{"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/reset-ring-attn-position-ids","entry":"reset_ring_attn_position_ids","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":16,"n_papers_ran":0,"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":1,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":16,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"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":"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/ring_attn_utils.py","file_url":"https://github.com/OpenRLHF/OpenRLHF/blob/HEAD/openrlhf/models/ring_attn_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":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"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/ring_attn_utils.py","file_url":"https://github.com/lfy-123/WIST/blob/HEAD/openrlhf/models/ring_attn_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":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"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/ring_attn_utils.py","file_url":"https://github.com/Rover912/PASMR/blob/HEAD/openrlhf/models/ring_attn_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":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"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/ring_attn_utils.py","file_url":"https://github.com/FrontierX-Lab/SGVR/blob/HEAD/MM-EUREKA/openrlhf/models/ring_attn_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":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"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/ring_attn_utils.py","file_url":"https://github.com/yunfeixie233/vigal/blob/HEAD/openrlhf/models/ring_attn_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":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"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/ring_attn_utils.py","file_url":"https://github.com/XingYuSSS/RLPA/blob/HEAD/openrlhf/models/ring_attn_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":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"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/ring_attn_utils.py","file_url":"https://github.com/tiger-ai-lab/vl-rethinker/blob/HEAD/openrlhf/models/ring_attn_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":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"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/ring_attn_utils.py","file_url":"https://github.com/rosieyzh/openrlhf-pretrain/blob/HEAD/openrlhf/models/ring_attn_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":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"arxiv_id":"2503.24290","paper":"/paper/open-reasoner-zero-an-open-source-approach-to","title":"Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model","date":"2025-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"open-reasoner-zero/open-reasoner-zero","path":"orz/ppo/models.py","file_url":"https://github.com/open-reasoner-zero/open-reasoner-zero/blob/HEAD/orz/ppo/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"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/ring_attn_utils.py","file_url":"https://github.com/szk123456789/Nash_RS/blob/HEAD/openrlhf/models/ring_attn_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"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/ring_attn_utils.py","file_url":"https://github.com/OpenLLMAI/OpenLLaMA2/blob/HEAD/openrlhf/models/ring_attn_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":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"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/ring_attn_utils.py","file_url":"https://github.com/eddycmu/demystify-long-cot/blob/HEAD/openrlhf/openrlhf/models/ring_attn_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"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/ring_attn_utils.py","file_url":"https://github.com/lifan-yuan/implicitprm/blob/HEAD/train/openrlhf/models/ring_attn_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":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"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/ring_attn_utils.py","file_url":"https://github.com/zkshan2002/RTO/blob/HEAD/openrlhf/models/ring_attn_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":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"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/ring_attn_utils.py","file_url":"https://github.com/miaoyuchun/InfoRM/blob/HEAD/openrlhf/models/ring_attn_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"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":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}}]}