"src/models/file_utils.py","file_url":"https://github.com/chaoyuaw/lvu/blob/HEAD/src/models/file_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b2be6c932ce41084","mcp_get_code":{"code_sha256":"b2be6c932ce41084"}},{"arxiv_id":"2011.01513","paper":"/paper/charbert-character-aware-pre-trained-language","title":"CharBERT: Character-aware Pre-trained Language Model","date":"2020-11-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wtma/CharBERT","path":"modeling/file_utils_roberta.py","file_url":"https://github.com/wtma/CharBERT/blob/HEAD/modeling/file_utils_roberta.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b2be6c932ce41084","mcp_get_code":{"code_sha256":"b2be6c932ce41084"}},{"arxiv_id":"2011.01513","paper":"/paper/charbert-character-aware-pre-trained-language","title":"CharBERT: Character-aware Pre-trained Language Model","date":"2020-11-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wtma/CharBERT","path":"modeling/file_utils.py","file_url":"https://github.com/wtma/CharBERT/blob/HEAD/modeling/file_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":"9a10ade1f3205dc9","mcp_get_code":{"code_sha256":"9a10ade1f3205dc9"}},{"arxiv_id":"2009.12719","paper":"/paper/stylized-dialogue-response-generation-using","title":"Stylized Dialogue Response Generation Using Stylized Unpaired Texts","date":"2020-09-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"silverriver/Stylized_Dialog","path":"TCFC/bt_beam/model/file_utils.py","file_url":"https://github.com/silverriver/Stylized_Dialog/blob/HEAD/TCFC/bt_beam/model/file_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b2be6c932ce41084","mcp_get_code":{"code_sha256":"b2be6c932ce41084"}},{"arxiv_id":"2005.00796","paper":"/paper/a-simple-language-model-for-task-oriented","title":"A Simple Language Model for Task-Oriented Dialogue","date":"2020-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/simpletod","path":"models/file_utils.py","file_url":"https://github.com/salesforce/simpletod/blob/HEAD/models/file_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"b2be6c932ce41084","mcp_get_code":{"code_sha256":"b2be6c932ce41084"}},{"arxiv_id":"2004.10964","paper":"/paper/don-t-stop-pretraining-adapt-language-models","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","date":"2020-04-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shizhediao/t-dna","path":"TDNA/modeling.py","file_url":"https://github.com/shizhediao/t-dna/blob/HEAD/TDNA/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3cbbdc1cef27d05d","mcp_get_code":{"code_sha256":"3cbbdc1cef27d05d"}},{"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/file_utils.py","file_url":"https://github.com/michael-wzhu/mpnet_zh/blob/HEAD/src/file_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"b2be6c932ce41084","mcp_get_code":{"code_sha256":"b2be6c932ce41084"}},{"arxiv_id":"1910.13461","paper":"/paper/bart-denoising-sequence-to-sequence-pre","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","date":"2019-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"i2r-simmc/i2r-simmc-2020","path":"src/file_utils.py","file_url":"https://github.com/i2r-simmc/i2r-simmc-2020/blob/HEAD/src/file_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"070b5bdeecd71825","mcp_get_code":{"code_sha256":"070b5bdeecd71825"}},{"arxiv_id":"1909.11942","paper":"/paper/albert-a-lite-bert-for-self-supervised","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","date":"2019-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Soikonomou/albert_final","path":"src/model/ALBERT/file_utils.py","file_url":"https://github.com/Soikonomou/albert_final/blob/HEAD/src/model/ALBERT/file_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":"b2be6c932ce41084","mcp_get_code":{"code_sha256":"b2be6c932ce41084"}},{"arxiv_id":"2025.findings-emnlp.70","paper":null,"title":"arXiv:2025.findings-emnlp.70","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"passing2961/EmpGPT-3","path":"from_epitome/file_utils.py","file_url":"https://github.com/passing2961/EmpGPT-3/blob/HEAD/from_epitome/file_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b2be6c932ce41084","mcp_get_code":{"code_sha256":"b2be6c932ce41084"}}]}