{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JV6X35LJHAPFDIADVPVL4OL5BN","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":"4eb73b387613894a0b3c2ac3ae027d61669efb475408ec9201f6e2f8c1c6116d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-06-11T04:02:25Z","title_canon_sha256":"63b2aac4b4c5d7665f38f1e2ced11556d7aa85fcec16ba103d0942474eca79ce"},"schema_version":"1.0","source":{"id":"2606.12875","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12875","created_at":"2026-06-12T01:08:56Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12875v1","created_at":"2026-06-12T01:08:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12875","created_at":"2026-06-12T01:08:56Z"},{"alias_kind":"pith_short_12","alias_value":"JV6X35LJHAPF","created_at":"2026-06-12T01:08:56Z"},{"alias_kind":"pith_short_16","alias_value":"JV6X35LJHAPFDIAD","created_at":"2026-06-12T01:08:56Z"},{"alias_kind":"pith_short_8","alias_value":"JV6X35LJ","created_at":"2026-06-12T01:08:56Z"}],"graph_snapshots":[{"event_id":"sha256:eb42aa1e411d1d7518f4b2f0e908c4df90905002a77321109603012968deb79c","target":"graph","created_at":"2026-06-12T01:08:56Z","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/2606.12875/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study continuous-time reinforcement learning for the optimal switching problem, in which a decision-maker controls a diffusion process by switching among finitely many regimes, incurring both running and transition costs. To enable exploration, we relax the classical deterministic switching control to a randomized framework, where the switching decisions are governed by a continuous-time Markov chain with state-dependent generator, and augment the cost functional with a KL-divergence regularization weighted by a temperature parameter $\\lambda$. Under mild assumptions on the coefficients, we","authors_text":"Yuchao Dong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-06-11T04:02:25Z","title":"Randomized Optimal Switching Problem and Related Mirror Descent Flow"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12875","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":"sha256:7351e1e1aeb92b7a230d67d8e397a14ea9b7eb6708cae4a42f9db59de3e26cdd","target":"record","created_at":"2026-06-12T01:08:56Z","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":"4eb73b387613894a0b3c2ac3ae027d61669efb475408ec9201f6e2f8c1c6116d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-06-11T04:02:25Z","title_canon_sha256":"63b2aac4b4c5d7665f38f1e2ced11556d7aa85fcec16ba103d0942474eca79ce"},"schema_version":"1.0","source":{"id":"2606.12875","kind":"arxiv","version":1}},"canonical_sha256":"4d7d7df569381e51a003abeabe397d0b698ca63d36e1fd90ce2989f4cf2e4688","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d7d7df569381e51a003abeabe397d0b698ca63d36e1fd90ce2989f4cf2e4688","first_computed_at":"2026-06-12T01:08:56.211099Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:08:56.211099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZFPT91Yza7B52HMpCjWUsZioUrVdi4u2CLgSpdYSsV6ZS49jRGCDoQHG0gi2fEmcv5eTcvj4MlcT43LZD3gdCQ==","signature_status":"signed_v1","signed_at":"2026-06-12T01:08:56.211935Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.12875","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7351e1e1aeb92b7a230d67d8e397a14ea9b7eb6708cae4a42f9db59de3e26cdd","sha256:eb42aa1e411d1d7518f4b2f0e908c4df90905002a77321109603012968deb79c"],"state_sha256":"c4f1c40d58f23ad9b85f1d83da132c93c977450a98ba54e5b98101e7a13ba3fb"}