{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/compute-gigpo-outcome-advantage","entry":"compute_gigpo_outcome_advantage","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":5,"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":4,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":4},"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":"2607.25308","paper":"/paper/arxiv-2607-25308","title":"CAST: Game Solvers as Turn-Level Teachers for LLM Agents CAST: GAME SOLVERS AS TURN-LEVEL TEACHERS FOR LLM AGENTS","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"Wloner0809/CAST","path":"rllm/gigpo/core_gigpo.py","file_url":"https://github.com/Wloner0809/CAST/blob/HEAD/rllm/gigpo/core_gigpo.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":"9a939d57d1c4290d","mcp_get_code":{"code_sha256":"9a939d57d1c4290d"}},{"arxiv_id":"2607.01440","paper":"/paper/arxiv-2607-01440","title":"FaithMed: Training LLMs For Faithful Evidence-Based Medical Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"cxcscmu/FaithMed","path":"verl-agent/gigpo/faithmed_gigpo_pr.py","file_url":"https://github.com/cxcscmu/FaithMed/blob/HEAD/verl-agent/gigpo/faithmed_gigpo_pr.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3771d2235bb7f07c","mcp_get_code":{"code_sha256":"3771d2235bb7f07c"}},{"arxiv_id":"2604.02268","paper":"/paper/arxiv-2604-02268","title":"SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"ZJU-REAL/SkillZero","path":"gigpo/core_gigpo.py","file_url":"https://github.com/ZJU-REAL/SkillZero/blob/HEAD/gigpo/core_gigpo.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":"76f7db977dc304c0","mcp_get_code":{"code_sha256":"76f7db977dc304c0"}},{"arxiv_id":"2601.20209","paper":"/paper/arxiv-2601-20209","title":"SPARK: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"jinyangwu/SPARK","path":"gigpo/core_gigpo.py","file_url":"https://github.com/jinyangwu/SPARK/blob/HEAD/gigpo/core_gigpo.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":"c8e5b3681d41b8a9","mcp_get_code":{"code_sha256":"c8e5b3681d41b8a9"}},{"arxiv_id":"2509.13347","paper":"/paper/arxiv-2509-13347","title":"OpenHA: A Series of Open-Source Hierarchical Agentic Models in Minecraft","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"CraftJarvis/OpenHA","path":"CrossAgent/MTRL/gigpo/core_gigpo.py","file_url":"https://github.com/CraftJarvis/OpenHA/blob/HEAD/CrossAgent/MTRL/gigpo/core_gigpo.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c8e5b3681d41b8a9","mcp_get_code":{"code_sha256":"c8e5b3681d41b8a9"}}]}