{"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/rewardmodel","entry":"RewardModel","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":10,"n_papers_ran":7,"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":10,"n_samples_ran":7,"n_samples_fingerprinted":1,"n_places":10,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":7,"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":"2601.06487","paper":"/paper/arxiv-2601-06487","title":"ArenaRL: Scaling RL for Open-Ended Agents via Tournamentbased Relative Ranking","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Alibaba-NLP/qqr","path":"qqr/reward_models/arena/double_elimination.py","file_url":"https://github.com/Alibaba-NLP/qqr/blob/HEAD/qqr/reward_models/arena/double_elimination.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":"859b40ac082593cf","mcp_get_code":{"code_sha256":"859b40ac082593cf"}},{"arxiv_id":"2509.23802","paper":"/paper/arxiv-2509-23802","title":"STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"iiiiii11/STAIR","path":"reward_model.py","file_url":"https://github.com/iiiiii11/STAIR/blob/HEAD/reward_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b0f89e1331a5019","mcp_get_code":{"code_sha256":"9b0f89e1331a5019"}},{"arxiv_id":"2506.00388","paper":"/paper/clarify-contrastive-preference-reinforcement","title":"CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries","date":"2025-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"moonoutcloudback/clarify_pbrl","path":"reward_model.py","file_url":"https://github.com/moonoutcloudback/clarify_pbrl/blob/HEAD/reward_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3d27511acaa0b08b","mcp_get_code":{"code_sha256":"3d27511acaa0b08b"}},{"arxiv_id":"2408.04190","paper":"/paper/listwise-reward-estimation-for-offline","title":"Listwise Reward Estimation for Offline Preference-based Reinforcement Learning","date":"2024-08-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chwoong/lire","path":"Reward_learning/reward_model.py","file_url":"https://github.com/chwoong/lire/blob/HEAD/Reward_learning/reward_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"84a651a8f7389135","mcp_get_code":{"code_sha256":"84a651a8f7389135"}},{"arxiv_id":"2402.17257","paper":"/paper/rime-robust-preference-based-reinforcement","title":"RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences","date":"2024-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cjreinforce/rime_icml2024","path":"reward_model_RIME.py","file_url":"https://github.com/cjreinforce/rime_icml2024/blob/HEAD/reward_model_RIME.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3a1138fef2b4ce3c","mcp_get_code":{"code_sha256":"3a1138fef2b4ce3c"}},{"arxiv_id":"2306.00398","paper":"/paper/preference-grounded-token-level-guidance-for-1","title":"Preference-grounded Token-level Guidance for Language Model Fine-tuning","date":"2023-06-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shentao-yang/preference_grounded_guidance","path":"sum_task/reward_model.py","file_url":"https://github.com/shentao-yang/preference_grounded_guidance/blob/HEAD/sum_task/reward_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6fdf28a6230ef77d","mcp_get_code":{"code_sha256":"6fdf28a6230ef77d"}},{"arxiv_id":"2305.17400","paper":"/paper/query-policy-misalignment-in-preference-based","title":"Query-Policy Misalignment in Preference-Based Reinforcement Learning","date":"2023-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huxiao09/qpa","path":"reward_model.py","file_url":"https://github.com/huxiao09/qpa/blob/HEAD/reward_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fe29d8cf8d1bbbeb","mcp_get_code":{"code_sha256":"fe29d8cf8d1bbbeb"}},{"arxiv_id":"2205.12401","paper":"/paper/reward-uncertainty-for-exploration-in-1","title":"Reward Uncertainty for Exploration in Preference-based Reinforcement Learning","date":"2022-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rll-research/rune","path":"reward_model_explore.py","file_url":"https://github.com/rll-research/rune/blob/HEAD/reward_model_explore.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b518ac768ca194c9","mcp_get_code":{"code_sha256":"b518ac768ca194c9"}},{"arxiv_id":"2106.05091","paper":"/paper/pebble-feedback-efficient-interactive","title":"PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training","date":"2021-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pokaxpoka/b_pref","path":"reward_model.py","file_url":"https://github.com/pokaxpoka/b_pref/blob/HEAD/reward_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7317e4f9684221bb","mcp_get_code":{"code_sha256":"7317e4f9684221bb"}},{"arxiv_id":"1912.01603","paper":"/paper/dream-to-control-learning-behaviors-by-latent","title":"Dream to Control: Learning Behaviors by Latent Imagination","date":"2019-12-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Yizhao111/dreamer-pytorch","path":"agent.py","file_url":"https://github.com/Yizhao111/dreamer-pytorch/blob/HEAD/agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ff12acbebe54d7cc","mcp_get_code":{"code_sha256":"ff12acbebe54d7cc"}}]}