{"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/reduce-std","entry":"reduce_std","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":5,"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":2,"n_samples_fingerprinted":2,"n_places":6,"n_places_pointer_only":0,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":1},"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":"2410.06554","paper":"/paper/the-accuracy-paradox-in-rlhf-when-better","title":"The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models","date":"2024-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"EIT-NLP/AccuracyParadox-RLHF","path":"fgrlhf/utils.py","file_url":"https://github.com/EIT-NLP/AccuracyParadox-RLHF/blob/HEAD/fgrlhf/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"174bfbbeb1f29e12","mcp_get_code":{"code_sha256":"174bfbbeb1f29e12"}},{"arxiv_id":"2402.04315","paper":"/paper/training-language-models-to-generate-text","title":"Training Language Models to Generate Text with Citations via Fine-grained Rewards","date":"2024-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hcy123902/atg-w-fg-rw","path":"fgrlhf/utils.py","file_url":"https://github.com/hcy123902/atg-w-fg-rw/blob/HEAD/fgrlhf/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":"174bfbbeb1f29e12","mcp_get_code":{"code_sha256":"174bfbbeb1f29e12"}},{"arxiv_id":"2305.13829","paper":"/paper/learn-from-mistakes-through-cooperative","title":"Learning from Mistakes via Cooperative Study Assistant for Large Language Models","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dqwang122/salam","path":"src/utils/utils.py","file_url":"https://github.com/dqwang122/salam/blob/HEAD/src/utils/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"174bfbbeb1f29e12","mcp_get_code":{"code_sha256":"174bfbbeb1f29e12"}},{"arxiv_id":"2212.10409","paper":"/paper/reinforced-clarification-question-generation","title":"ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situations","date":"2022-12-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"allenai/clarifydelphi","path":"Code/utils/utils.py","file_url":"https://github.com/allenai/clarifydelphi/blob/HEAD/Code/utils/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":"174bfbbeb1f29e12","mcp_get_code":{"code_sha256":"174bfbbeb1f29e12"}},{"arxiv_id":"2210.03078","paper":"/paper/rainier-reinforced-knowledge-introspector-for","title":"Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering","date":"2022-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liujch1998/rainier","path":"rainier/ppo.py","file_url":"https://github.com/liujch1998/rainier/blob/HEAD/rainier/ppo.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"24a6def7a7175be1","mcp_get_code":{"code_sha256":"24a6def7a7175be1"}},{"arxiv_id":"1806.07851","paper":"/paper/sim-to-real-reinforcement-learning-for","title":"Sim-to-Real Reinforcement Learning for Deformable Object Manipulation","date":"2018-06-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JanMatas/Rainbow_ddpg","path":"rainbow_ddpg/ddpg.py","file_url":"https://github.com/JanMatas/Rainbow_ddpg/blob/HEAD/rainbow_ddpg/ddpg.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"955e88fe58fc905a","mcp_get_code":{"code_sha256":"955e88fe58fc905a"}}]}