{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5BAJN34OXHAL4UJ52DHOZRCMVB","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":"3a259e78527fcf5283f40d73467b2dcb795ede01b2b0f529c0294a8023bc68cb","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-30T14:54:34Z","title_canon_sha256":"48ec17545061f64651808459c4efc143c4b778423bb1214001c7b6cccdfb03f0"},"schema_version":"1.0","source":{"id":"2606.31769","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.31769","created_at":"2026-07-01T01:18:14Z"},{"alias_kind":"arxiv_version","alias_value":"2606.31769v1","created_at":"2026-07-01T01:18:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31769","created_at":"2026-07-01T01:18:14Z"},{"alias_kind":"pith_short_12","alias_value":"5BAJN34OXHAL","created_at":"2026-07-01T01:18:14Z"},{"alias_kind":"pith_short_16","alias_value":"5BAJN34OXHAL4UJ5","created_at":"2026-07-01T01:18:14Z"},{"alias_kind":"pith_short_8","alias_value":"5BAJN34O","created_at":"2026-07-01T01:18:14Z"}],"graph_snapshots":[{"event_id":"sha256:6ded3cd90208ed263c9269c1fc0b1accd3ce4b51f7d967951b57e180b7e9712d","target":"graph","created_at":"2026-07-01T01:18:14Z","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/2606.31769/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study policy optimization for online episodic tabular Markov decision processes with unknown transition kernels, aiming for best-of-both-worlds guarantees together with data-dependent regret bounds. Recent work (Dann et al., 2023; Li et al., 2026) has shown that policy optimization can adapt to both adversarial and stochastic losses with first-order, second-order, and path-length bounds, but only under known transitions, leaving open whether such data-dependent guarantees are achievable by policy optimization when the transition kernel is unknown. We resolve this by developing a new algorit","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":"2026-06-30T14:54:34Z","title":"Policy Optimization Achieves Data-Dependent Regret Bounds in MDPs with Unknown Transitions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31769","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:c21bae554984b896cd5f754173bd53b676260dc95e2873e671b684b3f9a361f5","target":"record","created_at":"2026-07-01T01:18:14Z","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":"3a259e78527fcf5283f40d73467b2dcb795ede01b2b0f529c0294a8023bc68cb","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-30T14:54:34Z","title_canon_sha256":"48ec17545061f64651808459c4efc143c4b778423bb1214001c7b6cccdfb03f0"},"schema_version":"1.0","source":{"id":"2606.31769","kind":"arxiv","version":1}},"canonical_sha256":"e84096ef8eb9c0be513dd0ceecc44ca85122eda56bc2ac9e492459e017012cb4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e84096ef8eb9c0be513dd0ceecc44ca85122eda56bc2ac9e492459e017012cb4","first_computed_at":"2026-07-01T01:18:14.238041Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:18:14.238041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9w3PlrR+yoEtczbbmeyt+gCX+HcatVfdShSek6qQsoLUMB2JfzqOd78U0uDXZaV/XOVBq4uTgRW5mo2CIzEcAg==","signature_status":"signed_v1","signed_at":"2026-07-01T01:18:14.238549Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.31769","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c21bae554984b896cd5f754173bd53b676260dc95e2873e671b684b3f9a361f5","sha256:6ded3cd90208ed263c9269c1fc0b1accd3ce4b51f7d967951b57e180b7e9712d"],"state_sha256":"3246a24ab5d0526eb35fc43176b158e6a98a256c34a2f81d9b5e10e9e7a3a1ed"}