{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DIQJ7VWGI5ZFURS6IIJCGODEFH","short_pith_number":"pith:DIQJ7VWG","canonical_record":{"source":{"id":"2502.04477","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-02-06T20:01:59Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"7896ced173e6a3d004eb9fc23958b750c92960a50701eb41c356767fea5d8bda","abstract_canon_sha256":"ee1abdbca0bb20c9454c2de4e3ed360f94287af4007f85a3c4c843becd4bcb15"},"schema_version":"1.0"},"canonical_sha256":"1a209fd6c647725a465e421223386429fc44c9f59c3c7bd036d39a8ced730440","source":{"kind":"arxiv","id":"2502.04477","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DIQJ7VWGI5ZFURS6IIJCGODEFH","target":"record","payload":{"canonical_record":{"source":{"id":"2502.04477","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-02-06T20:01:59Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"7896ced173e6a3d004eb9fc23958b750c92960a50701eb41c356767fea5d8bda","abstract_canon_sha256":"ee1abdbca0bb20c9454c2de4e3ed360f94287af4007f85a3c4c843becd4bcb15"},"schema_version":"1.0"},"canonical_sha256":"1a209fd6c647725a465e421223386429fc44c9f59c3c7bd036d39a8ced730440","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:50.377250Z","signature_b64":"ONlUJPhkCDrCmBHuxibYcMt2IprhFPT/ZpN1J3Fe5Ogw/+/B8YBtqpdPjf84PwDK/6pYtYRcrw8RT11XcxrcBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a209fd6c647725a465e421223386429fc44c9f59c3c7bd036d39a8ced730440","last_reissued_at":"2026-07-05T11:20:50.376780Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:50.376780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.04477","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:20:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aflJafQPWzJdgw590KDn9Z6/uLyGnbphA3EiZX3tMtQ0lVeKIOfpkHg5NIEG/ISo3v+R/MKEOfCwQTjNOv3tBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:06:15.675482Z"},"content_sha256":"8bd20ad01d41b68bdd05da171096650232d3e56aabbc6fbab2bdf4ce176be170","schema_version":"1.0","event_id":"sha256:8bd20ad01d41b68bdd05da171096650232d3e56aabbc6fbab2bdf4ce176be170"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DIQJ7VWGI5ZFURS6IIJCGODEFH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Near-Optimal Sample Complexity for MDPs via Anchoring","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"math.OC","authors_text":"Jongmin Lee, Mario Bravo, Roberto Cominetti","submitted_at":"2025-02-06T20:01:59Z","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 $"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04477","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.04477/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:20:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rjYHlQ6USHWHM7AI6Jymq7pKzrOfwzmPUZw7/2GhLthsTe2pEjQcF8ooRFdcQ5a5E2/DO1rmXDi95R4k+avuDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:06:15.676369Z"},"content_sha256":"30e892762968f1a20a1c9ab20f083955b5d4b4eadbe3f04eb798ed3583972060","schema_version":"1.0","event_id":"sha256:30e892762968f1a20a1c9ab20f083955b5d4b4eadbe3f04eb798ed3583972060"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DIQJ7VWGI5ZFURS6IIJCGODEFH/bundle.json","state_url":"https://pith.science/pith/DIQJ7VWGI5ZFURS6IIJCGODEFH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DIQJ7VWGI5ZFURS6IIJCGODEFH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T08:06:15Z","links":{"resolver":"https://pith.science/pith/DIQJ7VWGI5ZFURS6IIJCGODEFH","bundle":"https://pith.science/pith/DIQJ7VWGI5ZFURS6IIJCGODEFH/bundle.json","state":"https://pith.science/pith/DIQJ7VWGI5ZFURS6IIJCGODEFH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DIQJ7VWGI5ZFURS6IIJCGODEFH/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PYeRNJognfGM8V5MD/YQml3/NKIR0Skd0mjf8rypFqK/VQCgWfoqY4PD0t3zYnaDm2CiLAYeOybMzmPcPQ6eDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T08:06:15.681790Z","bundle_sha256":"d03d7e2caa2a990df5ca411a6b88f343cd1d5f807ebd4ae2a7c4b4257a63f90c"}}