{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4CT2BJIXH7QY2ZR5R2V6F34SJQ","short_pith_number":"pith:4CT2BJIX","canonical_record":{"source":{"id":"2506.08121","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-06-09T18:20:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d64d1748e66243c9575e4587a573af2be13a5a05524610bcae6a9182ed398fe6","abstract_canon_sha256":"3863f8aa0fe53e0bedb9e2394dfd97fd8da2a98f2204b54cb5f84d572e77a673"},"schema_version":"1.0"},"canonical_sha256":"e0a7a0a5173fe18d663d8eabe2ef924c0e37243792e4c2c6abf30a5ae27d9b11","source":{"kind":"arxiv","id":"2506.08121","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08121","created_at":"2026-07-05T11:18:45Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08121v1","created_at":"2026-07-05T11:18:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08121","created_at":"2026-07-05T11:18:45Z"},{"alias_kind":"pith_short_12","alias_value":"4CT2BJIXH7QY","created_at":"2026-07-05T11:18:45Z"},{"alias_kind":"pith_short_16","alias_value":"4CT2BJIXH7QY2ZR5","created_at":"2026-07-05T11:18:45Z"},{"alias_kind":"pith_short_8","alias_value":"4CT2BJIX","created_at":"2026-07-05T11:18:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4CT2BJIXH7QY2ZR5R2V6F34SJQ","target":"record","payload":{"canonical_record":{"source":{"id":"2506.08121","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-06-09T18:20:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d64d1748e66243c9575e4587a573af2be13a5a05524610bcae6a9182ed398fe6","abstract_canon_sha256":"3863f8aa0fe53e0bedb9e2394dfd97fd8da2a98f2204b54cb5f84d572e77a673"},"schema_version":"1.0"},"canonical_sha256":"e0a7a0a5173fe18d663d8eabe2ef924c0e37243792e4c2c6abf30a5ae27d9b11","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:45.047557Z","signature_b64":"cdENDgWRTWsB3Crt9BpqeinY05pVOHWyYyUwFp8wdBLWXn1YheSH2Rd2gxoLXlTPClviHlxlHbtDrtFr3HqiAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0a7a0a5173fe18d663d8eabe2ef924c0e37243792e4c2c6abf30a5ae27d9b11","last_reissued_at":"2026-07-05T11:18:45.047094Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:45.047094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.08121","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":"2026-07-05T11:18:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VBu9r50Wkrb3rRTx5Qv3fLKR2Ai2YVNEDUNtuDWdpz1rsTFcsOZvBWTVHzOvWqq4Gv4XYkjKUiOkPvczSA+hDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:57:41.208383Z"},"content_sha256":"6ee03f163f800ff699f457d4d8621bfc2fc7941531676afa55a1c28b4bb35d11","schema_version":"1.0","event_id":"sha256:6ee03f163f800ff699f457d4d8621bfc2fc7941531676afa55a1c28b4bb35d11"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4CT2BJIXH7QY2ZR5R2V6F34SJQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Continuous Policy and Value Iteration for Stochastic Control Problems and Its Convergence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Gu Wang, Qi Feng","submitted_at":"2025-06-09T18:20:21Z","abstract_excerpt":"We introduce a continuous policy-value iteration algorithm where the approximations of the value function of a stochastic control problem and the optimal control are simultaneously updated through Langevin-type dynamics. This framework applies to both the entropy-regularized relaxed control problems and the classical control problems, with infinite horizon. We establish policy improvement and demonstrate convergence to the optimal control under the monotonicity condition of the Hamiltonian. By utilizing Langevin-type stochastic differential equations for continuous updates along the policy ite"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08121","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/2506.08121/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":"2026-07-05T11:18:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h7xadJ3sr12LYB4D+0KasL0i9tNncAs3gV5s/S92hih4XEZ98UrXsb/DXuq09VE0A8db/Ri2phjcH7h4ZBNMBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:57:41.208899Z"},"content_sha256":"93262ebfdf69dc409853c4a29124a26924498cfb31b24bf8c9f25cceff5af5ad","schema_version":"1.0","event_id":"sha256:93262ebfdf69dc409853c4a29124a26924498cfb31b24bf8c9f25cceff5af5ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4CT2BJIXH7QY2ZR5R2V6F34SJQ/bundle.json","state_url":"https://pith.science/pith/4CT2BJIXH7QY2ZR5R2V6F34SJQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4CT2BJIXH7QY2ZR5R2V6F34SJQ/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":"2026-08-08T12:57:41Z","links":{"resolver":"https://pith.science/pith/4CT2BJIXH7QY2ZR5R2V6F34SJQ","bundle":"https://pith.science/pith/4CT2BJIXH7QY2ZR5R2V6F34SJQ/bundle.json","state":"https://pith.science/pith/4CT2BJIXH7QY2ZR5R2V6F34SJQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4CT2BJIXH7QY2ZR5R2V6F34SJQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4CT2BJIXH7QY2ZR5R2V6F34SJQ","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":"3863f8aa0fe53e0bedb9e2394dfd97fd8da2a98f2204b54cb5f84d572e77a673","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-06-09T18:20:21Z","title_canon_sha256":"d64d1748e66243c9575e4587a573af2be13a5a05524610bcae6a9182ed398fe6"},"schema_version":"1.0","source":{"id":"2506.08121","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08121","created_at":"2026-07-05T11:18:45Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08121v1","created_at":"2026-07-05T11:18:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08121","created_at":"2026-07-05T11:18:45Z"},{"alias_kind":"pith_short_12","alias_value":"4CT2BJIXH7QY","created_at":"2026-07-05T11:18:45Z"},{"alias_kind":"pith_short_16","alias_value":"4CT2BJIXH7QY2ZR5","created_at":"2026-07-05T11:18:45Z"},{"alias_kind":"pith_short_8","alias_value":"4CT2BJIX","created_at":"2026-07-05T11:18:45Z"}],"graph_snapshots":[{"event_id":"sha256:93262ebfdf69dc409853c4a29124a26924498cfb31b24bf8c9f25cceff5af5ad","target":"graph","created_at":"2026-07-05T11:18:45Z","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/2506.08121/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a continuous policy-value iteration algorithm where the approximations of the value function of a stochastic control problem and the optimal control are simultaneously updated through Langevin-type dynamics. This framework applies to both the entropy-regularized relaxed control problems and the classical control problems, with infinite horizon. We establish policy improvement and demonstrate convergence to the optimal control under the monotonicity condition of the Hamiltonian. By utilizing Langevin-type stochastic differential equations for continuous updates along the policy ite","authors_text":"Gu Wang, Qi Feng","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-06-09T18:20:21Z","title":"Continuous Policy and Value Iteration for Stochastic Control Problems and Its Convergence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08121","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":"sha256:6ee03f163f800ff699f457d4d8621bfc2fc7941531676afa55a1c28b4bb35d11","target":"record","created_at":"2026-07-05T11:18:45Z","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":"3863f8aa0fe53e0bedb9e2394dfd97fd8da2a98f2204b54cb5f84d572e77a673","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-06-09T18:20:21Z","title_canon_sha256":"d64d1748e66243c9575e4587a573af2be13a5a05524610bcae6a9182ed398fe6"},"schema_version":"1.0","source":{"id":"2506.08121","kind":"arxiv","version":1}},"canonical_sha256":"e0a7a0a5173fe18d663d8eabe2ef924c0e37243792e4c2c6abf30a5ae27d9b11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0a7a0a5173fe18d663d8eabe2ef924c0e37243792e4c2c6abf30a5ae27d9b11","first_computed_at":"2026-07-05T11:18:45.047094Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:45.047094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cdENDgWRTWsB3Crt9BpqeinY05pVOHWyYyUwFp8wdBLWXn1YheSH2Rd2gxoLXlTPClviHlxlHbtDrtFr3HqiAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:45.047557Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.08121","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ee03f163f800ff699f457d4d8621bfc2fc7941531676afa55a1c28b4bb35d11","sha256:93262ebfdf69dc409853c4a29124a26924498cfb31b24bf8c9f25cceff5af5ad"],"state_sha256":"1a4ebc25f8a7d1f0c7d87c4808e5c41b5f2b472a467c5da68540fda48bcedd14"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hEkMFiwcLaQUU7Zb7IiO65XnChGOU6RB3qG/jyb4caPPPODTTe3cHAwh6FA/2XIqX5NW3bA6ws5CYyVcXrpkBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:57:41.213355Z","bundle_sha256":"1388f4fb2ce4b0d0b86e23dc38e7555fa6f43716bfe81448cb727a70741d03ad"}}