{"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/compute-detach-dpo-loss-rm","entry":"compute_detach_dpo_loss_rm","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":49,"n_papers_ran":48,"n_papers_ran_no_instrument_failure":4,"n_papers_ran_instrument_only":44,"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":4,"n_samples_ran":3,"n_samples_constructed":0,"n_samples_ran_checked":2,"n_samples_instrument":1,"n_samples_unverified":1,"n_samples_fingerprinted":0,"n_places":49,"n_places_pointer_only":44,"n_places_pointer_only_link_open":27,"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":1,"ran_fixture":0,"ran":2,"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":"2608.24696","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2608-24696","title":"On-policy Distillation with Verifiable Reward","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"LeapLabTHU/OPDVR","path":"verl/recipe/prime/prime_core_algos.py","file_url":"https://github.com/LeapLabTHU/OPDVR/blob/HEAD/verl/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","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, LeapLabTHU/OPDVR when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2608.09836","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2608-09836","title":"Mismatch Matters: On-Policy Distillation Beyond Token Agreement","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"yzc-666/TIDE","path":"verl/recipe/prime/prime_core_algos.py","file_url":"https://github.com/yzc-666/TIDE/blob/HEAD/verl/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","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, yzc-666/TIDE when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2608.01743","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2608-01743","title":"Toward Plasticity-Preserving KL Regularization for Capability Retention in LLM Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"Lumina04/CoKL","path":"recipe/prime/prime_core_algos.py","file_url":"https://github.com/Lumina04/CoKL/blob/HEAD/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2607.10481","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2607-10481","title":"ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"Hesse73/ARMOR","path":"verl/recipe/prime/prime_core_algos.py","file_url":"https://github.com/Hesse73/ARMOR/blob/HEAD/verl/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","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, Hesse73/ARMOR when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2606.26790","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2606-26790","title":"OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"jinyangwu/OPID","path":"recipe/prime/prime_core_algos.py","file_url":"https://github.com/jinyangwu/OPID/blob/HEAD/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2606.25757","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2606-25757","title":"OPERA: Aligning Open-Ended Reasoning via Objective Perplexity-based Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"pangpang-xuan/OPERA","path":"verl/recipe/prime/prime_core_algos.py","file_url":"https://github.com/pangpang-xuan/OPERA/blob/HEAD/verl/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","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, pangpang-xuan/OPERA when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2606.24994","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2606-24994","title":"ExTra: Exploratory Trajectory Optimization for Language Model Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"allen4747/extra","path":"verl/recipe/prime/prime_core_algos.py","file_url":"https://github.com/allen4747/extra/blob/HEAD/verl/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2606.19236","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2606-19236","title":"STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"hp-luo/STARE","path":"recipe/prime/prime_core_algos.py","file_url":"https://github.com/hp-luo/STARE/blob/HEAD/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2606.06021","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2606-06021","title":"OPRD: On-Policy Representation Distillation","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"ShenzhiYang2000/OPRD","path":"verl/recipe/prime/prime_core_algos.py","file_url":"https://github.com/ShenzhiYang2000/OPRD/blob/HEAD/verl/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","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, ShenzhiYang2000/OPRD when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2606.02684","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2606-02684","title":"Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"YuYingLi0/FiRe-OPD","path":"verl/recipe/prime/prime_core_algos.py","file_url":"https://github.com/YuYingLi0/FiRe-OPD/blob/HEAD/verl/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","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, YuYingLi0/FiRe-OPD when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2605.25864","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2605-25864","title":"When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewards","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Lumina04/CARE","path":"recipe/prime/prime_core_algos.py","file_url":"https://github.com/Lumina04/CARE/blob/HEAD/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2605.11739","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2605-11739","title":"Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"caiyuchen-ustc/EffOPD","path":"EffOPD/verl/recipe/prime/prime_core_algos.py","file_url":"https://github.com/caiyuchen-ustc/EffOPD/blob/HEAD/EffOPD/verl/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","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, caiyuchen-ustc/EffOPD when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2605.01111","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2605-01111","title":"When Less is Enough: Efficient Inference via Collaborative Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"fairytale9/llm_bottleneck","path":"recipe/prime/prime_core_algos.py","file_url":"https://github.com/fairytale9/llm_bottleneck/blob/HEAD/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2604.17928","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2604-17928","title":"HEALing Entropy Collapse: Enhancing Exploration in Few-Shot RLVR via Hybrid-Domain Entropy Dynamics Alignment","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"XMUDeepLIT/HEAL","path":"recipe/prime/prime_core_algos.py","file_url":"https://github.com/XMUDeepLIT/HEAL/blob/HEAD/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2604.17555","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2604-17555","title":"CoSearch: Joint Training of Reasoning and Document Ranking via Reinforcement Learning for Agentic Search","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"snap-research/CoSearch","path":"verl/recipe/prime/prime_core_algos.py","file_url":"https://github.com/snap-research/CoSearch/blob/HEAD/verl/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","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, snap-research/CoSearch when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2604.17252","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2604-17252","title":"Seeing Isn't Believing: Mitigating Belief Inertia via Active Intervention in Embodied Agents","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"WangHanLinHenry/EVU","path":"verl-agent/recipe/prime/prime_core_algos.py","file_url":"https://github.com/WangHanLinHenry/EVU/blob/HEAD/verl-agent/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","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, WangHanLinHenry/EVU when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2604.09793","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2604-09793","title":"GIANTS: Generative Insight Anticipation from Scientific Literature","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"joyheyueya/giants","path":"recipe/prime/prime_core_algos.py","file_url":"https://github.com/joyheyueya/giants/blob/HEAD/recipe/prime/prime_core_algos.py","status":"ran","verification_level":1,"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":"e696489c417f49c0","code_sha256_prefix":"e696489c417f49c0","mcp_get_code":{"code_sha256":"e696489c417f49c0"}},{"arxiv_id":"2604.03993","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2604-03993","title":"Can LLMs Learn to Reason Robustly under Noisy Supervision?","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"ShenzhiYang2000/OLR","path":"recipe/prime/prime_core_algos.py","file_url":"https://github.com/ShenzhiYang2000/OLR/blob/HEAD/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2603.20046","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2603-20046","title":"Experience is the Best Teacher: Motivating Effective Exploration in Reinforcement Learning for LLMs","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"sikelifei/HeRL","path":"recipe/prime/prime_core_algos.py","file_url":"https://github.com/sikelifei/HeRL/blob/HEAD/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","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, sikelifei/HeRL when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2603.19880","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2603-19880","title":"What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"Jasper-Yan/SCRL","path":"verl/recipe/prime/prime_core_algos.py","file_url":"https://github.com/Jasper-Yan/SCRL/blob/HEAD/verl/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2603.17145","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2603-17145","title":"REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judge","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"YasminZhang/REAL","path":"recipe/prime/prime_core_algos.py","file_url":"https://github.com/YasminZhang/REAL/blob/HEAD/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2603.14389","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2603-14389","title":"From log π to π: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"FlyTune/DGPO-RL","path":"recipe/prime/prime_core_algos.py","file_url":"https://github.com/FlyTune/DGPO-RL/blob/HEAD/recipe/prime/prime_core_algos.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":"2b46e6f09a2ce9ae","code_sha256_prefix":"2b46e6f09a2ce9ae","mcp_get_code":{"code_sha256":"2b46e6f09a2ce9ae"}},{"arxiv_id":"2603.12109","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2603-12109","title":"On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agents","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"unimpor/T3","path":"verl/recipe/prime/prime_core_algos.py","file_url":"https://github.com/unimpor/T3/blob/HEAD/verl/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","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, unimpor/T3 when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2603.07079","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2603-07079","title":"Entropy-Aware On-Policy Distillation of Language Models","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"WLS04/EOPD","path":"recipe/prime/prime_core_algos.py","file_url":"https://github.com/WLS04/EOPD/blob/HEAD/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2603.04597","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2603-04597","title":"Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"LuckyyySTA/GOLF","path":"golf/verl/recipe/prime/prime_core_algos.py","file_url":"https://github.com/LuckyyySTA/GOLF/blob/HEAD/golf/verl/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2603.02938","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2603-02938","title":"Beyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"mysteriouslfz/GraphSSR","path":"reinforcement_learning/recipe/prime/prime_core_algos.py","file_url":"https://github.com/mysteriouslfz/GraphSSR/blob/HEAD/reinforcement_learning/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2602.17550","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2602-17550","title":"MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"FlyTune/MASPO-RL","path":"recipe/prime/prime_core_algos.py","file_url":"https://github.com/FlyTune/MASPO-RL/blob/HEAD/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2602.11909","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2602-11909","title":"Echo: Towards Advanced Audio Comprehension via Audio-Interleaved Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"wdqqdw/Echo","path":"verl/recipe/prime/prime_core_algos.py","file_url":"https://github.com/wdqqdw/Echo/blob/HEAD/verl/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","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, wdqqdw/Echo when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2602.01365","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2602-01365","title":"When Domains Interact: Asymmetric and Order-Sensitive Cross-Domain Effects in Reinforcement Learning for Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"uservan/cross_domain","path":"verl/recipe/prime/prime_core_algos.py","file_url":"https://github.com/uservan/cross_domain/blob/HEAD/verl/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","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, uservan/cross_domain when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2601.21468","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-21468","title":"MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"meituan/MemOCR","path":"recipe/prime/prime_core_algos.py","file_url":"https://github.com/meituan/MemOCR/blob/HEAD/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2601.17687","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-17687","title":"Agentic reinforcement learning empowers next-generation chemical language models for molecular design and synthesis","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"HowardLi1984/ChemCraft","path":"chemcraft_rl/recipe/prime/prime_core_algos.py","file_url":"https://github.com/HowardLi1984/ChemCraft/blob/HEAD/chemcraft_rl/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","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, HowardLi1984/ChemCraft when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2601.09233","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-09233","title":"GIFT: Reconciling Post-Training Objectives via Finite-Temperature Gibbs Initialization","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"zzy1127/GIFT","path":"verl/recipe/prime/prime_core_algos.py","file_url":"https://github.com/zzy1127/GIFT/blob/HEAD/verl/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","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, zzy1127/GIFT when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2601.04786","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-04786","title":"AgentOCR: Reimagining Agent History via Optical Self-Compression","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"langfengQ/AgentOCR","path":"recipe/prime/prime_core_algos.py","file_url":"https://github.com/langfengQ/AgentOCR/blob/HEAD/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2601.04767","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-04767","title":"AT 2 PO: Agentic Turn-based Policy Optimization via Tree Search","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"zzfoutofspace/ATPO","path":"ATPO/verl_atpo/recipe/prime/prime_core_algos.py","file_url":"https://github.com/zzfoutofspace/ATPO/blob/HEAD/ATPO/verl_atpo/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","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, zzfoutofspace/ATPO when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2512.14157","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2512-14157","title":"Ophiuchus: Incentivizing Tool-augmented \"Think with Images\" for Joint Medical Segmentation, Understanding and Reasoning","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"SII-zyj/Ophiuchus","path":"recipe/prime/prime_core_algos.py","file_url":"https://github.com/SII-zyj/Ophiuchus/blob/HEAD/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2512.11391","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2512-11391","title":"Mitigating the Safety Alignment Tax with Null-Space Constrained Policy Optimization","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"ivanniu/NSPO","path":"verl/recipe/prime/prime_core_algos.py","file_url":"https://github.com/ivanniu/NSPO/blob/HEAD/verl/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","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, ivanniu/NSPO when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2510.04678","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2510-04678","title":"Multi-Agent Tool-Integrated Policy Optimization","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"mzf666/MATPO","path":"recipe/prime/prime_core_algos.py","file_url":"https://github.com/mzf666/MATPO/blob/HEAD/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2509.25787","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2509-25787","title":"Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Ranking","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"bytedance/EvoQuality","path":"verl/recipe/prime/prime_core_algos.py","file_url":"https://github.com/bytedance/EvoQuality/blob/HEAD/verl/recipe/prime/prime_core_algos.py","status":"ran","verification_level":1,"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":"e696489c417f49c0","code_sha256_prefix":"e696489c417f49c0","mcp_get_code":{"code_sha256":"e696489c417f49c0"}},{"arxiv_id":"2506.12935","arxiv_id_is_arxiv":true,"paper":"/paper/soundmind-rl-incentivized-logic-reasoning-for","title":"SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models","date":"2025-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xid32/SoundMind","path":"recipe/prime/prime_core_algos.py","file_url":"https://github.com/xid32/SoundMind/blob/HEAD/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2506.08672","arxiv_id_is_arxiv":true,"paper":"/paper/rulereasoner-reinforced-rule-based-reasoning","title":"RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling","date":"2025-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bigai-nlco/rulereasoner","path":"verl/recipe/prime/prime_core_algos.py","file_url":"https://github.com/bigai-nlco/rulereasoner/blob/HEAD/verl/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2505.20046","arxiv_id_is_arxiv":true,"paper":"/paper/rearank-reasoning-re-ranking-agent-via","title":"REARANK: Reasoning Re-ranking Agent via Reinforcement Learning","date":"2025-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lezhang7/rearank","path":"verl/recipe/prime/prime_core_algos.py","file_url":"https://github.com/lezhang7/rearank/blob/HEAD/verl/recipe/prime/prime_core_algos.py","status":"ran","verification_level":1,"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":"e696489c417f49c0","code_sha256_prefix":"e696489c417f49c0","mcp_get_code":{"code_sha256":"e696489c417f49c0"}},{"arxiv_id":"2505.18822","arxiv_id_is_arxiv":true,"paper":"/paper/adactrl-towards-adaptive-and-controllable","title":"AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting","date":"2025-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"joeying1019/adactrl","path":"recipe/prime/prime_core_algos.py","file_url":"https://github.com/joeying1019/adactrl/blob/HEAD/recipe/prime/prime_core_algos.py","status":"ran","verification_level":1,"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":"b0af30a76b102578","code_sha256_prefix":"b0af30a76b102578","mcp_get_code":{"code_sha256":"b0af30a76b102578"}},{"arxiv_id":"2505.14362","arxiv_id_is_arxiv":true,"paper":"/paper/deepeyes-incentivizing-thinking-with-images","title":"DeepEyes: Incentivizing \"Thinking with Images\" via Reinforcement Learning","date":"2025-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"visual-agent/deepeyes","path":"recipe/prime/prime_core_algos.py","file_url":"https://github.com/visual-agent/deepeyes/blob/HEAD/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2504.16084","arxiv_id_is_arxiv":true,"paper":"/paper/ttrl-test-time-reinforcement-learning","title":"TTRL: Test-Time Reinforcement Learning","date":"2025-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"prime-rl/ttrl","path":"verl/recipe/prime/prime_core_algos.py","file_url":"https://github.com/prime-rl/ttrl/blob/HEAD/verl/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2410.02992","arxiv_id_is_arxiv":true,"paper":"/paper/guided-stream-of-search-learning-to-better","title":"Guided Stream of Search: Learning to Better Search with Language Models via Optimal Path Guidance","date":"2024-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"snu-mllab/guided-rest","path":"recipe/prime/prime_core_algos.py","file_url":"https://github.com/snu-mllab/guided-rest/blob/HEAD/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"2409.19256","arxiv_id_is_arxiv":true,"paper":"/paper/hybridflow-a-flexible-and-efficient-rlhf","title":"HybridFlow: A Flexible and Efficient RLHF Framework","date":"2024-09-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"du-nlp-lab/lengthreward","path":"recipe/prime/prime_core_algos.py","file_url":"https://github.com/du-nlp-lab/lengthreward/blob/HEAD/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"openreview_v70fTOqer2","arxiv_id_is_arxiv":false,"paper":null,"title":"OpenReview id openreview_v70fTOqer2","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"liziniu/KnapsackRL","path":"recipe/prime/prime_core_algos.py","file_url":"https://github.com/liziniu/KnapsackRL/blob/HEAD/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"openreview_lbaBsu0CaY","arxiv_id_is_arxiv":false,"paper":null,"title":"OpenReview id openreview_lbaBsu0CaY","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Tunanzzz/Meerkat-VL","path":"recipe/prime/prime_core_algos.py","file_url":"https://github.com/Tunanzzz/Meerkat-VL/blob/HEAD/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"arxiv_id":"openreview_Tkdgg5uqNK","arxiv_id_is_arxiv":false,"paper":null,"title":"OpenReview id openreview_Tkdgg5uqNK","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"ZhijianZhou/Disppo","path":"recipe/prime/prime_core_algos.py","file_url":"https://github.com/ZhijianZhou/Disppo/blob/HEAD/recipe/prime/prime_core_algos.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from LeapLabTHU/OPDVR, and GitHub detected no licence in that repository when it was checked","code_sha256":"4d91e4383716e42c","code_sha256_prefix":"4d91e4383716e42c","mcp_get_code":{"code_sha256":"4d91e4383716e42c"}}],"record_sha256":"264a9c21919365d3dd20b80e5a46727618ff12e0feab7e84bc793c27dcb77ab2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}