{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CHS6VQH4UVNWF746MQKITXQQC2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a0d9d3e90b3fd7695e1ed94d53f540403a43942bc2635c99228a2160b908a606","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-12T03:20:24Z","title_canon_sha256":"a553f839b835ffb46dcb0fb8d8eb8c3995e64ab782e4b0ea08b0881da51eb5f3"},"schema_version":"1.0","source":{"id":"2605.11461","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.11461","created_at":"2026-05-20T00:04:35Z"},{"alias_kind":"arxiv_version","alias_value":"2605.11461v2","created_at":"2026-05-20T00:04:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.11461","created_at":"2026-05-20T00:04:35Z"},{"alias_kind":"pith_short_12","alias_value":"CHS6VQH4UVNW","created_at":"2026-05-20T00:04:35Z"},{"alias_kind":"pith_short_16","alias_value":"CHS6VQH4UVNWF746","created_at":"2026-05-20T00:04:35Z"},{"alias_kind":"pith_short_8","alias_value":"CHS6VQH4","created_at":"2026-05-20T00:04:35Z"}],"graph_snapshots":[{"event_id":"sha256:7ce78f37fe40d8e88e4d3ea0525a166a47dd6b1417fbabf20670f9e1eb75afed","target":"graph","created_at":"2026-05-20T00:04:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Experiments across multiple reasoning benchmarks demonstrate that GCPO significantly improves both reasoning accuracy and solution diversity over existing approaches."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"GCPO replaces individual rollout competition with team-level credit assignment based on contributions to collective solution coverage."}],"snapshot_sha256":"811f064361e94f8e95068ab133f6c15bb946d0a481d6252b59f8c4d2b29ac605"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"4d92269dc825e89728ba0dff14924c146e4ad67d8bb07e132ca431858ce1a53a"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.11461/integrity.json","findings":[],"snapshot_sha256":"f3a30e2b5c553c5c8855fc2177d622744c629cc9279bc9fc569c646f70227da7","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Haoxuan Chen, Jian-Fang Hu, Tianming Liang, Wei-Shi Zheng","cross_cats":["cs.LG"],"headline":"GCPO replaces individual rollout competition with team-level credit assignment based on contributions to collective solution coverage.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-12T03:20:24Z","title":"Breaking $\\textit{Winner-Takes-All}$: Cooperative Policy Optimization Improves Diverse LLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.11461","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-13T01:53:17.683923Z","id":"167135f8-3676-4243-a715-400957f35937","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"GCPO replaces individual rollout competition with team-level credit assignment based on contributions to collective solution coverage.","strongest_claim":"Experiments across multiple reasoning benchmarks demonstrate that GCPO significantly improves both reasoning accuracy and solution diversity over existing approaches.","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."}},"verdict_id":"167135f8-3676-4243-a715-400957f35937"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:198b3c930fa91dc45cb90f17671921b57452652367d8e6fc0b857eb2ece072da","target":"record","created_at":"2026-05-20T00:04:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a0d9d3e90b3fd7695e1ed94d53f540403a43942bc2635c99228a2160b908a606","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-12T03:20:24Z","title_canon_sha256":"a553f839b835ffb46dcb0fb8d8eb8c3995e64ab782e4b0ea08b0881da51eb5f3"},"schema_version":"1.0","source":{"id":"2605.11461","kind":"arxiv","version":2}},"canonical_sha256":"11e5eac0fca55b62ff9e641489de10169af9b1dc277c8d906bbd50b85a04bcae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11e5eac0fca55b62ff9e641489de10169af9b1dc277c8d906bbd50b85a04bcae","first_computed_at":"2026-05-20T00:04:35.997203Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:35.997203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qveeiKVWv1kkCDsp8FYD3nYaRFBC1oNB7VbSqSqn2fhTM5aSj/j+hFWf74DoJwkOSVOayZavchshEPJ5A3YlDg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:35.998389Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.11461","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:198b3c930fa91dc45cb90f17671921b57452652367d8e6fc0b857eb2ece072da","sha256:7ce78f37fe40d8e88e4d3ea0525a166a47dd6b1417fbabf20670f9e1eb75afed"],"state_sha256":"3a323e5a77de5a8f2468cbdb98a44c1ade836096861c24bb41ef9227a28d6093"}