{"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/regex-match","entry":"regex_match","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":8,"n_papers_ran":7,"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":3,"n_samples_ran":2,"n_samples_fingerprinted":2,"n_places":8,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":2,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":1},"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":"2404.04163","paper":"/paper/dwell-in-the-beginning-how-language-models","title":"Dwell in the Beginning: How Language Models Embed Long Documents for Dense Retrieval","date":"2024-04-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cxcscmu/longembeddinganalysis","path":"OpenMatch/src/openmatch/qa_utils.py","file_url":"https://github.com/cxcscmu/longembeddinganalysis/blob/HEAD/OpenMatch/src/openmatch/qa_utils.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"93b0eef32604c3f7","mcp_get_code":{"code_sha256":"93b0eef32604c3f7"}},{"arxiv_id":"2308.13259","paper":"/paper/knowledge-driven-cot-exploring-faithful","title":"Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answering","date":"2023-08-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adelwang/kd-cot","path":"pipeline/Retriever/Retriever.py","file_url":"https://github.com/adelwang/kd-cot/blob/HEAD/pipeline/Retriever/Retriever.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"442d4287320d335d","mcp_get_code":{"code_sha256":"442d4287320d335d"}},{"arxiv_id":"2305.19912","paper":"/paper/structure-aware-language-model-pretraining","title":"Structure-Aware Language Model Pretraining Improves Dense Retrieval on Structured Data","date":"2023-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openmatch/openmatch","path":"src/openmatch/qa_utils.py","file_url":"https://github.com/openmatch/openmatch/blob/HEAD/src/openmatch/qa_utils.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"93b0eef32604c3f7","mcp_get_code":{"code_sha256":"93b0eef32604c3f7"}},{"arxiv_id":"2305.17331","paper":"/paper/augmentation-adapted-retriever-improves","title":"Augmentation-Adapted Retriever Improves Generalization of Language Models as Generic Plug-In","date":"2023-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OpenMatch/Augmentation-Adapted-Retriever","path":"src/Retriever/qa_utils.py","file_url":"https://github.com/OpenMatch/Augmentation-Adapted-Retriever/blob/HEAD/src/Retriever/qa_utils.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"93b0eef32604c3f7","mcp_get_code":{"code_sha256":"93b0eef32604c3f7"}},{"arxiv_id":"2305.06984","paper":"/paper/evaluating-open-domain-question-answering-in","title":"Evaluating Open-Domain Question Answering in the Era of Large Language Models","date":"2023-05-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ehsk/openqa-eval","path":"src/oqaeval/squad_evaluate.py","file_url":"https://github.com/ehsk/openqa-eval/blob/HEAD/src/oqaeval/squad_evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"db77dd5d7d909a53","mcp_get_code":{"code_sha256":"db77dd5d7d909a53"}},{"arxiv_id":"2102.10073","paper":"/paper/pyserini-an-easy-to-use-python-toolkit-to","title":"Pyserini: An Easy-to-Use Python Toolkit to Support Replicable IR Research with Sparse and Dense Representations","date":"2021-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"castorini/pyserini","path":"pyserini/eval/evaluate_dpr_retrieval.py","file_url":"https://github.com/castorini/pyserini/blob/HEAD/pyserini/eval/evaluate_dpr_retrieval.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"93b0eef32604c3f7","mcp_get_code":{"code_sha256":"93b0eef32604c3f7"}},{"arxiv_id":"2101.00294","paper":"/paper/reader-guided-passage-reranking-for-open","title":"Rider: Reader-Guided Passage Reranking for Open-Domain Question Answering","date":"2021-01-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"morningmoni/GAR","path":"rider/rider.py","file_url":"https://github.com/morningmoni/GAR/blob/HEAD/rider/rider.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"442d4287320d335d","mcp_get_code":{"code_sha256":"442d4287320d335d"}},{"arxiv_id":"2023.findings-acl.734","paper":null,"title":"arXiv:2023.findings-acl.734","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"OpenMatch/OpenMatch","path":"src/openmatch/qa_utils.py","file_url":"https://github.com/OpenMatch/OpenMatch/blob/HEAD/src/openmatch/qa_utils.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"93b0eef32604c3f7","mcp_get_code":{"code_sha256":"93b0eef32604c3f7"}}]}