{"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/format-reward","entry":"format_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":35,"n_papers_ran":15,"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":25,"n_samples_ran":11,"n_samples_fingerprinted":4,"n_places":39,"n_places_pointer_only":18,"by_status":{"ran_honours":6,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":5,"unverified":14},"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":"2608.26550","paper":"/paper/arxiv-2608-26550","title":"SPEAR: Distilling Domain-Adaptive Reasoning Skeletons via Sequential Symbolic Alignment in Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"zhuochunli/SPEAR","path":"reward.py","file_url":"https://github.com/zhuochunli/SPEAR/blob/HEAD/reward.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3f97780f21c0b793","mcp_get_code":{"code_sha256":"3f97780f21c0b793"}},{"arxiv_id":"2608.18096","paper":"/paper/arxiv-2608-18096","title":"MAVEN: A Macro-Societal Value Evaluation Framework of Multimodal Content with Compact Aligned Evaluators","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"zzzzzzzzjj/MAVEN","path":"src/train/reward_funcs.py","file_url":"https://github.com/zzzzzzzzjj/MAVEN/blob/HEAD/src/train/reward_funcs.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":"cb8ca9226da3a936","mcp_get_code":{"code_sha256":"cb8ca9226da3a936"}},{"arxiv_id":"2607.26710","paper":"/paper/arxiv-2607-26710","title":"PowerAtlas: Towards Electricity-Computing Co-Scheduling for Power Systems","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"JAVA-Jiang/PowerAtlas","path":"poweratlas/reward.py","file_url":"https://github.com/JAVA-Jiang/PowerAtlas/blob/HEAD/poweratlas/reward.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"df8361c06df60d8e","mcp_get_code":{"code_sha256":"df8361c06df60d8e"}},{"arxiv_id":"2606.12900","paper":"/paper/arxiv-2606-12900","title":"Zero-source LLM Hallucination Detection with Human-like Criteria Probing","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"TRISKEL10N/HCPD","path":"src/open_r1/rewards.py","file_url":"https://github.com/TRISKEL10N/HCPD/blob/HEAD/src/open_r1/rewards.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":"ce353d566f3f2c9f","mcp_get_code":{"code_sha256":"ce353d566f3f2c9f"}},{"arxiv_id":"2606.06819","paper":"/paper/arxiv-2606-06819","title":"VideoSEG-O3: A Multi-turn Reinforcement Learning Framework for Reasoning Video Object Segmentation","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Dmmm1997/VideoSEG-O3","path":"projects/open_r1/rewards.py","file_url":"https://github.com/Dmmm1997/VideoSEG-O3/blob/HEAD/projects/open_r1/rewards.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":"09e6ed2ece2264f7","mcp_get_code":{"code_sha256":"09e6ed2ece2264f7"}},{"arxiv_id":"2605.11666","paper":"/paper/arxiv-2605-11666","title":"Evolutionary Task Discovery: Advancing Reasoning Frontiers via Skill Composition and Complexity Scaling","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"liqinye/EvoTD","path":"src/reward_function.py","file_url":"https://github.com/liqinye/EvoTD/blob/HEAD/src/reward_function.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d67cad27811abe22","mcp_get_code":{"code_sha256":"d67cad27811abe22"}},{"arxiv_id":"2605.02545","paper":"/paper/arxiv-2605-02545","title":"Strategy-Aware Optimization Modeling with Reasoning LLMs","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"rachhhhing/SAGE","path":"reward_func/batch_score.py","file_url":"https://github.com/rachhhhing/SAGE/blob/HEAD/reward_func/batch_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c15d4169879b293c","mcp_get_code":{"code_sha256":"c15d4169879b293c"}},{"arxiv_id":"2605.02545","paper":"/paper/arxiv-2605-02545","title":"Strategy-Aware Optimization Modeling with Reasoning LLMs","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"rachhhhing/SAGE","path":"reward_func/batch_score_no_tem.py","file_url":"https://github.com/rachhhhing/SAGE/blob/HEAD/reward_func/batch_score_no_tem.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ef9fa7347607c290","mcp_get_code":{"code_sha256":"ef9fa7347607c290"}},{"arxiv_id":"2602.10635","paper":"/paper/arxiv-2602-10635","title":"OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"MIT-MI/human_behavior_atlas","path":"training/rl/reward_function/human_behaviour.py","file_url":"https://github.com/MIT-MI/human_behavior_atlas/blob/HEAD/training/rl/reward_function/human_behaviour.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fd2112df3f149ab0","mcp_get_code":{"code_sha256":"fd2112df3f149ab0"}},{"arxiv_id":"2602.10635","paper":"/paper/arxiv-2602-10635","title":"OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"MIT-MI/human_behavior_atlas","path":"training/rl/reward_function/human_behaviour_harpo.py","file_url":"https://github.com/MIT-MI/human_behavior_atlas/blob/HEAD/training/rl/reward_function/human_behaviour_harpo.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b55511b458d41522","mcp_get_code":{"code_sha256":"b55511b458d41522"}},{"arxiv_id":"2602.03876","paper":"/paper/arxiv-2602-03876","title":"GOPO: Policy Optimization using Ranked Rewards","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"friendshipkim/gopo","path":"src/open_r1/rewards.py","file_url":"https://github.com/friendshipkim/gopo/blob/HEAD/src/open_r1/rewards.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":"ce353d566f3f2c9f","mcp_get_code":{"code_sha256":"ce353d566f3f2c9f"}},{"arxiv_id":"2602.02258","paper":"/paper/arxiv-2602-02258","title":"Alignment-Aware Model Adaptation via Feedback-Guided Optimization","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"facebookresearch/TruthRL","path":"training/open-r1/src/open_r1/rewards.py","file_url":"https://github.com/facebookresearch/TruthRL/blob/HEAD/training/open-r1/src/open_r1/rewards.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ce353d566f3f2c9f","mcp_get_code":{"code_sha256":"ce353d566f3f2c9f"}},{"arxiv_id":"2601.19686","paper":"/paper/arxiv-2601-19686","title":"2 RELATED WORK Reinforcement learning has emerged as a powerful paradigm for enhancing the reasoning abilities of LLMs","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"zywang0104/Video-KTR","path":"src/r1-v/src/open_r1/grpo.py","file_url":"https://github.com/zywang0104/Video-KTR/blob/HEAD/src/r1-v/src/open_r1/grpo.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"26720b6f9ee7eba4","mcp_get_code":{"code_sha256":"26720b6f9ee7eba4"}},{"arxiv_id":"2601.19404","paper":"/paper/arxiv-2601-19404","title":"RPO:Reinforcement Fine-Tuning with Partial Reasoning Optimization","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"yhz5613813/RPO","path":"src/open_r1/rewards.py","file_url":"https://github.com/yhz5613813/RPO/blob/HEAD/src/open_r1/rewards.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0a5c0b6fb53cd48c","mcp_get_code":{"code_sha256":"0a5c0b6fb53cd48c"}},{"arxiv_id":"2601.14044","paper":"/paper/arxiv-2601-14044","title":"Weather-R1: Logically Consistent Reinforcement Fine-Tuning for Multimodal Reasoning in Meteorology","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Marcowky/Weather-R1","path":"src/weather_r1/weather_r1_reward.py","file_url":"https://github.com/Marcowky/Weather-R1/blob/HEAD/src/weather_r1/weather_r1_reward.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MPL-2.0","inline_ok":false,"code_sha256_prefix":"12486ec2a6bdbe17","mcp_get_code":{"code_sha256":"12486ec2a6bdbe17"}},{"arxiv_id":"2601.05167","paper":"/paper/arxiv-2601-05167","title":"RelayLLM: Efficient Reasoning via Collaborative Decoding","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Chengsong-Huang/RelayLLM","path":"RL_stage/data_filter.py","file_url":"https://github.com/Chengsong-Huang/RelayLLM/blob/HEAD/RL_stage/data_filter.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e8ef1d6648c2b294","mcp_get_code":{"code_sha256":"e8ef1d6648c2b294"}},{"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":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ca32d84f17d98414","mcp_get_code":{"code_sha256":"ca32d84f17d98414"}},{"arxiv_id":"2601.00388","paper":"/paper/arxiv-2601-00388","title":"Vision-Language Reasoning for Geolocalization: A Reinforcement Learning Approach","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"aialt/geo-r","path":"src/open-r1-multimodal/src/open_r1/grpo.py","file_url":"https://github.com/aialt/geo-r/blob/HEAD/src/open-r1-multimodal/src/open_r1/grpo.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":"e89f2eec0a18d4c2","mcp_get_code":{"code_sha256":"e89f2eec0a18d4c2"}},{"arxiv_id":"2511.04902","paper":"/paper/arxiv-2511-04902","title":"You Need Reasoning to Learn Reasoning: The Limitations of Label-Free RL in Weak Base Models","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"BorealisAI/CuMa","path":"src/open_r1/rewards.py","file_url":"https://github.com/BorealisAI/CuMa/blob/HEAD/src/open_r1/rewards.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ce353d566f3f2c9f","mcp_get_code":{"code_sha256":"ce353d566f3f2c9f"}},{"arxiv_id":"2510.23569","paper":"/paper/arxiv-2510-23569","title":"EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"InternRobotics/EgoThinker","path":"EgoThinker-RFT/src/open_r1/grpo.py","file_url":"https://github.com/InternRobotics/EgoThinker/blob/HEAD/EgoThinker-RFT/src/open_r1/grpo.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"26720b6f9ee7eba4","mcp_get_code":{"code_sha256":"26720b6f9ee7eba4"}},{"arxiv_id":"2510.23569","paper":"/paper/arxiv-2510-23569","title":"EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"InternRobotics/EgoThinker","path":"EgoThinker-RFT/src/open_r1/grpo_video.py","file_url":"https://github.com/InternRobotics/EgoThinker/blob/HEAD/EgoThinker-RFT/src/open_r1/grpo_video.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"06eb76b246b185f7","mcp_get_code":{"code_sha256":"06eb76b246b185f7"}},{"arxiv_id":"2510.14605","paper":"/paper/arxiv-2510-14605","title":"Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"om-ai-lab/VLM-R1","path":"src/open-r1-multimodal/src/open_r1/grpo.py","file_url":"https://github.com/om-ai-lab/VLM-R1/blob/HEAD/src/open-r1-multimodal/src/open_r1/grpo.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":"e89f2eec0a18d4c2","mcp_get_code":{"code_sha256":"e89f2eec0a18d4c2"}},{"arxiv_id":"2507.05791","paper":"/paper/gta1-gui-test-time-scaling-agent","title":"GTA1: GUI Test-time Scaling Agent","date":"2025-07-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yan98/gta1","path":"src/grpo_grounding.py","file_url":"https://github.com/yan98/gta1/blob/HEAD/src/grpo_grounding.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b6cc386477eb6792","mcp_get_code":{"code_sha256":"b6cc386477eb6792"}},{"arxiv_id":"2507.02834","paper":null,"title":"arXiv:2507.02834","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"huggingface/open-r1","path":"src/open_r1/rewards.py","file_url":"https://github.com/huggingface/open-r1/blob/HEAD/src/open_r1/rewards.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":"ce353d566f3f2c9f","mcp_get_code":{"code_sha256":"ce353d566f3f2c9f"}},{"arxiv_id":"2507.02834","paper":null,"title":"arXiv:2507.02834","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"dhcode-cpp/X-R1","path":"src/x_r1/benchmark.py","file_url":"https://github.com/dhcode-cpp/X-R1/blob/HEAD/src/x_r1/benchmark.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":"2627a2d9d4808062","mcp_get_code":{"code_sha256":"2627a2d9d4808062"}},{"arxiv_id":"2506.20639","paper":"/paper/diffucoder-understanding-and-improving-masked","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","date":"2025-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apple/ml-diffucoder","path":"src/open_r1/rewards.py","file_url":"https://github.com/apple/ml-diffucoder/blob/HEAD/src/open_r1/rewards.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ce353d566f3f2c9f","mcp_get_code":{"code_sha256":"ce353d566f3f2c9f"}},{"arxiv_id":"2505.15810","paper":"/paper/gui-g1-understanding-r1-zero-like-training","title":"GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents","date":"2025-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuqi-zhou/gui-g1","path":"src/open-r1-multimodal/src/open_r1/grpo.py","file_url":"https://github.com/yuqi-zhou/gui-g1/blob/HEAD/src/open-r1-multimodal/src/open_r1/grpo.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":"e89f2eec0a18d4c2","mcp_get_code":{"code_sha256":"e89f2eec0a18d4c2"}},{"arxiv_id":"2505.14460","paper":"/paper/visualquality-r1-reasoning-induced-image","title":"VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank","date":"2025-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tianhewu/visualquality-r1","path":"src/open-r1-multimodal/src/open_r1/grpo.py","file_url":"https://github.com/tianhewu/visualquality-r1/blob/HEAD/src/open-r1-multimodal/src/open_r1/grpo.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":"e89f2eec0a18d4c2","mcp_get_code":{"code_sha256":"e89f2eec0a18d4c2"}},{"arxiv_id":"2505.12434","paper":"/paper/videorft-incentivizing-video-reasoning","title":"VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning","date":"2025-05-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qiwang98/videorft","path":"src/r1-v/src/open_r1/grpo.py","file_url":"https://github.com/qiwang98/videorft/blob/HEAD/src/r1-v/src/open_r1/grpo.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":"26720b6f9ee7eba4","mcp_get_code":{"code_sha256":"26720b6f9ee7eba4"}},{"arxiv_id":"2505.09655","paper":"/paper/dra-grpo-exploring-diversity-aware-reward","title":"DRA-GRPO: Exploring Diversity-Aware Reward Adjustment for R1-Zero-Like Training of Large Language Models","date":"2025-05-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiwenc1/dra-grpo","path":"src/open_r1/rewards.py","file_url":"https://github.com/xiwenc1/dra-grpo/blob/HEAD/src/open_r1/rewards.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0a5c0b6fb53cd48c","mcp_get_code":{"code_sha256":"0a5c0b6fb53cd48c"}},{"arxiv_id":"2504.15777","paper":"/paper/tina-tiny-reasoning-models-via-lora","title":"Tina: Tiny Reasoning Models via LoRA","date":"2025-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shangshang-wang/tina","path":"tina/post_train_hf/rewards.py","file_url":"https://github.com/shangshang-wang/tina/blob/HEAD/tina/post_train_hf/rewards.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":"0a5c0b6fb53cd48c","mcp_get_code":{"code_sha256":"0a5c0b6fb53cd48c"}},{"arxiv_id":"2504.01805","paper":"/paper/spatial-r1-enhancing-mllms-in-video-spatial","title":"SpaceR: Reinforcing MLLMs in Video Spatial Reasoning","date":"2025-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ouyangkun10/spacer","path":"SpaceR-SG-RLVR/src/r1-v/src/open_r1/SG-RLVR.py","file_url":"https://github.com/ouyangkun10/spacer/blob/HEAD/SpaceR-SG-RLVR/src/r1-v/src/open_r1/SG-RLVR.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"f23cbd84b69ec52c","mcp_get_code":{"code_sha256":"f23cbd84b69ec52c"}},{"arxiv_id":"2503.24376","paper":"/paper/exploring-the-effect-of-reinforcement","title":"Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1","date":"2025-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tencentarc/seed-bench-r1","path":"src/open_r1_egoplan/grpo.py","file_url":"https://github.com/tencentarc/seed-bench-r1/blob/HEAD/src/open_r1_egoplan/grpo.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":"1fd4dec0e26848af","mcp_get_code":{"code_sha256":"1fd4dec0e26848af"}},{"arxiv_id":"2503.16219","paper":"/paper/reinforcement-learning-for-reasoning-in-small","title":"Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't","date":"2025-03-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"knoveleng/open-rs","path":"src/open_r1/rewards.py","file_url":"https://github.com/knoveleng/open-rs/blob/HEAD/src/open_r1/rewards.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0a5c0b6fb53cd48c","mcp_get_code":{"code_sha256":"0a5c0b6fb53cd48c"}},{"arxiv_id":"2503.13377","paper":"/paper/timezero-temporal-video-grounding-with","title":"TimeZero: Temporal Video Grounding with Reasoning-Guided LVLM","date":"2025-03-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"www-ye/timezero","path":"src/open_r1/grpo.py","file_url":"https://github.com/www-ye/timezero/blob/HEAD/src/open_r1/grpo.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":"26720b6f9ee7eba4","mcp_get_code":{"code_sha256":"26720b6f9ee7eba4"}},{"arxiv_id":"2503.11197","paper":"/paper/reinforcement-learning-outperforms-supervised","title":"Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering","date":"2025-03-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiaomi-research/r1-aqa","path":"src/utils/rewards.py","file_url":"https://github.com/xiaomi-research/r1-aqa/blob/HEAD/src/utils/rewards.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":"54511e51a854f064","mcp_get_code":{"code_sha256":"54511e51a854f064"}},{"arxiv_id":"2409.02813","paper":"/paper/mmmu-pro-a-more-robust-multi-discipline","title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","date":"2024-09-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opendatalab/pm4bench","path":"src/pm4bench/qgo/reward.py","file_url":"https://github.com/opendatalab/pm4bench/blob/HEAD/src/pm4bench/qgo/reward.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":"c17d2901ecfbf4cb","mcp_get_code":{"code_sha256":"c17d2901ecfbf4cb"}},{"arxiv_id":"2405.20313","paper":"/paper/sequence-augmented-se-3-flow-matching-for","title":"Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Backbone Generation","date":"2024-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ding523/Curr_REFT","path":"train_code/grpo/open-r1-multimodal/src/open_r1/Stage1_judge_math_resize.py","file_url":"https://github.com/ding523/Curr_REFT/blob/HEAD/train_code/grpo/open-r1-multimodal/src/open_r1/Stage1_judge_math_resize.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"baace3dc73e1da05","mcp_get_code":{"code_sha256":"baace3dc73e1da05"}},{"arxiv_id":"2025.emnlp-main.67","paper":null,"title":"arXiv:2025.emnlp-main.67","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"isyuhaochen/RRC-DSCD","path":"code/rl/rewards.py","file_url":"https://github.com/isyuhaochen/RRC-DSCD/blob/HEAD/code/rl/rewards.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"70ba7655c5039f8f","mcp_get_code":{"code_sha256":"70ba7655c5039f8f"}}]}