{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MOQSQJZOFZKOMRJBF6BYTH6IMX","short_pith_number":"pith:MOQSQJZO","schema_version":"1.0","canonical_sha256":"63a128272e2e54e645212f83899fc865fa51f0f57ea1549829f16a7a72890344","source":{"kind":"arxiv","id":"2605.28273","version":1},"attestation_state":"computed","paper":{"title":"Global Policy-Space Response Oracles for Two-Player Zero-Sum Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chao Wang, Feihong Yang, Jian Wang, Junyu Zhang, Xudong Zhang","submitted_at":"2026-05-27T10:18:33Z","abstract_excerpt":"The Policy-Space Response Oracles (PSRO) framework scales equilibrium computation to large zero-sum games by iteratively expanding a restricted strategy set using deep reinforcement learning (DRL). A central challenge is to construct, under limited computational budgets, a small strategy population whose induced game well approximates the full game. Existing PSRO variants typically expand the population using best responses to meta-strategies computed from restricted-game payoffs, which can lead to inefficient expansions that provide limited global improvement. We propose to guide population e"},"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":false},"canonical_record":{"source":{"id":"2605.28273","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T10:18:33Z","cross_cats_sorted":[],"title_canon_sha256":"2ff0beb202c4cbf03f052f29fc8ae5a577d94467a558946b8f387cad1a30fd16","abstract_canon_sha256":"235c3aa3eeb259b10927991eeab4e2586f4fdf83df20e9af5a0d8a007b56406c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:05:04.829900Z","signature_b64":"4beTW/CoADbBeq/Y0vS5wV7KlQha9OxS+sLfxPG4QQWhE2WmhqsKWLZyG4y6vP37BkFShzEUEQihRg2UlKD1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63a128272e2e54e645212f83899fc865fa51f0f57ea1549829f16a7a72890344","last_reissued_at":"2026-05-28T01:05:04.829499Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:05:04.829499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Global Policy-Space Response Oracles for Two-Player Zero-Sum Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chao Wang, Feihong Yang, Jian Wang, Junyu Zhang, Xudong Zhang","submitted_at":"2026-05-27T10:18:33Z","abstract_excerpt":"The Policy-Space Response Oracles (PSRO) framework scales equilibrium computation to large zero-sum games by iteratively expanding a restricted strategy set using deep reinforcement learning (DRL). A central challenge is to construct, under limited computational budgets, a small strategy population whose induced game well approximates the full game. Existing PSRO variants typically expand the population using best responses to meta-strategies computed from restricted-game payoffs, which can lead to inefficient expansions that provide limited global improvement. We propose to guide population e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28273","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.28273/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"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":"2605.28273","created_at":"2026-05-28T01:05:04.829557+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28273v1","created_at":"2026-05-28T01:05:04.829557+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28273","created_at":"2026-05-28T01:05:04.829557+00:00"},{"alias_kind":"pith_short_12","alias_value":"MOQSQJZOFZKO","created_at":"2026-05-28T01:05:04.829557+00:00"},{"alias_kind":"pith_short_16","alias_value":"MOQSQJZOFZKOMRJB","created_at":"2026-05-28T01:05:04.829557+00:00"},{"alias_kind":"pith_short_8","alias_value":"MOQSQJZO","created_at":"2026-05-28T01:05:04.829557+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MOQSQJZOFZKOMRJBF6BYTH6IMX","json":"https://pith.science/pith/MOQSQJZOFZKOMRJBF6BYTH6IMX.json","graph_json":"https://pith.science/api/pith-number/MOQSQJZOFZKOMRJBF6BYTH6IMX/graph.json","events_json":"https://pith.science/api/pith-number/MOQSQJZOFZKOMRJBF6BYTH6IMX/events.json","paper":"https://pith.science/paper/MOQSQJZO"},"agent_actions":{"view_html":"https://pith.science/pith/MOQSQJZOFZKOMRJBF6BYTH6IMX","download_json":"https://pith.science/pith/MOQSQJZOFZKOMRJBF6BYTH6IMX.json","view_paper":"https://pith.science/paper/MOQSQJZO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28273&json=true","fetch_graph":"https://pith.science/api/pith-number/MOQSQJZOFZKOMRJBF6BYTH6IMX/graph.json","fetch_events":"https://pith.science/api/pith-number/MOQSQJZOFZKOMRJBF6BYTH6IMX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MOQSQJZOFZKOMRJBF6BYTH6IMX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MOQSQJZOFZKOMRJBF6BYTH6IMX/action/storage_attestation","attest_author":"https://pith.science/pith/MOQSQJZOFZKOMRJBF6BYTH6IMX/action/author_attestation","sign_citation":"https://pith.science/pith/MOQSQJZOFZKOMRJBF6BYTH6IMX/action/citation_signature","submit_replication":"https://pith.science/pith/MOQSQJZOFZKOMRJBF6BYTH6IMX/action/replication_record"}},"created_at":"2026-05-28T01:05:04.829557+00:00","updated_at":"2026-05-28T01:05:04.829557+00:00"}