{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DIQJ7VWGI5ZFURS6IIJCGODEFH","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":"ee1abdbca0bb20c9454c2de4e3ed360f94287af4007f85a3c4c843becd4bcb15","cross_cats_sorted":["cs.DS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-02-06T20:01:59Z","title_canon_sha256":"7896ced173e6a3d004eb9fc23958b750c92960a50701eb41c356767fea5d8bda"},"schema_version":"1.0","source":{"id":"2502.04477","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04477","created_at":"2026-07-05T11:20:50Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04477v2","created_at":"2026-07-05T11:20:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04477","created_at":"2026-07-05T11:20:50Z"},{"alias_kind":"pith_short_12","alias_value":"DIQJ7VWGI5ZF","created_at":"2026-07-05T11:20:50Z"},{"alias_kind":"pith_short_16","alias_value":"DIQJ7VWGI5ZFURS6","created_at":"2026-07-05T11:20:50Z"},{"alias_kind":"pith_short_8","alias_value":"DIQJ7VWG","created_at":"2026-07-05T11:20:50Z"}],"graph_snapshots":[{"event_id":"sha256:30e892762968f1a20a1c9ab20f083955b5d4b4eadbe3f04eb798ed3583972060","target":"graph","created_at":"2026-07-05T11:20:50Z","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/2502.04477/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study a new model-free algorithm to compute $\\varepsilon$-optimal policies for average reward Markov decision processes, in the weakly communicating case. Given a generative model, our procedure combines a recursive sampling technique with Halpern's anchored iteration, and computes an $\\varepsilon$-optimal policy with sample and time complexity $\\widetilde{O}(|\\mathcal{S}||\\mathcal{A}|\\|h^*\\|_{\\text{sp}}^{2}/\\varepsilon^{2})$ both in high probability and in expectation. To our knowledge, this is the best complexity among model-free algorithms, matching the known lower bound up to a factor $","authors_text":"Jongmin Lee, Mario Bravo, Roberto Cominetti","cross_cats":["cs.DS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-02-06T20:01:59Z","title":"Near-Optimal Sample Complexity for MDPs via Anchoring"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04477","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":"sha256:8bd20ad01d41b68bdd05da171096650232d3e56aabbc6fbab2bdf4ce176be170","target":"record","created_at":"2026-07-05T11:20:50Z","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":"ee1abdbca0bb20c9454c2de4e3ed360f94287af4007f85a3c4c843becd4bcb15","cross_cats_sorted":["cs.DS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-02-06T20:01:59Z","title_canon_sha256":"7896ced173e6a3d004eb9fc23958b750c92960a50701eb41c356767fea5d8bda"},"schema_version":"1.0","source":{"id":"2502.04477","kind":"arxiv","version":2}},"canonical_sha256":"1a209fd6c647725a465e421223386429fc44c9f59c3c7bd036d39a8ced730440","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a209fd6c647725a465e421223386429fc44c9f59c3c7bd036d39a8ced730440","first_computed_at":"2026-07-05T11:20:50.376780Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:50.376780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ONlUJPhkCDrCmBHuxibYcMt2IprhFPT/ZpN1J3Fe5Ogw/+/B8YBtqpdPjf84PwDK/6pYtYRcrw8RT11XcxrcBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:50.377250Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.04477","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8bd20ad01d41b68bdd05da171096650232d3e56aabbc6fbab2bdf4ce176be170","sha256:30e892762968f1a20a1c9ab20f083955b5d4b4eadbe3f04eb798ed3583972060"],"state_sha256":"dc29b59dd01b9130b78eb391646a5b212d2f121f782246ca5d82b7f19bd36012"}