{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CHS6VQH4UVNWF746MQKITXQQC2","short_pith_number":"pith:CHS6VQH4","schema_version":"1.0","canonical_sha256":"11e5eac0fca55b62ff9e641489de10169af9b1dc277c8d906bbd50b85a04bcae","source":{"kind":"arxiv","id":"2605.11461","version":2},"attestation_state":"computed","paper":{"title":"Breaking $\\textit{Winner-Takes-All}$: Cooperative Policy Optimization Improves Diverse LLM Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"GCPO replaces individual rollout competition with team-level credit assignment based on contributions to collective solution coverage.","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Haoxuan Chen, Jian-Fang Hu, Tianming Liang, Wei-Shi Zheng","submitted_at":"2026-05-12T03:20:24Z","abstract_excerpt":"Reinforcement learning with verifiers (RLVR) has become a central paradigm for improving LLM reasoning, yet popular group-based optimization algorithms like GRPO often suffer from exploration collapse, where the models prematurely converge on a narrow set of high-scoring patterns, lacking the ability to explore new solutions. Recent efforts attempt to alleviate this by adding entropy regularization or diversity bonus. However, these approaches do not change the \\textit{winner-takes-all} nature, where rollouts still compete for individual advantage rather than cooperating for maximizing global "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.11461","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-12T03:20:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a553f839b835ffb46dcb0fb8d8eb8c3995e64ab782e4b0ea08b0881da51eb5f3","abstract_canon_sha256":"a0d9d3e90b3fd7695e1ed94d53f540403a43942bc2635c99228a2160b908a606"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:35.998389Z","signature_b64":"qveeiKVWv1kkCDsp8FYD3nYaRFBC1oNB7VbSqSqn2fhTM5aSj/j+hFWf74DoJwkOSVOayZavchshEPJ5A3YlDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11e5eac0fca55b62ff9e641489de10169af9b1dc277c8d906bbd50b85a04bcae","last_reissued_at":"2026-05-20T00:04:35.997203Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:35.997203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Breaking $\\textit{Winner-Takes-All}$: Cooperative Policy Optimization Improves Diverse LLM Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"GCPO replaces individual rollout competition with team-level credit assignment based on contributions to collective solution coverage.","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Haoxuan Chen, Jian-Fang Hu, Tianming Liang, Wei-Shi Zheng","submitted_at":"2026-05-12T03:20:24Z","abstract_excerpt":"Reinforcement learning with verifiers (RLVR) has become a central paradigm for improving LLM reasoning, yet popular group-based optimization algorithms like GRPO often suffer from exploration collapse, where the models prematurely converge on a narrow set of high-scoring patterns, lacking the ability to explore new solutions. Recent efforts attempt to alleviate this by adding entropy regularization or diversity bonus. However, these approaches do not change the \\textit{winner-takes-all} nature, where rollouts still compete for individual advantage rather than cooperating for maximizing global "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments across multiple reasoning benchmarks demonstrate that GCPO significantly improves both reasoning accuracy and solution diversity over existing approaches.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the determinant volume over reward-weighted semantic embeddings provides a reliable, unbiased measure of non-redundant solution coverage whose marginal contributions can be computed and redistributed without introducing new optimization pathologies or sensitivity to embedding choice.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"GCPO shifts RLVR from rollout competition to team cooperation by assigning advantages via marginal contributions to a determinant-based coverage volume over semantic embeddings, yielding higher accuracy and solution diversity on reasoning benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"GCPO replaces individual rollout competition with team-level credit assignment based on contributions to collective solution coverage.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"811f064361e94f8e95068ab133f6c15bb946d0a481d6252b59f8c4d2b29ac605"},"source":{"id":"2605.11461","kind":"arxiv","version":2},"verdict":{"id":"167135f8-3676-4243-a715-400957f35937","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T01:53:17.683923Z","strongest_claim":"Experiments across multiple reasoning benchmarks demonstrate that GCPO significantly improves both reasoning accuracy and solution diversity over existing approaches.","one_line_summary":"GCPO shifts RLVR from rollout competition to team cooperation by assigning advantages via marginal contributions to a determinant-based coverage volume over semantic embeddings, yielding higher accuracy and solution diversity on reasoning benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the determinant volume over reward-weighted semantic embeddings provides a reliable, unbiased measure of non-redundant solution coverage whose marginal contributions can be computed and redistributed without introducing new optimization pathologies or sensitivity to embedding choice.","pith_extraction_headline":"GCPO replaces individual rollout competition with team-level credit assignment based on contributions to collective solution coverage."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.11461/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T12:35:47.127139Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T10:01:16.385739Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T08:27:15.467797Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"f3a30e2b5c553c5c8855fc2177d622744c629cc9279bc9fc569c646f70227da7"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"4d92269dc825e89728ba0dff14924c146e4ad67d8bb07e132ca431858ce1a53a"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.11461","created_at":"2026-05-20T00:04:35.997381+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.11461v2","created_at":"2026-05-20T00:04:35.997381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.11461","created_at":"2026-05-20T00:04:35.997381+00:00"},{"alias_kind":"pith_short_12","alias_value":"CHS6VQH4UVNW","created_at":"2026-05-20T00:04:35.997381+00:00"},{"alias_kind":"pith_short_16","alias_value":"CHS6VQH4UVNWF746","created_at":"2026-05-20T00:04:35.997381+00:00"},{"alias_kind":"pith_short_8","alias_value":"CHS6VQH4","created_at":"2026-05-20T00:04:35.997381+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CHS6VQH4UVNWF746MQKITXQQC2","json":"https://pith.science/pith/CHS6VQH4UVNWF746MQKITXQQC2.json","graph_json":"https://pith.science/api/pith-number/CHS6VQH4UVNWF746MQKITXQQC2/graph.json","events_json":"https://pith.science/api/pith-number/CHS6VQH4UVNWF746MQKITXQQC2/events.json","paper":"https://pith.science/paper/CHS6VQH4"},"agent_actions":{"view_html":"https://pith.science/pith/CHS6VQH4UVNWF746MQKITXQQC2","download_json":"https://pith.science/pith/CHS6VQH4UVNWF746MQKITXQQC2.json","view_paper":"https://pith.science/paper/CHS6VQH4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.11461&json=true","fetch_graph":"https://pith.science/api/pith-number/CHS6VQH4UVNWF746MQKITXQQC2/graph.json","fetch_events":"https://pith.science/api/pith-number/CHS6VQH4UVNWF746MQKITXQQC2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CHS6VQH4UVNWF746MQKITXQQC2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CHS6VQH4UVNWF746MQKITXQQC2/action/storage_attestation","attest_author":"https://pith.science/pith/CHS6VQH4UVNWF746MQKITXQQC2/action/author_attestation","sign_citation":"https://pith.science/pith/CHS6VQH4UVNWF746MQKITXQQC2/action/citation_signature","submit_replication":"https://pith.science/pith/CHS6VQH4UVNWF746MQKITXQQC2/action/replication_record"}},"created_at":"2026-05-20T00:04:35.997381+00:00","updated_at":"2026-05-20T00:04:35.997381+00:00"}