{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JZONJ646JVJQFIDEQB2VQ5TVPN","short_pith_number":"pith:JZONJ646","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"},"canonical_sha256":"4e5cd4fb9e4d5302a06480755876757b631f2255fde049ef6c750b6cf95be6f9","source":{"kind":"arxiv","id":"2605.20718","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20718","created_at":"2026-05-21T01:04:50Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20718v1","created_at":"2026-05-21T01:04:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20718","created_at":"2026-05-21T01:04:50Z"},{"alias_kind":"pith_short_12","alias_value":"JZONJ646JVJQ","created_at":"2026-05-21T01:04:50Z"},{"alias_kind":"pith_short_16","alias_value":"JZONJ646JVJQFIDE","created_at":"2026-05-21T01:04:50Z"},{"alias_kind":"pith_short_8","alias_value":"JZONJ646","created_at":"2026-05-21T01:04:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JZONJ646JVJQFIDEQB2VQ5TVPN","target":"record","payload":{"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"},"canonical_sha256":"4e5cd4fb9e4d5302a06480755876757b631f2255fde049ef6c750b6cf95be6f9","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"},"source_kind":"arxiv","source_id":"2605.20718","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":"2026-05-21T01:04:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w/8YI0nCmtCrkRA02F3uaA8UF67Kzk/QzY9BuqY8My6i2NLUpWr3Lp1nqfFQ/NGWTgu0so0+Z0W+OGsglLImAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T14:24:44.414944Z"},"content_sha256":"a5510367568929fc60f2a48231789e82fc623a241fac0277ab68b6fd5ef1071b","schema_version":"1.0","event_id":"sha256:a5510367568929fc60f2a48231789e82fc623a241fac0277ab68b6fd5ef1071b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JZONJ646JVJQFIDEQB2VQ5TVPN","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:04:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"esVyh6pO1hFyT5+hJY9Krkcl/LDgGQXO3bfUaoEBLTLW2IHMNNL4biKBdlpRV2FBsLd2wJETxeeUmc829I31DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T14:24:44.415358Z"},"content_sha256":"bea1a8a372a7557c0803357a546dead77804710b96e4a9ec68806cfe4e190a48","schema_version":"1.0","event_id":"sha256:bea1a8a372a7557c0803357a546dead77804710b96e4a9ec68806cfe4e190a48"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JZONJ646JVJQFIDEQB2VQ5TVPN/bundle.json","state_url":"https://pith.science/pith/JZONJ646JVJQFIDEQB2VQ5TVPN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JZONJ646JVJQFIDEQB2VQ5TVPN/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":"2026-05-24T14:24:44Z","links":{"resolver":"https://pith.science/pith/JZONJ646JVJQFIDEQB2VQ5TVPN","bundle":"https://pith.science/pith/JZONJ646JVJQFIDEQB2VQ5TVPN/bundle.json","state":"https://pith.science/pith/JZONJ646JVJQFIDEQB2VQ5TVPN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JZONJ646JVJQFIDEQB2VQ5TVPN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JZONJ646JVJQFIDEQB2VQ5TVPN","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":"878326038277a71b1640fd5280a344c5dc2dc55f5feb1a7f512395580846a203","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-05-20T05:19:53Z","title_canon_sha256":"e7e4d9b84aa3300f72be23485f3584b0024193b848b09968ae855676bbf63ecd"},"schema_version":"1.0","source":{"id":"2605.20718","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20718","created_at":"2026-05-21T01:04:50Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20718v1","created_at":"2026-05-21T01:04:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20718","created_at":"2026-05-21T01:04:50Z"},{"alias_kind":"pith_short_12","alias_value":"JZONJ646JVJQ","created_at":"2026-05-21T01:04:50Z"},{"alias_kind":"pith_short_16","alias_value":"JZONJ646JVJQFIDE","created_at":"2026-05-21T01:04:50Z"},{"alias_kind":"pith_short_8","alias_value":"JZONJ646","created_at":"2026-05-21T01:04:50Z"}],"graph_snapshots":[{"event_id":"sha256:bea1a8a372a7557c0803357a546dead77804710b96e4a9ec68806cfe4e190a48","target":"graph","created_at":"2026-05-21T01:04:50Z","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/2605.20718/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Erhan Bayraktar, Martin Hernandez, Qinxin Yan, Yuhua Zhu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-05-20T05:19:53Z","title":"Policy Gradient for Continuous-Time Mean-Field Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20718","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:a5510367568929fc60f2a48231789e82fc623a241fac0277ab68b6fd5ef1071b","target":"record","created_at":"2026-05-21T01:04:50Z","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":"878326038277a71b1640fd5280a344c5dc2dc55f5feb1a7f512395580846a203","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-05-20T05:19:53Z","title_canon_sha256":"e7e4d9b84aa3300f72be23485f3584b0024193b848b09968ae855676bbf63ecd"},"schema_version":"1.0","source":{"id":"2605.20718","kind":"arxiv","version":1}},"canonical_sha256":"4e5cd4fb9e4d5302a06480755876757b631f2255fde049ef6c750b6cf95be6f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4e5cd4fb9e4d5302a06480755876757b631f2255fde049ef6c750b6cf95be6f9","first_computed_at":"2026-05-21T01:04:50.615534Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:50.615534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uwke/fayUGqWW70bQbijBwSqhhRHH1EvQCgUXWaI5CTaXQjeLAgIGqrgjJs/McBI6EBKtw8B1avMekpnG3tlDw==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:50.616256Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20718","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5510367568929fc60f2a48231789e82fc623a241fac0277ab68b6fd5ef1071b","sha256:bea1a8a372a7557c0803357a546dead77804710b96e4a9ec68806cfe4e190a48"],"state_sha256":"7e11187b657c94e211bbe056dc8be15b0005c50863c84fe63db0797af10e33d2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cw06Nr/51VCCiEDSmnAuOtHforc/CM87DFgCrIF/YSld2KZbtFYqSPZdL6Rhts8jXYNU6VXIJVgmUI5zehBYBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T14:24:44.418725Z","bundle_sha256":"77494bf0b586a7fe6c42e4cc89df75a7d33797fa7c488ca8537d569f279d69ee"}}