{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LCFFQAKSRL4XI7YDLP72D2NZ7D","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":"59f6dd108cb657a3ef0e0da7f76a2e9944a660af49045866232f9675246032d1","cross_cats_sorted":["cs.LG","q-fin.CP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-07-05T14:06:59Z","title_canon_sha256":"1799f05ad60916078d6b384c2ffb58d7ce7a751179f3b1953d3d15fc99ab4f7b"},"schema_version":"1.0","source":{"id":"2407.04521","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04521","created_at":"2026-07-05T10:36:26Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04521v2","created_at":"2026-07-05T10:36:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04521","created_at":"2026-07-05T10:36:26Z"},{"alias_kind":"pith_short_12","alias_value":"LCFFQAKSRL4X","created_at":"2026-07-05T10:36:26Z"},{"alias_kind":"pith_short_16","alias_value":"LCFFQAKSRL4XI7YD","created_at":"2026-07-05T10:36:26Z"},{"alias_kind":"pith_short_8","alias_value":"LCFFQAKS","created_at":"2026-07-05T10:36:26Z"}],"graph_snapshots":[{"event_id":"sha256:a6e01e3e227bdda5944b11ad24ca68f890ae0a0bff8451ad57bfb085581a521a","target":"graph","created_at":"2026-07-05T10:36:26Z","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/2407.04521/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper studies the continuous-time q-learning in mean-field jump-diffusion models when the population distribution is not directly observable. We propose the integrated q-function in decoupled form (decoupled Iq-function) from the representative agent's perspective and establish its martingale characterization, which provides a unified policy evaluation rule for both mean-field game (MFG) and mean-field control (MFC) problems. Moreover, we consider the learning procedure where the representative agent updates the population distribution based on his own state values. Depending on the task ","authors_text":"Fengyi Yuan, Xiang Yu, Xiaoli Wei","cross_cats":["cs.LG","q-fin.CP"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-07-05T14:06:59Z","title":"Unified continuous-time q-learning for mean-field game and mean-field control problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04521","kind":"arxiv","version":2},"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":"sha256:73c45387804fa6e664144e3553f57a27c1e6677e2582913423ee1d27f829935a","target":"record","created_at":"2026-07-05T10:36:26Z","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":"59f6dd108cb657a3ef0e0da7f76a2e9944a660af49045866232f9675246032d1","cross_cats_sorted":["cs.LG","q-fin.CP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-07-05T14:06:59Z","title_canon_sha256":"1799f05ad60916078d6b384c2ffb58d7ce7a751179f3b1953d3d15fc99ab4f7b"},"schema_version":"1.0","source":{"id":"2407.04521","kind":"arxiv","version":2}},"canonical_sha256":"588a5801528af9747f035bffa1e9b9f8c06eb06e4e6bc12b764ccf6c057250a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"588a5801528af9747f035bffa1e9b9f8c06eb06e4e6bc12b764ccf6c057250a2","first_computed_at":"2026-07-05T10:36:26.225774Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:36:26.225774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IThJfYtjEFOHKq2SH1QujP2re87nAWOlZQW1AakCL+xcpxcZ/my8k25/rdvgPSeSij1JvDXp6bT/q4ScLpWbAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:36:26.226262Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.04521","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73c45387804fa6e664144e3553f57a27c1e6677e2582913423ee1d27f829935a","sha256:a6e01e3e227bdda5944b11ad24ca68f890ae0a0bff8451ad57bfb085581a521a"],"state_sha256":"f1ec652529b461b85bc42dfe064ff576725727c1576dff614bebbecdfb327929"}