{"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/sanitize-text","entry":"sanitize_text","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":2,"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":"2604.06854","paper":"/paper/arxiv-2604-06854","title":"To Adapt or not to Adapt, Rethinking the Value of Medical Knowledge-Aware Large Language Models To Adapt or not to Adapt, Rethinking the Value of Medical Knowledge-Aware Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"Maits27/Deduplication","path":"limpieza/limpiar.py","file_url":"https://github.com/Maits27/Deduplication/blob/HEAD/limpieza/limpiar.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f20265615e665fbb","mcp_get_code":{"code_sha256":"f20265615e665fbb"}},{"arxiv_id":"2604.06559","paper":"/paper/arxiv-2604-06559","title":"ExplainFuzz: Explainable and Constraint-Conditioned Test Generation with Probabilistic Circuits","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"niMgnoeSeeL/ExplainFuzz","path":"xml_concretizer/extract_pools.py","file_url":"https://github.com/niMgnoeSeeL/ExplainFuzz/blob/HEAD/xml_concretizer/extract_pools.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c01d8001e909f052","mcp_get_code":{"code_sha256":"c01d8001e909f052"}},{"arxiv_id":"2305.15387","paper":"/paper/peek-across-improving-multi-document-modeling","title":"Peek Across: Improving Multi-Document Modeling via Cross-Document Question-Answering","date":"2023-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aviclu/peekacross","path":"pretrain_qamden.py","file_url":"https://github.com/aviclu/peekacross/blob/HEAD/pretrain_qamden.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"31e3adacd2841d84","mcp_get_code":{"code_sha256":"31e3adacd2841d84"}},{"arxiv_id":"2305.10722","paper":"/paper/discriminative-diffusion-models-as-few-shot","title":"Discffusion: Discriminative Diffusion Models as Few-shot Vision and Language Learners","date":"2023-05-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eric-ai-lab/dsd","path":"dsd_infer.py","file_url":"https://github.com/eric-ai-lab/dsd/blob/HEAD/dsd_infer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fc89a1b3e420c811","mcp_get_code":{"code_sha256":"fc89a1b3e420c811"}},{"arxiv_id":"2110.08499","paper":"/paper/primer-pyramid-based-masked-sentence-pre","title":"PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization","date":"2021-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"allenai/open-mds","path":"src/open_mds/common/util.py","file_url":"https://github.com/allenai/open-mds/blob/HEAD/src/open_mds/common/util.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":"31e3adacd2841d84","mcp_get_code":{"code_sha256":"31e3adacd2841d84"}},{"arxiv_id":"2006.03659","paper":"/paper/declutr-deep-contrastive-learning-for","title":"DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations","date":"2020-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JohnGiorgi/DeCLUTR","path":"declutr/common/util.py","file_url":"https://github.com/JohnGiorgi/DeCLUTR/blob/HEAD/declutr/common/util.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":"31e3adacd2841d84","mcp_get_code":{"code_sha256":"31e3adacd2841d84"}}]}