{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JWKTAAMM44P3DVZQIGM4523WZL","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":"0244715691c2b8b3bcb67a522f865499e0f8e10e86808de6336226a981c989b6","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-02T10:09:29Z","title_canon_sha256":"bc908ab3554c74d7df3a2c817052193312cc2ff09c763e05f7dc58f3a982de6a"},"schema_version":"1.0","source":{"id":"2602.01903","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.01903","created_at":"2026-06-03T01:05:09Z"},{"alias_kind":"arxiv_version","alias_value":"2602.01903v2","created_at":"2026-06-03T01:05:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.01903","created_at":"2026-06-03T01:05:09Z"},{"alias_kind":"pith_short_12","alias_value":"JWKTAAMM44P3","created_at":"2026-06-03T01:05:09Z"},{"alias_kind":"pith_short_16","alias_value":"JWKTAAMM44P3DVZQ","created_at":"2026-06-03T01:05:09Z"},{"alias_kind":"pith_short_8","alias_value":"JWKTAAMM","created_at":"2026-06-03T01:05:09Z"}],"graph_snapshots":[{"event_id":"sha256:14f21e9708cc80e0fba0558b8292acd1af7d23b99fe8731e5984bd94dbf586c1","target":"graph","created_at":"2026-06-03T01:05:09Z","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/2602.01903/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work studies online episodic tabular Markov decision processes (MDPs) with known transitions and develops best-of-both-worlds algorithms that achieve refined data-dependent regret bounds in the adversarial regime and variance-dependent regret bounds in the stochastic regime. We quantify MDP complexity using a first-order quantity and several new data-dependent measures for the adversarial regime, including a second-order quantity and a path-length measure, as well as variance-based measures for the stochastic regime. To adapt to these measures, we develop algorithms based on global optimi","authors_text":"Kenji Yamanishi, Mingyi Li, Taira Tsuchiya","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-02T10:09:29Z","title":"Data- and Variance-dependent Regret Bounds for Online Tabular MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.01903","kind":"arxiv","version":2},"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":"sha256:13a14daa1fad9842498dd25eb6adddd3c61dc1f91807912eec634b5b2f5492af","target":"record","created_at":"2026-06-03T01:05:09Z","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":"0244715691c2b8b3bcb67a522f865499e0f8e10e86808de6336226a981c989b6","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-02T10:09:29Z","title_canon_sha256":"bc908ab3554c74d7df3a2c817052193312cc2ff09c763e05f7dc58f3a982de6a"},"schema_version":"1.0","source":{"id":"2602.01903","kind":"arxiv","version":2}},"canonical_sha256":"4d9530018ce71fb1d7304199ceeb76cae621c33d9e035bf5e11115468a4c62bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d9530018ce71fb1d7304199ceeb76cae621c33d9e035bf5e11115468a4c62bd","first_computed_at":"2026-06-03T01:05:09.956547Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:09.956547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F48Ees4tNzw1duKw47Ln7kL9MZKayNH7TPKo1qwZ+Yb5rpz1hHOpcBVdvqMv3d+YCsbOFlEv2e5a75Nm/ujZCA==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:09.957025Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.01903","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13a14daa1fad9842498dd25eb6adddd3c61dc1f91807912eec634b5b2f5492af","sha256:14f21e9708cc80e0fba0558b8292acd1af7d23b99fe8731e5984bd94dbf586c1"],"state_sha256":"b4fe9aa2cb060af5e362c43b80d98fa86b62fd030b855a13de6c90dce646bff9"}