{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NVVSHA7RJAUATL5LGW5A73LBSO","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":"fd8d85d8ee9d7bc761e7ce4b1aa22cb9ff6c4ea1587236a29da63c1023e17809","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GT","submitted_at":"2024-10-22T00:55:04Z","title_canon_sha256":"0db9c1cf4d4ea278f74f91a17b2d03c1d884c3b10478a3f2a7f4ae6d38b4d032"},"schema_version":"1.0","source":{"id":"2410.16600","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16600","created_at":"2026-07-05T11:21:37Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16600v3","created_at":"2026-07-05T11:21:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16600","created_at":"2026-07-05T11:21:37Z"},{"alias_kind":"pith_short_12","alias_value":"NVVSHA7RJAUA","created_at":"2026-07-05T11:21:37Z"},{"alias_kind":"pith_short_16","alias_value":"NVVSHA7RJAUATL5L","created_at":"2026-07-05T11:21:37Z"},{"alias_kind":"pith_short_8","alias_value":"NVVSHA7R","created_at":"2026-07-05T11:21:37Z"}],"graph_snapshots":[{"event_id":"sha256:01ce698a97c7577656ed3c83c70d5f2a3850fd13668ea5523900033cbd027b19","target":"graph","created_at":"2026-07-05T11:21:37Z","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/2410.16600/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Behavioral diversity, expert imitation, fairness, safety goals and others give rise to preferences in sequential decision making domains that do not decompose additively across time. We introduce the class of convex Markov games that allow general convex preferences over occupancy measures. Despite infinite time horizon and strictly higher generality than Markov games, pure strategy Nash equilibria exist. Furthermore, equilibria can be approximated empirically by performing gradient descent on an upper bound of exploitability. Our experiments reveal novel solutions to classic repeated normal-f","authors_text":"Andreas Haupt, Georgios Piliouras, Ian Gemp, Luke Marris, Siqi Liu","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GT","submitted_at":"2024-10-22T00:55:04Z","title":"Convex Markov Games: A New Frontier for Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16600","kind":"arxiv","version":3},"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":"sha256:688c294f8771047e19543f80328ff363fd86a2b8d19e9a63d6ca2f8af7251c84","target":"record","created_at":"2026-07-05T11:21:37Z","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":"fd8d85d8ee9d7bc761e7ce4b1aa22cb9ff6c4ea1587236a29da63c1023e17809","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GT","submitted_at":"2024-10-22T00:55:04Z","title_canon_sha256":"0db9c1cf4d4ea278f74f91a17b2d03c1d884c3b10478a3f2a7f4ae6d38b4d032"},"schema_version":"1.0","source":{"id":"2410.16600","kind":"arxiv","version":3}},"canonical_sha256":"6d6b2383f1482809afab35ba0fed6193b4b127a66781199a0d8016999a91ce14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d6b2383f1482809afab35ba0fed6193b4b127a66781199a0d8016999a91ce14","first_computed_at":"2026-07-05T11:21:37.406032Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:37.406032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BRhwWwZhwFpnl/CwQ2SH7Qv5AQAr+dpsU/yPM0YHSBTpm0KnTmF5CvlCFctaxZzKEJnqEwfJiYI2rGfq0Ke+Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:37.406533Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.16600","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:688c294f8771047e19543f80328ff363fd86a2b8d19e9a63d6ca2f8af7251c84","sha256:01ce698a97c7577656ed3c83c70d5f2a3850fd13668ea5523900033cbd027b19"],"state_sha256":"67f0ff3c5f0f254859f43e3ef7ba1336417f923a90ef3d848b4ed279f08bb11d"}