{"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/get-data-statistics","entry":"get_data_statistics","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":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":3,"n_samples_ran":1,"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":1,"unverified":2},"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":"2604.00536","paper":"/paper/arxiv-2604-00536","title":"Optimsyn: Influence-Guided Rubrics Optimization for Synthetic Data Generation","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"FanZT6/OptimSyn","path":"training/influence/warmup/data_arguments.py","file_url":"https://github.com/FanZT6/OptimSyn/blob/HEAD/training/influence/warmup/data_arguments.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fc5b455108e53a6e","mcp_get_code":{"code_sha256":"fc5b455108e53a6e"}},{"arxiv_id":"2602.08351","paper":"/paper/arxiv-2602-08351","title":"The Chicken and Egg Dilemma: Co-optimizing Data and Model Configurations for LLMs","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"princeton-nlp/LESS","path":"less/train/data_arguments.py","file_url":"https://github.com/princeton-nlp/LESS/blob/HEAD/less/train/data_arguments.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fc5b455108e53a6e","mcp_get_code":{"code_sha256":"fc5b455108e53a6e"}},{"arxiv_id":"2407.15235","paper":"/paper/tagcos-task-agnostic-gradient-clustered","title":"TAGCOS: Task-agnostic Gradient Clustered Coreset Selection for Instruction Tuning Data","date":"2024-07-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"2003pro/tagcos","path":"train/data_arguments.py","file_url":"https://github.com/2003pro/tagcos/blob/HEAD/train/data_arguments.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fc5b455108e53a6e","mcp_get_code":{"code_sha256":"fc5b455108e53a6e"}},{"arxiv_id":"2402.04333","paper":"/paper/less-selecting-influential-data-for-targeted","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","date":"2024-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-nlp/less","path":"less/train/data_arguments.py","file_url":"https://github.com/princeton-nlp/less/blob/HEAD/less/train/data_arguments.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fc5b455108e53a6e","mcp_get_code":{"code_sha256":"fc5b455108e53a6e"}},{"arxiv_id":"2307.02245","paper":"/paper/set-learning-for-accurate-and-calibrated","title":"Set Learning for Accurate and Calibrated Models","date":"2023-07-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lukasmut/oko","path":"utils.py","file_url":"https://github.com/lukasmut/oko/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c23ff4a1bdfee069","mcp_get_code":{"code_sha256":"c23ff4a1bdfee069"}},{"arxiv_id":"2210.00354","paper":"/paper/model-free-sequential-testing-for-conditional","title":"Model-X Sequential Testing for Conditional Independence via Testing by Betting","date":"2022-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shaersh/ecrt","path":"src/sampling_functions.py","file_url":"https://github.com/shaersh/ecrt/blob/HEAD/src/sampling_functions.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9138c2a93cce4369","mcp_get_code":{"code_sha256":"9138c2a93cce4369"}}]}