{"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/clear-output","entry":"clear_output","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":3,"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":5,"n_samples_ran":2,"n_samples_fingerprinted":2,"n_places":7,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"unverified":3},"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":"2608.06310","paper":"/paper/arxiv-2608-06310","title":"RRC: Unlocking Generative Reward Models in LLM Reinforcement Learning via Ranking-Based Reward Construction","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"allenai/WildBench","path":"src/unified_utils.py","file_url":"https://github.com/allenai/WildBench/blob/HEAD/src/unified_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bab78e56b3db5391","mcp_get_code":{"code_sha256":"bab78e56b3db5391"}},{"arxiv_id":"2408.14774","paper":"/paper/instruct-skillmix-a-powerful-pipeline-for-llm","title":"Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning","date":"2024-08-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-pli/Instruct-SkillMix","path":"WildBench/src/unified_utils.py","file_url":"https://github.com/princeton-pli/Instruct-SkillMix/blob/HEAD/WildBench/src/unified_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5997e26073b93ac2","mcp_get_code":{"code_sha256":"5997e26073b93ac2"}},{"arxiv_id":"2406.04770","paper":"/paper/wildbench-benchmarking-llms-with-challenging","title":"WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild","date":"2024-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"allenai/wildbench","path":"src/unified_utils.py","file_url":"https://github.com/allenai/wildbench/blob/HEAD/src/unified_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"bab78e56b3db5391","mcp_get_code":{"code_sha256":"bab78e56b3db5391"}},{"arxiv_id":"2406.04127","paper":"/paper/are-we-done-with-mmlu","title":"Are We Done with MMLU?","date":"2024-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wildeval/zeroeval","path":"src/unified_utils.py","file_url":"https://github.com/wildeval/zeroeval/blob/HEAD/src/unified_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":"27c94753060ee864","mcp_get_code":{"code_sha256":"27c94753060ee864"}},{"arxiv_id":"2405.19874","paper":"/paper/is-in-context-learning-sufficient-for","title":"Is In-Context Learning Sufficient for Instruction Following in LLMs?","date":"2024-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tml-epfl/icl-alignment","path":"src/unified_utils.py","file_url":"https://github.com/tml-epfl/icl-alignment/blob/HEAD/src/unified_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":"484169aa666774ae","mcp_get_code":{"code_sha256":"484169aa666774ae"}},{"arxiv_id":"1911.03705","paper":"/paper/commongen-a-constrained-text-generation","title":"CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning","date":"2019-11-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"allenai/CommonGen-Eval","path":"data_utils.py","file_url":"https://github.com/allenai/CommonGen-Eval/blob/HEAD/data_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":"e00658a45cf979c4","mcp_get_code":{"code_sha256":"e00658a45cf979c4"}},{"arxiv_id":"2024.findings-emnlp.504","paper":null,"title":"arXiv:2024.findings-emnlp.504","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Re-Align/URIAL","path":"src/unified_utils.py","file_url":"https://github.com/Re-Align/URIAL/blob/HEAD/src/unified_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":"484169aa666774ae","mcp_get_code":{"code_sha256":"484169aa666774ae"}}]}