{"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/filter-words","entry":"filter_words","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":5,"n_papers_ran":1,"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":6,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":5},"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":"2411.07336","paper":"/paper/setlexsem-challenge-using-set-operations-to","title":"SetLexSem Challenge: Using Set Operations to Evaluate the Lexical and Semantic Robustness of Language Models","date":"2024-11-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amazon-science/setlexsem-challenge","path":"setlexsem/generate/sample.py","file_url":"https://github.com/amazon-science/setlexsem-challenge/blob/HEAD/setlexsem/generate/sample.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":"8431ddf5ad802651","mcp_get_code":{"code_sha256":"8431ddf5ad802651"}},{"arxiv_id":"2310.04678","paper":"/paper/doris-mae-scientific-document-retrieval-using","title":"DORIS-MAE: Scientific Document Retrieval using Multi-level Aspect-based Queries","date":"2023-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Real-Doris-Mae/Doris-Mae-Dataset","path":"create_candidate_pool/create_candidate_pool.py","file_url":"https://github.com/Real-Doris-Mae/Doris-Mae-Dataset/blob/HEAD/create_candidate_pool/create_candidate_pool.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"8bc1dcf8359aad73","mcp_get_code":{"code_sha256":"8bc1dcf8359aad73"}},{"arxiv_id":"2110.01256","paper":"/paper/revisiting-self-training-for-few-shot","title":"Revisiting Self-Training for Few-Shot Learning of Language Model","date":"2021-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"timoschick/pet","path":"petal.py","file_url":"https://github.com/timoschick/pet/blob/HEAD/petal.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":"a40f233e44e61f6e","mcp_get_code":{"code_sha256":"a40f233e44e61f6e"}},{"arxiv_id":"2109.01135","paper":"/paper/sequence-to-sequence-learning-with-latent","title":"Sequence-to-Sequence Learning with Latent Neural Grammars","date":"2021-09-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yli1/CGPS","path":"attention_visualization.py","file_url":"https://github.com/yli1/CGPS/blob/HEAD/attention_visualization.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":"efe28f7dd3f19e7f","mcp_get_code":{"code_sha256":"efe28f7dd3f19e7f"}},{"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_folder.py","file_url":"https://github.com/shangjingbo1226/AutoNER/blob/HEAD/preprocess_partial_ner/encode_folder.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":"312894e2aabb76ca","mcp_get_code":{"code_sha256":"312894e2aabb76ca"}},{"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":"0bdd8090a26c0251","mcp_get_code":{"code_sha256":"0bdd8090a26c0251"}}]}