{"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/strip-accents","entry":"strip_accents","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":10,"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":8,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":10,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":8},"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":"2601.02578","paper":"/paper/arxiv-2601-02578","title":"DataParasite Enables Scalable and Repurposable Online Data Curation","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"emeryberger/CSrankings","path":"util/old/split-csrankings.py","file_url":"https://github.com/emeryberger/CSrankings/blob/HEAD/util/old/split-csrankings.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"b34f5dfa407987e8","mcp_get_code":{"code_sha256":"b34f5dfa407987e8"}},{"arxiv_id":"2304.01196","paper":"/paper/baize-an-open-source-chat-model-with","title":"Baize: An Open-Source Chat Model with Parameter-Efficient Tuning on Self-Chat Data","date":"2023-04-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ilyagusev/rulm","path":"data_processing/convert_wiki.py","file_url":"https://github.com/ilyagusev/rulm/blob/HEAD/data_processing/convert_wiki.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":"b34f5dfa407987e8","mcp_get_code":{"code_sha256":"b34f5dfa407987e8"}},{"arxiv_id":"2109.08359","paper":"/paper/distilling-linguistic-context-for-language","title":"Distilling Linguistic Context for Language Model Compression","date":"2021-09-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"geondopark/ckd","path":"data_augment.py","file_url":"https://github.com/geondopark/ckd/blob/HEAD/data_augment.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"22fcb8611ccd6b38","mcp_get_code":{"code_sha256":"22fcb8611ccd6b38"}},{"arxiv_id":"2105.02732","paper":"/paper/what-s-in-the-box-an-analysis-of-undesirable","title":"What's in the Box? A Preliminary Analysis of Undesirable Content in the Common Crawl Corpus","date":"2021-05-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"josephdviviano/whatsinthebox","path":"witb/utils/textutils.py","file_url":"https://github.com/josephdviviano/whatsinthebox/blob/HEAD/witb/utils/textutils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c2e55f8f1a1f1444","mcp_get_code":{"code_sha256":"c2e55f8f1a1f1444"}},{"arxiv_id":"2006.07264","paper":"/paper/low-resource-languages-a-review-of-past-work","title":"Low-resource Languages: A Review of Past Work and Future Challenges","date":"2020-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"danielinux7/Multilingual-Parallel-Corpus","path":"src/utils/ab/parse_dictionary.py","file_url":"https://github.com/danielinux7/Multilingual-Parallel-Corpus/blob/HEAD/src/utils/ab/parse_dictionary.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":"048d5b46b5abc501","mcp_get_code":{"code_sha256":"048d5b46b5abc501"}},{"arxiv_id":"2003.13027","paper":"/paper/abstractive-text-summarization-based-on","title":"Abstractive Text Summarization based on Language Model Conditioning and Locality Modeling","date":"2020-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"axenov/BERT-Summ-OpenNMT","path":"summarizer.py","file_url":"https://github.com/axenov/BERT-Summ-OpenNMT/blob/HEAD/summarizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4b6fcd8cda10ebc3","mcp_get_code":{"code_sha256":"4b6fcd8cda10ebc3"}},{"arxiv_id":"2003.10564","paper":"/paper/improving-yoruba-diacritic-restoration","title":"Improving Yorùbá Diacritic Restoration","date":"2020-03-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Niger-Volta-LTI/yoruba-adr","path":"src/make_parallel_text.py","file_url":"https://github.com/Niger-Volta-LTI/yoruba-adr/blob/HEAD/src/make_parallel_text.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"043014f7b6c20907","mcp_get_code":{"code_sha256":"043014f7b6c20907"}},{"arxiv_id":"1910.06262","paper":"/paper/restoring-ancient-text-using-deep-learning-a","title":"Restoring ancient text using deep learning: a case study on Greek epigraphy","date":"2019-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sommerschield/ancient-text-restoration","path":"pythia/util/text_clean.py","file_url":"https://github.com/sommerschield/ancient-text-restoration/blob/HEAD/pythia/util/text_clean.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":"b34f5dfa407987e8","mcp_get_code":{"code_sha256":"b34f5dfa407987e8"}},{"arxiv_id":"1902.01718","paper":"/paper/end-to-end-open-domain-question-answering","title":"End-to-End Open-Domain Question Answering with BERTserini","date":"2019-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rsvp-ai/bertserini","path":"bertserini/utils/utils.py","file_url":"https://github.com/rsvp-ai/bertserini/blob/HEAD/bertserini/utils/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":"b668a6a9dda0f7b1","mcp_get_code":{"code_sha256":"b668a6a9dda0f7b1"}},{"arxiv_id":"1805.05492","paper":"/paper/did-the-model-understand-the-question","title":"Did the Model Understand the Question?","date":"2018-05-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pramodkaushik/np_analysis","path":"neural_programmer/wiki_data.py","file_url":"https://github.com/pramodkaushik/np_analysis/blob/HEAD/neural_programmer/wiki_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":"8378d8e8e76a6e45","mcp_get_code":{"code_sha256":"8378d8e8e76a6e45"}}]}