{"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-dataset","entry":"clean_dataset","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":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":6,"n_samples_ran":0,"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":0,"unverified":6},"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":"2310.07579","paper":"/paper/in-context-unlearning-language-models-as-few","title":"In-Context Unlearning: Language Models as Few Shot Unlearners","date":"2023-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MartinPawel/In-Context-Unlearning","path":"local_dataset_utilities.py","file_url":"https://github.com/MartinPawel/In-Context-Unlearning/blob/HEAD/local_dataset_utilities.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b8a02b31356a1521","mcp_get_code":{"code_sha256":"b8a02b31356a1521"}},{"arxiv_id":"2305.07759","paper":"/paper/tinystories-how-small-can-language-models-be","title":"TinyStories: How Small Can Language Models Be and Still Speak Coherent English?","date":"2023-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"danbraunai/simple_stories_train","path":"simple_stories_train/tokenizer.py","file_url":"https://github.com/danbraunai/simple_stories_train/blob/HEAD/simple_stories_train/tokenizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"69981ccab3e11aa0","mcp_get_code":{"code_sha256":"69981ccab3e11aa0"}},{"arxiv_id":"2202.04599","paper":"/paper/missing-data-imputation-and-acquisition-with","title":"Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlo","date":"2022-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ipeis/HH-VAEM","path":"src/datasets.py","file_url":"https://github.com/ipeis/HH-VAEM/blob/HEAD/src/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"896634a7bacb2c3e","mcp_get_code":{"code_sha256":"896634a7bacb2c3e"}},{"arxiv_id":"2003.06222","paper":"/paper/an-evaluation-of-change-point-detection","title":"An Evaluation of Change Point Detection Algorithms","date":"2020-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alan-turing-institute/TCPD","path":"build_tcpd.py","file_url":"https://github.com/alan-turing-institute/TCPD/blob/HEAD/build_tcpd.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"720f4672c2ed9380","mcp_get_code":{"code_sha256":"720f4672c2ed9380"}},{"arxiv_id":"1808.08166","paper":"/paper/an-empirical-study-of-rich-subgroup-fairness","title":"An Empirical Study of Rich Subgroup Fairness for Machine Learning","date":"2018-08-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"algowatchpenn/GerryFair","path":"gerryfair/clean.py","file_url":"https://github.com/algowatchpenn/GerryFair/blob/HEAD/gerryfair/clean.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cd537de833dfde8f","mcp_get_code":{"code_sha256":"cd537de833dfde8f"}},{"arxiv_id":"1808.08166","paper":"/paper/an-empirical-study-of-rich-subgroup-fairness","title":"An Empirical Study of Rich Subgroup Fairness for Machine Learning","date":"2018-08-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sethneel/GerryFair","path":"gerryfair/clean.py","file_url":"https://github.com/sethneel/GerryFair/blob/HEAD/gerryfair/clean.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8adf5d639ebb5df1","mcp_get_code":{"code_sha256":"8adf5d639ebb5df1"}}]}