{"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/reward-function","entry":"reward_function","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":7,"n_samples_ran":3,"n_samples_fingerprinted":2,"n_places":7,"n_places_pointer_only":3,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":2,"ran":0,"unverified":4},"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":"2602.03120","paper":"/paper/arxiv-2602-03120","title":"Quantized Evolution Strategies: High-precision Fine-tuning of Quantized LLMs at Low-precision Cost","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"dibbla/Quantized-Evolution-Strategies","path":"countdown/countdown_task.py","file_url":"https://github.com/dibbla/Quantized-Evolution-Strategies/blob/HEAD/countdown/countdown_task.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8c2091b066dcd117","mcp_get_code":{"code_sha256":"8c2091b066dcd117"}},{"arxiv_id":"2601.04525","paper":"/paper/arxiv-2601-04525","title":"GRACE: Reinforcement Learning for Grounded Response and Abstention under Contextual Evidence","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"YiboZhao624/Grace","path":"src/custom_reward_v2.py","file_url":"https://github.com/YiboZhao624/Grace/blob/HEAD/src/custom_reward_v2.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a294d7ea55dda89b","mcp_get_code":{"code_sha256":"a294d7ea55dda89b"}},{"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":"yynil/rwkvinside","path":"rl/train_rl_model.py","file_url":"https://github.com/yynil/rwkvinside/blob/HEAD/rl/train_rl_model.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":"f872aa95062d3ac2","mcp_get_code":{"code_sha256":"f872aa95062d3ac2"}},{"arxiv_id":"2310.07659","paper":"/paper/well-begun-is-half-done-generator-agnostic","title":"Well Begun is Half Done: Generator-agnostic Knowledge Pre-Selection for Knowledge-Grounded Dialogue","date":"2023-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qinlang14/GATE","path":"KnowledgeSelection/GATEModel/model.py","file_url":"https://github.com/qinlang14/GATE/blob/HEAD/KnowledgeSelection/GATEModel/model.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"168f20dbfff6d5a6","mcp_get_code":{"code_sha256":"168f20dbfff6d5a6"}},{"arxiv_id":"2302.02662","paper":"/paper/grounding-large-language-models-in","title":"Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning","date":"2023-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"flowersteam/grounding_llms_with_online_rl","path":"experiments/train_language_agent.py","file_url":"https://github.com/flowersteam/grounding_llms_with_online_rl/blob/HEAD/experiments/train_language_agent.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"351f0073ef3dccf5","mcp_get_code":{"code_sha256":"351f0073ef3dccf5"}},{"arxiv_id":"2206.05357","paper":"/paper/anchor-changing-regularized-natural-policy","title":"Anchor-Changing Regularized Natural Policy Gradient for Multi-Objective Reinforcement Learning","date":"2022-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tliu1997/arnpg-morl","path":"Acrobot-v1/ARNPG-EPD_acrobot.py","file_url":"https://github.com/tliu1997/arnpg-morl/blob/HEAD/Acrobot-v1/ARNPG-EPD_acrobot.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"202f8338817a32ef","mcp_get_code":{"code_sha256":"202f8338817a32ef"}},{"arxiv_id":"1805.00909","paper":"/paper/reinforcement-learning-and-control-as","title":"Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review","date":"2018-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sjoshi804/CS-267A-Final-Project","path":"agent_pyro.py","file_url":"https://github.com/sjoshi804/CS-267A-Final-Project/blob/HEAD/agent_pyro.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fcd52224251960ce","mcp_get_code":{"code_sha256":"fcd52224251960ce"}}]}