{"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/read-corpus","entry":"read_corpus","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":11,"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":12,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":12,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":1,"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":"2607.29168","paper":"/paper/arxiv-2607-29168","title":"Authorship Verification of Transcribed German-Language Videos","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"Fraunhofer-SIT/WIFS2026-TranscribedGermanAV","path":"common.py","file_url":"https://github.com/Fraunhofer-SIT/WIFS2026-TranscribedGermanAV/blob/HEAD/common.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":"389f822170b32c3f","mcp_get_code":{"code_sha256":"389f822170b32c3f"}},{"arxiv_id":"2606.31741","paper":"/paper/arxiv-2606-31741","title":"STEB: Style Text Embedding Benchmark","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"dykang/PASTEL","path":"code/StyleTransfer/utils/readData.py","file_url":"https://github.com/dykang/PASTEL/blob/HEAD/code/StyleTransfer/utils/readData.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e878567faaeaed4a","mcp_get_code":{"code_sha256":"e878567faaeaed4a"}},{"arxiv_id":"2306.05212","paper":"/paper/reta-llm-a-retrieval-augmented-large-language","title":"RETA-LLM: A Retrieval-Augmented Large Language Model Toolkit","date":"2023-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ruc-gsai/yulan-ir","path":"RETA-LLM/indexer/train_dam_module.py","file_url":"https://github.com/ruc-gsai/yulan-ir/blob/HEAD/RETA-LLM/indexer/train_dam_module.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f3a020ae6e1e35b7","mcp_get_code":{"code_sha256":"f3a020ae6e1e35b7"}},{"arxiv_id":"2210.11766","paper":"/paper/cefr-based-sentence-difficulty-annotation-and","title":"CEFR-Based Sentence Difficulty Annotation and Assessment","date":"2022-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yukiar/CEFR-SP","path":"src/model.py","file_url":"https://github.com/yukiar/CEFR-SP/blob/HEAD/src/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":"52aa6a438836ec5d","mcp_get_code":{"code_sha256":"52aa6a438836ec5d"}},{"arxiv_id":"2205.03772","paper":"/paper/math-kg-construction-and-applications-of","title":"Math-KG: Construction and Applications of Mathematical Knowledge Graph","date":"2022-05-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wjn1996/mathematical-knowledge-entity-recognition","path":"data.py","file_url":"https://github.com/wjn1996/mathematical-knowledge-entity-recognition/blob/HEAD/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":"acb71b1830976876","mcp_get_code":{"code_sha256":"acb71b1830976876"}},{"arxiv_id":"2008.00401","paper":"/paper/multilingual-translation-with-extensible","title":"Multilingual Translation with Extensible Multilingual Pretraining and Finetuning","date":"2020-08-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kenji-imamura/sentpiece_mimic","path":"src/SentPiece.py","file_url":"https://github.com/kenji-imamura/sentpiece_mimic/blob/HEAD/src/SentPiece.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":"18c68ce4f301ae56","mcp_get_code":{"code_sha256":"18c68ce4f301ae56"}},{"arxiv_id":"1809.03599","paper":"/paper/learning-named-entity-tagger-using-domain","title":"Learning Named Entity Tagger using Domain-Specific Dictionary","date":"2018-09-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shangjingbo1226/AutoNER","path":"preprocess_partial_ner/encode_mixed_dataset.py","file_url":"https://github.com/shangjingbo1226/AutoNER/blob/HEAD/preprocess_partial_ner/encode_mixed_dataset.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":"235d841405c43b80","mcp_get_code":{"code_sha256":"235d841405c43b80"}},{"arxiv_id":"1808.09357","paper":"/paper/rational-recurrences","title":"Rational Recurrences","date":"2018-08-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Noahs-ARK/rational-recurrences","path":"language_model/train_lm.py","file_url":"https://github.com/Noahs-ARK/rational-recurrences/blob/HEAD/language_model/train_lm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1855e1e72c54dfb0","mcp_get_code":{"code_sha256":"1855e1e72c54dfb0"}},{"arxiv_id":"1808.09357","paper":"/paper/rational-recurrences","title":"Rational Recurrences","date":"2018-08-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Noahs-ARK/rational-recurrences","path":"classification/dataloader.py","file_url":"https://github.com/Noahs-ARK/rational-recurrences/blob/HEAD/classification/dataloader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bb9a0e505460a9eb","mcp_get_code":{"code_sha256":"bb9a0e505460a9eb"}},{"arxiv_id":"1708.00107","paper":"/paper/learned-in-translation-contextualized-word","title":"Learned in Translation: Contextualized Word Vectors","date":"2017-08-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"richinkabra/CoVe-BCN","path":"MTLSTM/train/train_base.py","file_url":"https://github.com/richinkabra/CoVe-BCN/blob/HEAD/MTLSTM/train/train_base.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":"a78b6fff8d3fe895","mcp_get_code":{"code_sha256":"a78b6fff8d3fe895"}},{"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":"yangliuy/HybridNCM","path":"generation/hncm_dataloader.py","file_url":"https://github.com/yangliuy/HybridNCM/blob/HEAD/generation/hncm_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":"289d479248805b28","mcp_get_code":{"code_sha256":"289d479248805b28"}},{"arxiv_id":"2023.findings-emnlp.384","paper":null,"title":"arXiv:2023.findings-emnlp.384","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"JHL-HUST/SparseMA","path":"dataloader/dataloader_utils.py","file_url":"https://github.com/JHL-HUST/SparseMA/blob/HEAD/dataloader/dataloader_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":"db87d7553f6d4b43","mcp_get_code":{"code_sha256":"db87d7553f6d4b43"}}]}