{"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/compute-reward","entry":"compute_reward","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":26,"n_papers_ran":6,"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":17,"n_samples_ran":4,"n_samples_fingerprinted":0,"n_places":28,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":2,"unverified":13},"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":"2606.21173","paper":"/paper/arxiv-2606-21173","title":"Inverting the Bellman Equation: From Q-Values to World Models","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"aletcher/inverting-bellman","path":"training/wm.py","file_url":"https://github.com/aletcher/inverting-bellman/blob/HEAD/training/wm.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"558feeda58f8f8b0","mcp_get_code":{"code_sha256":"558feeda58f8f8b0"}},{"arxiv_id":"2606.09124","paper":"/paper/arxiv-2606-09124","title":"A Regret Minimization Framework on Preference Learning in Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"OpenRLHF/OpenRLHF","path":"openrlhf/models/utils.py","file_url":"https://github.com/OpenRLHF/OpenRLHF/blob/HEAD/openrlhf/models/utils.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":"812f2e3f5cda7c93","mcp_get_code":{"code_sha256":"812f2e3f5cda7c93"}},{"arxiv_id":"2606.09124","paper":"/paper/arxiv-2606-09124","title":"A Regret Minimization Framework on Preference Learning in Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"YSLIU627/Regularized-Preference-Optimization","path":"OpenRLHF/openrlhf/models/utils.py","file_url":"https://github.com/YSLIU627/Regularized-Preference-Optimization/blob/HEAD/OpenRLHF/openrlhf/models/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":"99a2d91ea5aed978","mcp_get_code":{"code_sha256":"99a2d91ea5aed978"}},{"arxiv_id":"2603.22352","paper":"/paper/arxiv-2603-22352","title":"WIST: Web-Grounded Iterative Self-Play Tree for Domain-Targeted Reasoning Improvement","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"lfy-123/WIST","path":"openrlhf/models/utils.py","file_url":"https://github.com/lfy-123/WIST/blob/HEAD/openrlhf/models/utils.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":"812f2e3f5cda7c93","mcp_get_code":{"code_sha256":"812f2e3f5cda7c93"}},{"arxiv_id":"2602.18734","paper":"/paper/arxiv-2602-18734","title":"Rethinking Retrieval-Augmented Generation as a Cooperative Decision-Making Problem","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"CoderrrSong/CoRAG","path":"run_train.py","file_url":"https://github.com/CoderrrSong/CoRAG/blob/HEAD/run_train.py","status":"unverified","verification_level":0,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"21b0c022839c8308","mcp_get_code":{"code_sha256":"21b0c022839c8308"}},{"arxiv_id":"2601.20209","paper":"/paper/arxiv-2601-20209","title":"SPARK: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"jinyangwu/SPARK","path":"agent_system/environments/env_package/alfworld/envs_spark.py","file_url":"https://github.com/jinyangwu/SPARK/blob/HEAD/agent_system/environments/env_package/alfworld/envs_spark.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":"bcf675e5b7ccd7fd","mcp_get_code":{"code_sha256":"bcf675e5b7ccd7fd"}},{"arxiv_id":"2601.20209","paper":"/paper/arxiv-2601-20209","title":"SPARK: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"jinyangwu/SPARK","path":"agent_system/environments/env_package/sciworld/envs_spark.py","file_url":"https://github.com/jinyangwu/SPARK/blob/HEAD/agent_system/environments/env_package/sciworld/envs_spark.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":"724e8c51164a5ff8","mcp_get_code":{"code_sha256":"724e8c51164a5ff8"}},{"arxiv_id":"2601.17671","paper":"/paper/arxiv-2601-17671","title":"Align to the Pivot: Dual Alignment with Self-Feedback for Multilingual Math Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Rover912/PASMR","path":"openrlhf/models/utils.py","file_url":"https://github.com/Rover912/PASMR/blob/HEAD/openrlhf/models/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":"0d27f3b8c425d79f","mcp_get_code":{"code_sha256":"0d27f3b8c425d79f"}},{"arxiv_id":"2601.17563","paper":"/paper/arxiv-2601-17563","title":"Towards Generalisable Imitation Learning Through Conditioned Transition Estimation and Online Behaviour Alignment","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"NathanGavenski/UfO","path":"models/utils/discriminator.py","file_url":"https://github.com/NathanGavenski/UfO/blob/HEAD/models/utils/discriminator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f525e5e2d8d5ebe1","mcp_get_code":{"code_sha256":"f525e5e2d8d5ebe1"}},{"arxiv_id":"2601.05073","paper":"/paper/arxiv-2601-05073","title":"Milestones over Outcome: Unlocking Geometric Reasoning with Sub-Goal Verifiable Reward","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"FrontierX-Lab/SGVR","path":"MM-EUREKA/openrlhf/models/utils.py","file_url":"https://github.com/FrontierX-Lab/SGVR/blob/HEAD/MM-EUREKA/openrlhf/models/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":"0d27f3b8c425d79f","mcp_get_code":{"code_sha256":"0d27f3b8c425d79f"}},{"arxiv_id":"2601.00423","paper":"/paper/arxiv-2601-00423","title":"E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"shengjun-zhang/VisualGRPO","path":"fastvideo/reward_model/utils.py","file_url":"https://github.com/shengjun-zhang/VisualGRPO/blob/HEAD/fastvideo/reward_model/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":"a6ffa44bdd5d788c","mcp_get_code":{"code_sha256":"a6ffa44bdd5d788c"}},{"arxiv_id":"2509.24372","paper":"/paper/arxiv-2509-24372","title":"Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"VsonicV/es-at-scale","path":"archive/es_fine-tuning_conciseness.py","file_url":"https://github.com/VsonicV/es-at-scale/blob/HEAD/archive/es_fine-tuning_conciseness.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"09dac1843ac531ad","mcp_get_code":{"code_sha256":"09dac1843ac531ad"}},{"arxiv_id":"2509.02522","paper":"/paper/arxiv-2509-02522","title":"Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"ritzz-ai/PACS","path":"src/pacs/pacs_core_algos.py","file_url":"https://github.com/ritzz-ai/PACS/blob/HEAD/src/pacs/pacs_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ce26874ffa04ebcc","mcp_get_code":{"code_sha256":"ce26874ffa04ebcc"}},{"arxiv_id":"2506.08011","paper":"/paper/play-to-generalize-learning-to-reason-through","title":"Play to Generalize: Learning to Reason Through Game Play","date":"2025-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yunfeixie233/vigal","path":"openrlhf/models/utils.py","file_url":"https://github.com/yunfeixie233/vigal/blob/HEAD/openrlhf/models/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":"0d27f3b8c425d79f","mcp_get_code":{"code_sha256":"0d27f3b8c425d79f"}},{"arxiv_id":"2505.15456","paper":"/paper/teaching-language-models-to-evolve-with-users","title":"Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment","date":"2025-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"XingYuSSS/RLPA","path":"openrlhf/models/utils.py","file_url":"https://github.com/XingYuSSS/RLPA/blob/HEAD/openrlhf/models/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":"0d27f3b8c425d79f","mcp_get_code":{"code_sha256":"0d27f3b8c425d79f"}},{"arxiv_id":"2504.08837","paper":"/paper/vl-rethinker-incentivizing-self-reflection-of","title":"VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning","date":"2025-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tiger-ai-lab/vl-rethinker","path":"openrlhf/models/utils.py","file_url":"https://github.com/tiger-ai-lab/vl-rethinker/blob/HEAD/openrlhf/models/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":"0d27f3b8c425d79f","mcp_get_code":{"code_sha256":"0d27f3b8c425d79f"}},{"arxiv_id":"2504.07912","paper":"/paper/echo-chamber-rl-post-training-amplifies","title":"Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining","date":"2025-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rosieyzh/openrlhf-pretrain","path":"openrlhf/models/utils.py","file_url":"https://github.com/rosieyzh/openrlhf-pretrain/blob/HEAD/openrlhf/models/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":"0d27f3b8c425d79f","mcp_get_code":{"code_sha256":"0d27f3b8c425d79f"}},{"arxiv_id":"2503.10990","paper":"/paper/statistical-impossibility-and-possibility-of","title":"Statistical Impossibility and Possibility of Aligning LLMs with Human Preferences: From Condorcet Paradox to Nash Equilibrium","date":"2025-03-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"szk123456789/Nash_RS","path":"openrlhf/models/utils.py","file_url":"https://github.com/szk123456789/Nash_RS/blob/HEAD/openrlhf/models/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"99a2d91ea5aed978","mcp_get_code":{"code_sha256":"99a2d91ea5aed978"}},{"arxiv_id":"2502.14768","paper":"/paper/logic-rl-unleashing-llm-reasoning-with-rule","title":"Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning","date":"2025-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OpenLLMAI/OpenLLaMA2","path":"openrlhf/models/utils.py","file_url":"https://github.com/OpenLLMAI/OpenLLaMA2/blob/HEAD/openrlhf/models/utils.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":"812f2e3f5cda7c93","mcp_get_code":{"code_sha256":"812f2e3f5cda7c93"}},{"arxiv_id":"2502.03373","paper":"/paper/demystifying-long-chain-of-thought-reasoning","title":"Demystifying Long Chain-of-Thought Reasoning in LLMs","date":"2025-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eddycmu/demystify-long-cot","path":"openrlhf/openrlhf/models/utils.py","file_url":"https://github.com/eddycmu/demystify-long-cot/blob/HEAD/openrlhf/openrlhf/models/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1db73767f2ebd35e","mcp_get_code":{"code_sha256":"1db73767f2ebd35e"}},{"arxiv_id":"2412.16145","paper":"/paper/offline-reinforcement-learning-for-llm-multi","title":"Offline Reinforcement Learning for LLM Multi-Step Reasoning","date":"2024-12-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jwhj/oreo","path":"openrlhf/models/utils.py","file_url":"https://github.com/jwhj/oreo/blob/HEAD/openrlhf/models/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":"99a2d91ea5aed978","mcp_get_code":{"code_sha256":"99a2d91ea5aed978"}},{"arxiv_id":"2412.01981","paper":"/paper/free-process-rewards-without-process-labels","title":"Free Process Rewards without Process Labels","date":"2024-12-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lifan-yuan/implicitprm","path":"train/openrlhf/models/utils.py","file_url":"https://github.com/lifan-yuan/implicitprm/blob/HEAD/train/openrlhf/models/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":"38b7cb8077e28347","mcp_get_code":{"code_sha256":"38b7cb8077e28347"}},{"arxiv_id":"2410.20749","paper":"/paper/matryoshka-learning-to-drive-black-box-llms","title":"Matryoshka: Learning to Drive Black-Box LLMs with LLMs","date":"2024-10-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lichangh20/Matryoshka","path":"models/utils.py","file_url":"https://github.com/lichangh20/Matryoshka/blob/HEAD/models/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"99a2d91ea5aed978","mcp_get_code":{"code_sha256":"99a2d91ea5aed978"}},{"arxiv_id":"2404.18922","paper":"/paper/dpo-meets-ppo-reinforced-token-optimization","title":"DPO Meets PPO: Reinforced Token Optimization for RLHF","date":"2024-04-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zkshan2002/RTO","path":"openrlhf/models/utils.py","file_url":"https://github.com/zkshan2002/RTO/blob/HEAD/openrlhf/models/utils.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":"8b6588f381f57b54","mcp_get_code":{"code_sha256":"8b6588f381f57b54"}},{"arxiv_id":"2402.09345","paper":"/paper/mitigating-reward-hacking-via-information","title":"InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling","date":"2024-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"miaoyuchun/InfoRM","path":"openrlhf/models/utils.py","file_url":"https://github.com/miaoyuchun/InfoRM/blob/HEAD/openrlhf/models/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0d27f3b8c425d79f","mcp_get_code":{"code_sha256":"0d27f3b8c425d79f"}},{"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":"yinyueqin/denserewardrlhf-ppo","path":"denserlhf/trainer/ppo_utils/experience_maker.py","file_url":"https://github.com/yinyueqin/denserewardrlhf-ppo/blob/HEAD/denserlhf/trainer/ppo_utils/experience_maker.py","status":"unverified","verification_level":0,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b96e5125bdaa4277","mcp_get_code":{"code_sha256":"b96e5125bdaa4277"}},{"arxiv_id":"2107.06011","paper":"/paper/teaching-agents-how-to-map-spatial-reasoning","title":"Teaching Agents how to Map: Spatial Reasoning for Multi-Object Navigation","date":"2021-07-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PierreMarza/autonerf","path":"policy/rewards.py","file_url":"https://github.com/PierreMarza/autonerf/blob/HEAD/policy/rewards.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8916fff81fdefd69","mcp_get_code":{"code_sha256":"8916fff81fdefd69"}},{"arxiv_id":"1904.00370","paper":"/paper/variational-adversarial-active-learning","title":"Variational Adversarial Active Learning","date":"2019-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"johntiger1/vaal_querying","path":"rl_mnist.py","file_url":"https://github.com/johntiger1/vaal_querying/blob/HEAD/rl_mnist.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"e504dc7831b960c5","mcp_get_code":{"code_sha256":"e504dc7831b960c5"}}]}