{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/code/reset-ring-attn-position-ids","entry":"reset_ring_attn_position_ids","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-10-05T00:36:11+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 = n_papers_ran_no_instrument_failure (papers with a run with no instrument failure) + n_papers_ran_instrument_only (papers where every run was a failure of Syntology's instrument); n_samples_ran = n_samples_ran_checked (honoured, violated, no contract) + n_samples_instrument (failures of Syntology's instrument, not of the code).","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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":16,"n_papers_ran":0,"n_papers_ran_no_instrument_failure":0,"n_papers_ran_instrument_only":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_constructed":0,"n_samples_ran_checked":0,"n_samples_instrument":0,"n_samples_unverified":1,"n_samples_fingerprinted":0,"n_places":16,"n_places_pointer_only":1,"n_places_pointer_only_link_open":0,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_places_pointer_only_link_open counts the places where this paper's link allows the text and the stored copy does not","by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":1},"key_notes":{"n_samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"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","arxiv_id_is_arxiv":true,"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,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"e93117d99aa6b210","code_sha256_prefix":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"arxiv_id":"2603.22352","arxiv_id_is_arxiv":true,"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,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"e93117d99aa6b210","code_sha256_prefix":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"arxiv_id":"2601.17671","arxiv_id_is_arxiv":true,"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,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"e93117d99aa6b210","code_sha256_prefix":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"arxiv_id":"2601.05073","arxiv_id_is_arxiv":true,"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,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"e93117d99aa6b210","code_sha256_prefix":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"arxiv_id":"2506.08011","arxiv_id_is_arxiv":true,"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,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"e93117d99aa6b210","code_sha256_prefix":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"arxiv_id":"2505.15456","arxiv_id_is_arxiv":true,"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,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"e93117d99aa6b210","code_sha256_prefix":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"arxiv_id":"2504.08837","arxiv_id_is_arxiv":true,"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,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"e93117d99aa6b210","code_sha256_prefix":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"arxiv_id":"2504.07912","arxiv_id_is_arxiv":true,"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,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"e93117d99aa6b210","code_sha256_prefix":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"arxiv_id":"2503.24290","arxiv_id_is_arxiv":true,"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,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"e93117d99aa6b210","code_sha256_prefix":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"arxiv_id":"2503.10990","arxiv_id_is_arxiv":true,"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,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"e93117d99aa6b210","code_sha256_prefix":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"arxiv_id":"2502.14768","arxiv_id_is_arxiv":true,"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,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"e93117d99aa6b210","code_sha256_prefix":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"arxiv_id":"2502.03373","arxiv_id_is_arxiv":true,"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,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"e93117d99aa6b210","code_sha256_prefix":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"arxiv_id":"2412.01981","arxiv_id_is_arxiv":true,"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,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"e93117d99aa6b210","code_sha256_prefix":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"arxiv_id":"2404.18922","arxiv_id_is_arxiv":true,"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,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"e93117d99aa6b210","code_sha256_prefix":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"arxiv_id":"2402.09345","arxiv_id_is_arxiv":true,"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,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, miaoyuchun/InfoRM when it was checked","code_sha256":"e93117d99aa6b210","code_sha256_prefix":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}},{"arxiv_id":"2306.00398","arxiv_id_is_arxiv":true,"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,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"e93117d99aa6b210","code_sha256_prefix":"e93117d99aa6b210","mcp_get_code":{"code_sha256":"e93117d99aa6b210"}}],"record_sha256":"47d3eb6880b089286293cfa8ad453c3fcbd223d6c6b65b830673a092d72498e9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}