{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KNLQ4YW6XKCYB47SXDVEPDVQRU","short_pith_number":"pith:KNLQ4YW6","canonical_record":{"source":{"id":"2310.03354","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-05T07:19:33Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"c1b528f7dc5981820e2dc1080299b52a77884048a755f0cc908f63fd80f95eae","abstract_canon_sha256":"9ac08c793bb37ae55b8ce9d93002e9f142946b403f1004fff6727f2a7dca848e"},"schema_version":"1.0"},"canonical_sha256":"53570e62deba8580f3f2b8ea478eb08d02b58359394bcad19928042814cf3303","source":{"kind":"arxiv","id":"2310.03354","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.03354","created_at":"2026-07-05T06:57:32Z"},{"alias_kind":"arxiv_version","alias_value":"2310.03354v1","created_at":"2026-07-05T06:57:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03354","created_at":"2026-07-05T06:57:32Z"},{"alias_kind":"pith_short_12","alias_value":"KNLQ4YW6XKCY","created_at":"2026-07-05T06:57:32Z"},{"alias_kind":"pith_short_16","alias_value":"KNLQ4YW6XKCYB47S","created_at":"2026-07-05T06:57:32Z"},{"alias_kind":"pith_short_8","alias_value":"KNLQ4YW6","created_at":"2026-07-05T06:57:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KNLQ4YW6XKCYB47SXDVEPDVQRU","target":"record","payload":{"canonical_record":{"source":{"id":"2310.03354","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-05T07:19:33Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"c1b528f7dc5981820e2dc1080299b52a77884048a755f0cc908f63fd80f95eae","abstract_canon_sha256":"9ac08c793bb37ae55b8ce9d93002e9f142946b403f1004fff6727f2a7dca848e"},"schema_version":"1.0"},"canonical_sha256":"53570e62deba8580f3f2b8ea478eb08d02b58359394bcad19928042814cf3303","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:32.173649Z","signature_b64":"AJ1zdMZihvoTlHOnQ/5Xpy7Fhu5ubdgU8ZmCzRiHYkRJOyASX/lxKCcmJnfe2TjPvk+mVIhVbgaY9NxyRMFdCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53570e62deba8580f3f2b8ea478eb08d02b58359394bcad19928042814cf3303","last_reissued_at":"2026-07-05T06:57:32.173159Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:32.173159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.03354","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:57:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8kz3p1Pqk+feSxuhE8byxAcSm7eL0h8ArlPqisOR4RNU/3PGoZtQmk8N6Lc4Tvw+zewW/nqFgzwN4Xbp9NQbAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:48:02.352958Z"},"content_sha256":"f53afe46ff9932206141288420557f068f62c2f5e63e7809ad6f03808597dd34","schema_version":"1.0","event_id":"sha256:f53afe46ff9932206141288420557f068f62c2f5e63e7809ad6f03808597dd34"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KNLQ4YW6XKCYB47SXDVEPDVQRU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fictitious Cross-Play: Learning Global Nash Equilibrium in Mixed Cooperative-Competitive Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Chao Yu, Yancheng Liang, Yi Wu, Yu Wang, Zelai Xu","submitted_at":"2023-10-05T07:19:33Z","abstract_excerpt":"Self-play (SP) is a popular multi-agent reinforcement learning (MARL) framework for solving competitive games, where each agent optimizes policy by treating others as part of the environment. Despite the empirical successes, the theoretical properties of SP-based methods are limited to two-player zero-sum games. However, for mixed cooperative-competitive games where agents on the same team need to cooperate with each other, we can show a simple counter-example where SP-based methods cannot converge to a global Nash equilibrium (NE) with high probability. Alternatively, Policy-Space Response Or"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03354","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/2310.03354/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:57:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sTvD7jPah+rtHcHMOdzOnP7AEeiNokbZpgLjVyNHICgQDm6HFHEweESMiypJfhwY2kJ5g5MJbIzA0FOwUiJkDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:48:02.354065Z"},"content_sha256":"b91b811b9027831fce7e297d0b56234dc0521e02d0980fea3c223c3aba123e63","schema_version":"1.0","event_id":"sha256:b91b811b9027831fce7e297d0b56234dc0521e02d0980fea3c223c3aba123e63"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KNLQ4YW6XKCYB47SXDVEPDVQRU/bundle.json","state_url":"https://pith.science/pith/KNLQ4YW6XKCYB47SXDVEPDVQRU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KNLQ4YW6XKCYB47SXDVEPDVQRU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T17:48:02Z","links":{"resolver":"https://pith.science/pith/KNLQ4YW6XKCYB47SXDVEPDVQRU","bundle":"https://pith.science/pith/KNLQ4YW6XKCYB47SXDVEPDVQRU/bundle.json","state":"https://pith.science/pith/KNLQ4YW6XKCYB47SXDVEPDVQRU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KNLQ4YW6XKCYB47SXDVEPDVQRU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KNLQ4YW6XKCYB47SXDVEPDVQRU","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":"9ac08c793bb37ae55b8ce9d93002e9f142946b403f1004fff6727f2a7dca848e","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-05T07:19:33Z","title_canon_sha256":"c1b528f7dc5981820e2dc1080299b52a77884048a755f0cc908f63fd80f95eae"},"schema_version":"1.0","source":{"id":"2310.03354","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.03354","created_at":"2026-07-05T06:57:32Z"},{"alias_kind":"arxiv_version","alias_value":"2310.03354v1","created_at":"2026-07-05T06:57:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03354","created_at":"2026-07-05T06:57:32Z"},{"alias_kind":"pith_short_12","alias_value":"KNLQ4YW6XKCY","created_at":"2026-07-05T06:57:32Z"},{"alias_kind":"pith_short_16","alias_value":"KNLQ4YW6XKCYB47S","created_at":"2026-07-05T06:57:32Z"},{"alias_kind":"pith_short_8","alias_value":"KNLQ4YW6","created_at":"2026-07-05T06:57:32Z"}],"graph_snapshots":[{"event_id":"sha256:b91b811b9027831fce7e297d0b56234dc0521e02d0980fea3c223c3aba123e63","target":"graph","created_at":"2026-07-05T06:57:32Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.03354/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-play (SP) is a popular multi-agent reinforcement learning (MARL) framework for solving competitive games, where each agent optimizes policy by treating others as part of the environment. Despite the empirical successes, the theoretical properties of SP-based methods are limited to two-player zero-sum games. However, for mixed cooperative-competitive games where agents on the same team need to cooperate with each other, we can show a simple counter-example where SP-based methods cannot converge to a global Nash equilibrium (NE) with high probability. Alternatively, Policy-Space Response Or","authors_text":"Chao Yu, Yancheng Liang, Yi Wu, Yu Wang, Zelai Xu","cross_cats":["cs.LG","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-05T07:19:33Z","title":"Fictitious Cross-Play: Learning Global Nash Equilibrium in Mixed Cooperative-Competitive Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03354","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f53afe46ff9932206141288420557f068f62c2f5e63e7809ad6f03808597dd34","target":"record","created_at":"2026-07-05T06:57:32Z","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":"9ac08c793bb37ae55b8ce9d93002e9f142946b403f1004fff6727f2a7dca848e","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-05T07:19:33Z","title_canon_sha256":"c1b528f7dc5981820e2dc1080299b52a77884048a755f0cc908f63fd80f95eae"},"schema_version":"1.0","source":{"id":"2310.03354","kind":"arxiv","version":1}},"canonical_sha256":"53570e62deba8580f3f2b8ea478eb08d02b58359394bcad19928042814cf3303","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53570e62deba8580f3f2b8ea478eb08d02b58359394bcad19928042814cf3303","first_computed_at":"2026-07-05T06:57:32.173159Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:57:32.173159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AJ1zdMZihvoTlHOnQ/5Xpy7Fhu5ubdgU8ZmCzRiHYkRJOyASX/lxKCcmJnfe2TjPvk+mVIhVbgaY9NxyRMFdCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:57:32.173649Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.03354","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f53afe46ff9932206141288420557f068f62c2f5e63e7809ad6f03808597dd34","sha256:b91b811b9027831fce7e297d0b56234dc0521e02d0980fea3c223c3aba123e63"],"state_sha256":"2fd5de019ba54b98cea152da04351a175c94352465029a18924c762bbe72382f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IhwhjheOEVCgjclnC8NSzc4VJfkDvYHM5kizY/0hYCXd+AHsW6UvMwXZMwzk6FMmMqJ4ZI2MWqRVlUJ/84oFDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T17:48:02.361641Z","bundle_sha256":"f941aaeca4be08749a372386f4f2bf01ef4d614d83eed74cf626307baa5f946c"}}