{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:L625PECAXW57P3G7OYEK27F6B6","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":"03649888726816eee673573c7b83b77fe6ec0e1ac80a11e618820cec44fbb53f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T20:33:57Z","title_canon_sha256":"56e09b0bc9898e601c2f9db4a3b7bfd6a1f6ce50f9681a84c718a5fbdaa817f3"},"schema_version":"1.0","source":{"id":"2506.06521","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06521","created_at":"2026-07-05T11:17:51Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06521v1","created_at":"2026-07-05T11:17:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06521","created_at":"2026-07-05T11:17:51Z"},{"alias_kind":"pith_short_12","alias_value":"L625PECAXW57","created_at":"2026-07-05T11:17:51Z"},{"alias_kind":"pith_short_16","alias_value":"L625PECAXW57P3G7","created_at":"2026-07-05T11:17:51Z"},{"alias_kind":"pith_short_8","alias_value":"L625PECA","created_at":"2026-07-05T11:17:51Z"}],"graph_snapshots":[{"event_id":"sha256:d50b8e1ecdea08db1a8de0d53c20d7dcf5dbfcdc8552a3c5a06c5df7fd510bb3","target":"graph","created_at":"2026-07-05T11:17:51Z","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/2506.06521/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the gap-dependent regret bounds for episodic MDPs. We show that the Monotonic Value Propagation (MVP) algorithm achieves a variance-aware gap-dependent regret bound of $$\\tilde{O}\\left(\\left(\\sum_{\\Delta_h(s,a)>0} \\frac{H^2 \\log K \\land \\mathtt{Var}_{\\max}^{\\text{c}}}{\\Delta_h(s,a)} +\\sum_{\\Delta_h(s,a)=0}\\frac{ H^2 \\land \\mathtt{Var}_{\\max}^{\\text{c}}}{\\Delta_{\\mathrm{min}}} + SAH^4 (S \\lor H) \\right) \\log K\\right),$$ where $H$ is the planning horizon, $S$ is the number of states, $A$ is the number of actions, and $K$ is the number of episodes. Here, $\\Delta_h(s,a) =V_h^* (a) - Q_","authors_text":"Maryam Fazel, Runlong Zhou, Shulun Chen, Simon S. Du, Zihan Zhang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T20:33:57Z","title":"Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06521","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":"sha256:8348fbbd43011e0c09393565b7170b85eb5a65866ddd308d444c2b18cb0cb44c","target":"record","created_at":"2026-07-05T11:17:51Z","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":"03649888726816eee673573c7b83b77fe6ec0e1ac80a11e618820cec44fbb53f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T20:33:57Z","title_canon_sha256":"56e09b0bc9898e601c2f9db4a3b7bfd6a1f6ce50f9681a84c718a5fbdaa817f3"},"schema_version":"1.0","source":{"id":"2506.06521","kind":"arxiv","version":1}},"canonical_sha256":"5fb5d79040bdbbf7ecdf7608ad7cbe0faf73eef9a3cb18db5b835148ac0021f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5fb5d79040bdbbf7ecdf7608ad7cbe0faf73eef9a3cb18db5b835148ac0021f3","first_computed_at":"2026-07-05T11:17:51.544267Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:51.544267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4tXMxdTdxRed2XAHb5sE/825lMIXf9yE9SE8fFwGSa9RNRo3gE4y1HR2y73ohlN51FsWxQr3XyXxWw0rAbhMBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:51.544790Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.06521","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8348fbbd43011e0c09393565b7170b85eb5a65866ddd308d444c2b18cb0cb44c","sha256:d50b8e1ecdea08db1a8de0d53c20d7dcf5dbfcdc8552a3c5a06c5df7fd510bb3"],"state_sha256":"7a7a780cef54a84cb4e2f30d314a57b1082a4cfa0939dfdf9d02e593c59b2643"}