{"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/mix-datasets","entry":"mix_datasets","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":7,"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":7,"n_places_pointer_only":3,"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":"2410.10093","paper":"/paper/how-to-leverage-demonstration-data-in","title":"How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective","date":"2024-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tengxiao1/GSIL","path":"gsil/alignment/data.py","file_url":"https://github.com/tengxiao1/GSIL/blob/HEAD/gsil/alignment/data.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a934ef1868f33dea","mcp_get_code":{"code_sha256":"a934ef1868f33dea"}},{"arxiv_id":"2410.03145","paper":"/paper/margin-matching-preference-optimization","title":"Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback","date":"2024-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kykim0/margin-matching-pref-opt","path":"src/alignment/data.py","file_url":"https://github.com/kykim0/margin-matching-pref-opt/blob/HEAD/src/alignment/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":"7f7ffeb2c6fe3a5d","mcp_get_code":{"code_sha256":"7f7ffeb2c6fe3a5d"}},{"arxiv_id":"2407.11007","paper":"/paper/panacea-a-foundation-model-for-clinical-trial","title":"Panacea: A foundation model for clinical trial search, summarization, design, and recruitment","date":"2024-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"linjc16/panacea","path":"alignment/data.py","file_url":"https://github.com/linjc16/panacea/blob/HEAD/alignment/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"55606478536a9b0c","mcp_get_code":{"code_sha256":"55606478536a9b0c"}},{"arxiv_id":"2405.19332","paper":"/paper/self-exploring-language-models-active","title":"Self-Exploring Language Models: Active Preference Elicitation for Online Alignment","date":"2024-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shenao-zhang/selm","path":"src/alignment/data.py","file_url":"https://github.com/shenao-zhang/selm/blob/HEAD/src/alignment/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c0fe52f3f8580286","mcp_get_code":{"code_sha256":"c0fe52f3f8580286"}},{"arxiv_id":"2405.07551","paper":"/paper/mumath-code-combining-tool-use-large-language","title":"MuMath-Code: Combining Tool-Use Large Language Models with Multi-perspective Data Augmentation for Mathematical Reasoning","date":"2024-05-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"project-numina/aimo-progress-prize","path":"training/aimo/utils/data.py","file_url":"https://github.com/project-numina/aimo-progress-prize/blob/HEAD/training/aimo/utils/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":"239e500bda6db834","mcp_get_code":{"code_sha256":"239e500bda6db834"}},{"arxiv_id":"2405.00675","paper":"/paper/self-play-preference-optimization-for","title":"Self-Play Preference Optimization for Language Model Alignment","date":"2024-05-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uclaml/sppo","path":"sppo/alignment/data.py","file_url":"https://github.com/uclaml/sppo/blob/HEAD/sppo/alignment/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":"55606478536a9b0c","mcp_get_code":{"code_sha256":"55606478536a9b0c"}},{"arxiv_id":"2403.09630","paper":"/paper/generalized-predictive-model-for-autonomous","title":"GenAD: Generalized Predictive Model for Autonomous Driving","date":"2024-03-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"valeoai/VideoActionModel","path":"vam/datalib/data_mixing.py","file_url":"https://github.com/valeoai/VideoActionModel/blob/HEAD/vam/datalib/data_mixing.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2eb7a18c3d3c6298","mcp_get_code":{"code_sha256":"2eb7a18c3d3c6298"}}]}