{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Z44YQVWMTPR4T5B7LVMJV7L2A4","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":"cf2d1fb02421060f9b90a75677cb9b841c532a4fce483da2f6c56217df4d9e1f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-22T07:42:19Z","title_canon_sha256":"9240af97622163e9f6368136aee63c16ac45d63038fc9def3f281023af826c02"},"schema_version":"1.0","source":{"id":"2607.19854","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.19854","created_at":"2026-07-23T01:24:03Z"},{"alias_kind":"arxiv_version","alias_value":"2607.19854v1","created_at":"2026-07-23T01:24:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19854","created_at":"2026-07-23T01:24:03Z"},{"alias_kind":"pith_short_12","alias_value":"Z44YQVWMTPR4","created_at":"2026-07-23T01:24:03Z"},{"alias_kind":"pith_short_16","alias_value":"Z44YQVWMTPR4T5B7","created_at":"2026-07-23T01:24:03Z"},{"alias_kind":"pith_short_8","alias_value":"Z44YQVWM","created_at":"2026-07-23T01:24:03Z"}],"graph_snapshots":[{"event_id":"sha256:8016a3f1c2d482e86ad0950009abde0809d48f869f8e186039a37a820fc2bac1","target":"graph","created_at":"2026-07-23T01:24:03Z","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/2607.19854/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study horizon-free regret minimization for finite-horizon time-homogeneous tabular Markov decision processes with $S$ states, $A$ actions, horizon $H$, and per-trajectory total reward bounded by $1$.\n  We propose a new algorithm and prove a regret upper bound \\[\\tilde O(\\sqrt{SAK}+S^8A^3)\\] with failure probability $\\delta$, where $K$ is the number of episodes and $\\tilde O(\\cdot)$ hides $\\mathsf{poly}\\log(S,A,K,1/\\delta)$.\n  Thus, the regret is $H$-free and asymptotically optimal, matching the contextual-bandit lower bound $\\Omega(\\sqrt{SAK})$ up to logarithmic factors. This completely rem","authors_text":"Maryam Fazel, Runlong Zhou, 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":"2026-07-22T07:42:19Z","title":"Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19854","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:bf36ac7af886af1060bb1a46857a754846dcec25b3d2b355a7261d6dac791f17","target":"record","created_at":"2026-07-23T01:24:03Z","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":"cf2d1fb02421060f9b90a75677cb9b841c532a4fce483da2f6c56217df4d9e1f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-22T07:42:19Z","title_canon_sha256":"9240af97622163e9f6368136aee63c16ac45d63038fc9def3f281023af826c02"},"schema_version":"1.0","source":{"id":"2607.19854","kind":"arxiv","version":1}},"canonical_sha256":"cf398856cc9be3c9f43f5d589afd7a071f665e3ac3a34c0b48403c3a4cb468fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf398856cc9be3c9f43f5d589afd7a071f665e3ac3a34c0b48403c3a4cb468fc","first_computed_at":"2026-07-23T01:24:03.765830Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-23T01:24:03.765830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EPcLy4zDCoSfPfjdynNtBupmRXQHqsk+QwhY7+ya+BsFQPf9VOLkRMc9W8Q64aoa/Hh3UOsIcPla1LC5NBm+Cg==","signature_status":"signed_v1","signed_at":"2026-07-23T01:24:03.766672Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.19854","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf36ac7af886af1060bb1a46857a754846dcec25b3d2b355a7261d6dac791f17","sha256:8016a3f1c2d482e86ad0950009abde0809d48f869f8e186039a37a820fc2bac1"],"state_sha256":"219b04483e10aadfca02b5af02ada84c4586bf5cbc36d412bfe780447e005528"}