{"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/aggregate-predictions","entry":"aggregate_predictions","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":3,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":0,"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":"2506.20512","paper":"/paper/octothinker-mid-training-incentivizes","title":"OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling","date":"2025-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gair-nlp/octothinker","path":"eval/summarize_results.py","file_url":"https://github.com/gair-nlp/octothinker/blob/HEAD/eval/summarize_results.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":"33425041e7f88b7f","mcp_get_code":{"code_sha256":"33425041e7f88b7f"}},{"arxiv_id":"2407.03263","paper":"/paper/a-unified-framework-for-3d-scene","title":"A Unified Framework for 3D Scene Understanding","date":"2024-07-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dk-liang/uniseg3d","path":"uniseg3d/instance_seg_eval.py","file_url":"https://github.com/dk-liang/uniseg3d/blob/HEAD/uniseg3d/instance_seg_eval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cdbb52ae3380c642","mcp_get_code":{"code_sha256":"cdbb52ae3380c642"}},{"arxiv_id":"2402.03300","paper":"/paper/deepseekmath-pushing-the-limits-of","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","date":"2024-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deepseek-ai/deepseek-math","path":"evaluation/summarize_results.py","file_url":"https://github.com/deepseek-ai/deepseek-math/blob/HEAD/evaluation/summarize_results.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"33425041e7f88b7f","mcp_get_code":{"code_sha256":"33425041e7f88b7f"}},{"arxiv_id":"2108.11577","paper":"/paper/machine-unlearning-of-features-and-labels","title":"Machine Unlearning of Features and Labels","date":"2021-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alewarne/machineunlearning","path":"Unlearner/ensemble.py","file_url":"https://github.com/alewarne/machineunlearning/blob/HEAD/Unlearner/ensemble.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ee67d0762eb1c528","mcp_get_code":{"code_sha256":"ee67d0762eb1c528"}},{"arxiv_id":"2025.acl-long.1506","paper":null,"title":"arXiv:2025.acl-long.1506","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"deepseek-ai/DeepSeek-Math","path":"evaluation/summarize_results.py","file_url":"https://github.com/deepseek-ai/DeepSeek-Math/blob/HEAD/evaluation/summarize_results.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"33425041e7f88b7f","mcp_get_code":{"code_sha256":"33425041e7f88b7f"}}]}