{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WWIKMOZM25FCRX5RHYRJURMUOJ","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":"91f14b68a9cda9253985ded9dce877478b425d8b09684c4c7692a0e2baa00db3","cross_cats_sorted":["cs.LG","q-fin.CP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-12-04T11:48:07Z","title_canon_sha256":"629e83184e871638facfcc3fbcf092f986987c631c7bddce0a7436fea773447a"},"schema_version":"1.0","source":{"id":"2512.04697","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.04697","created_at":"2026-07-31T01:08:54Z"},{"alias_kind":"arxiv_version","alias_value":"2512.04697v3","created_at":"2026-07-31T01:08:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.04697","created_at":"2026-07-31T01:08:54Z"},{"alias_kind":"pith_short_12","alias_value":"WWIKMOZM25FC","created_at":"2026-07-31T01:08:54Z"},{"alias_kind":"pith_short_16","alias_value":"WWIKMOZM25FCRX5R","created_at":"2026-07-31T01:08:54Z"},{"alias_kind":"pith_short_8","alias_value":"WWIKMOZM","created_at":"2026-07-31T01:08:54Z"}],"graph_snapshots":[{"event_id":"sha256:cec2d41466a38d6e95bb383352cda3518d5b6a972e12aefe71f7a1287b58d897","target":"graph","created_at":"2026-07-31T01:08:54Z","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/2512.04697/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper studies the continuous-time reinforcement learning (RL) for optimal switching problems across multiple regimes. We consider a type of exploratory formulation under entropy regularization where the agent randomizes both the timing of switches and the selection of regimes through the generator matrix of an associated continuous-time finite-state Markov chain. We establish the well-posedness of the associated system of Hamilton-Jacobi-Bellman (HJB) equations and provide a characterization of the optimal policy. The policy improvement and the convergence of the policy iterations are rig","authors_text":"Mengge Li, Xiang Yu, Yijie Huang, Zhou Zhou","cross_cats":["cs.LG","q-fin.CP"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-12-04T11:48:07Z","title":"Continuous-time reinforcement learning for optimal switching over multiple regimes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.04697","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":"sha256:07c83459ef32002201dc6d2aedd7a16d3e5862f3f74e54250c606d0e60b335d3","target":"record","created_at":"2026-07-31T01:08:54Z","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":"91f14b68a9cda9253985ded9dce877478b425d8b09684c4c7692a0e2baa00db3","cross_cats_sorted":["cs.LG","q-fin.CP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-12-04T11:48:07Z","title_canon_sha256":"629e83184e871638facfcc3fbcf092f986987c631c7bddce0a7436fea773447a"},"schema_version":"1.0","source":{"id":"2512.04697","kind":"arxiv","version":3}},"canonical_sha256":"b590a63b2cd74a28dfb13e229a4594725bd6d6f638438ec7c3de1ba3b98aa3c0","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b590a63b2cd74a28dfb13e229a4594725bd6d6f638438ec7c3de1ba3b98aa3c0","first_computed_at":"2026-07-31T01:08:54.841852Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:08:54.841852Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2512.04697","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:07c83459ef32002201dc6d2aedd7a16d3e5862f3f74e54250c606d0e60b335d3","sha256:cec2d41466a38d6e95bb383352cda3518d5b6a972e12aefe71f7a1287b58d897"],"state_sha256":"d291f4e82a6a8bcb2b1f09d7d47b99d5e37b26d05c6ccbc82f089f199a8daae1"}