{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JZONJ646JVJQFIDEQB2VQ5TVPN","short_pith_number":"pith:JZONJ646","schema_version":"1.0","canonical_sha256":"4e5cd4fb9e4d5302a06480755876757b631f2255fde049ef6c750b6cf95be6f9","source":{"kind":"arxiv","id":"2605.20718","version":1},"attestation_state":"computed","paper":{"title":"Policy Gradient for Continuous-Time Mean-Field Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Erhan Bayraktar, Martin Hernandez, Qinxin Yan, Yuhua Zhu","submitted_at":"2026-05-20T05:19:53Z","abstract_excerpt":"This paper develops a policy gradient method for entropy-regularized mean-field control in the discounted infinite-horizon setting. We consider randomized feedback policies and a coupled representative-particle/population system, in which the representative state evolves jointly with a population law governed by a McKean--Vlasov equation. The resulting value function is therefore defined on the product space $\\mathbb R^d \\times \\mathcal P_2(\\mathbb R^d)$.\n  A key distinction from existing policy gradient methods for mean-field control is that, after computing the value function under a fixed p"},"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":"2605.20718","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-05-20T05:19:53Z","cross_cats_sorted":[],"title_canon_sha256":"e7e4d9b84aa3300f72be23485f3584b0024193b848b09968ae855676bbf63ecd","abstract_canon_sha256":"878326038277a71b1640fd5280a344c5dc2dc55f5feb1a7f512395580846a203"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:50.616256Z","signature_b64":"uwke/fayUGqWW70bQbijBwSqhhRHH1EvQCgUXWaI5CTaXQjeLAgIGqrgjJs/McBI6EBKtw8B1avMekpnG3tlDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e5cd4fb9e4d5302a06480755876757b631f2255fde049ef6c750b6cf95be6f9","last_reissued_at":"2026-05-21T01:04:50.615534Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:50.615534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Policy Gradient for Continuous-Time Mean-Field Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Erhan Bayraktar, Martin Hernandez, Qinxin Yan, Yuhua Zhu","submitted_at":"2026-05-20T05:19:53Z","abstract_excerpt":"This paper develops a policy gradient method for entropy-regularized mean-field control in the discounted infinite-horizon setting. We consider randomized feedback policies and a coupled representative-particle/population system, in which the representative state evolves jointly with a population law governed by a McKean--Vlasov equation. The resulting value function is therefore defined on the product space $\\mathbb R^d \\times \\mathcal P_2(\\mathbb R^d)$.\n  A key distinction from existing policy gradient methods for mean-field control is that, after computing the value function under a fixed p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20718","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/2605.20718/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":"2605.20718","created_at":"2026-05-21T01:04:50.615626+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20718v1","created_at":"2026-05-21T01:04:50.615626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20718","created_at":"2026-05-21T01:04:50.615626+00:00"},{"alias_kind":"pith_short_12","alias_value":"JZONJ646JVJQ","created_at":"2026-05-21T01:04:50.615626+00:00"},{"alias_kind":"pith_short_16","alias_value":"JZONJ646JVJQFIDE","created_at":"2026-05-21T01:04:50.615626+00:00"},{"alias_kind":"pith_short_8","alias_value":"JZONJ646","created_at":"2026-05-21T01:04:50.615626+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/JZONJ646JVJQFIDEQB2VQ5TVPN","json":"https://pith.science/pith/JZONJ646JVJQFIDEQB2VQ5TVPN.json","graph_json":"https://pith.science/api/pith-number/JZONJ646JVJQFIDEQB2VQ5TVPN/graph.json","events_json":"https://pith.science/api/pith-number/JZONJ646JVJQFIDEQB2VQ5TVPN/events.json","paper":"https://pith.science/paper/JZONJ646"},"agent_actions":{"view_html":"https://pith.science/pith/JZONJ646JVJQFIDEQB2VQ5TVPN","download_json":"https://pith.science/pith/JZONJ646JVJQFIDEQB2VQ5TVPN.json","view_paper":"https://pith.science/paper/JZONJ646","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20718&json=true","fetch_graph":"https://pith.science/api/pith-number/JZONJ646JVJQFIDEQB2VQ5TVPN/graph.json","fetch_events":"https://pith.science/api/pith-number/JZONJ646JVJQFIDEQB2VQ5TVPN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JZONJ646JVJQFIDEQB2VQ5TVPN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JZONJ646JVJQFIDEQB2VQ5TVPN/action/storage_attestation","attest_author":"https://pith.science/pith/JZONJ646JVJQFIDEQB2VQ5TVPN/action/author_attestation","sign_citation":"https://pith.science/pith/JZONJ646JVJQFIDEQB2VQ5TVPN/action/citation_signature","submit_replication":"https://pith.science/pith/JZONJ646JVJQFIDEQB2VQ5TVPN/action/replication_record"}},"created_at":"2026-05-21T01:04:50.615626+00:00","updated_at":"2026-05-21T01:04:50.615626+00:00"}