{"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/clean-doc","entry":"clean_doc","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":6,"n_papers_ran":0,"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":0,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":0,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":4},"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":"2403.00815","paper":"/paper/ram-ehr-retrieval-augmentation-meets-clinical","title":"RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Records","date":"2024-02-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ritaranx/RAM-EHR","path":"model_src/utils.py","file_url":"https://github.com/ritaranx/RAM-EHR/blob/HEAD/model_src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"99a40c2d6e975af6","mcp_get_code":{"code_sha256":"99a40c2d6e975af6"}},{"arxiv_id":"2306.15895","paper":"/paper/large-language-model-as-attributed-training-1","title":"Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias","date":"2023-06-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yueyu1030/attrprompt","path":"train_classifier/plm_model/utils.py","file_url":"https://github.com/yueyu1030/attrprompt/blob/HEAD/train_classifier/plm_model/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":"99a40c2d6e975af6","mcp_get_code":{"code_sha256":"99a40c2d6e975af6"}},{"arxiv_id":"2301.03726","paper":"/paper/neighborhood-regularized-self-training-for","title":"Neighborhood-Regularized Self-Training for Learning with Few Labels","date":"2023-01-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ritaranx/NeST","path":"utils.py","file_url":"https://github.com/ritaranx/NeST/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"99a40c2d6e975af6","mcp_get_code":{"code_sha256":"99a40c2d6e975af6"}},{"arxiv_id":"2108.00648","paper":"/paper/from-lsat-the-progress-and-challenges-of","title":"From LSAT: The Progress and Challenges of Complex Reasoning","date":"2021-08-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhongwanjun/AR-LSAT","path":"ARM/data_analysis/extract_cp_ner_dp_results.py","file_url":"https://github.com/zhongwanjun/AR-LSAT/blob/HEAD/ARM/data_analysis/extract_cp_ner_dp_results.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2771f46777734384","mcp_get_code":{"code_sha256":"2771f46777734384"}},{"arxiv_id":"1809.05679","paper":"/paper/graph-convolutional-networks-for-text","title":"Graph Convolutional Networks for Text Classification","date":"2018-09-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"codeKgu/text-gcn","path":"prep_data.py","file_url":"https://github.com/codeKgu/text-gcn/blob/HEAD/prep_data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d3fab161b1ada8bb","mcp_get_code":{"code_sha256":"d3fab161b1ada8bb"}},{"arxiv_id":"2024.findings-emnlp.621","paper":null,"title":"arXiv:2024.findings-emnlp.621","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"KDEGroup/Buzzer","path":"src/data_utils/csn.py","file_url":"https://github.com/KDEGroup/Buzzer/blob/HEAD/src/data_utils/csn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0a59f93b31fa6426","mcp_get_code":{"code_sha256":"0a59f93b31fa6426"}}]}