{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:D26ZTUJYDZK636ZMPBRXEHDKPN","short_pith_number":"pith:D26ZTUJY","canonical_record":{"source":{"id":"2602.16274","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-18T08:47:07Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"14cebc80d9c8b1d4ee8118afa2dbdcf352d29d05efc507f2a8b61e499244cfb4","abstract_canon_sha256":"5a795a1f0da2669b865991759010c00e455ba1edf72d11ac63760ab8b8311789"},"schema_version":"1.0"},"canonical_sha256":"1ebd99d1381e55edfb2c7863721c6a7b5f360e1058ec5d7371e6cede0a7ef068","source":{"kind":"arxiv","id":"2602.16274","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.16274","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"arxiv_version","alias_value":"2602.16274v2","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.16274","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"pith_short_12","alias_value":"D26ZTUJYDZK6","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"pith_short_16","alias_value":"D26ZTUJYDZK636ZM","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"pith_short_8","alias_value":"D26ZTUJY","created_at":"2026-05-20T00:00:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:D26ZTUJYDZK636ZMPBRXEHDKPN","target":"record","payload":{"canonical_record":{"source":{"id":"2602.16274","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-18T08:47:07Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"14cebc80d9c8b1d4ee8118afa2dbdcf352d29d05efc507f2a8b61e499244cfb4","abstract_canon_sha256":"5a795a1f0da2669b865991759010c00e455ba1edf72d11ac63760ab8b8311789"},"schema_version":"1.0"},"canonical_sha256":"1ebd99d1381e55edfb2c7863721c6a7b5f360e1058ec5d7371e6cede0a7ef068","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:34.699025Z","signature_b64":"8rzXM/sLZVcH54gGPseg5eIU42zGs7L3k61UzDRoJyAI7YHJctQPTcAiZcWkwGOmoqtoCKzEF6z4NUoGj2GADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ebd99d1381e55edfb2c7863721c6a7b5f360e1058ec5d7371e6cede0a7ef068","last_reissued_at":"2026-05-20T00:00:34.698272Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:34.698272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.16274","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":"2026-05-20T00:00:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9kUrKykQnEiNpDQfe7gQ4nqT1ixD+kQSSrT4QZfE9h8ZntPUhowf3QH8UtTnmnIXhoZgJGT37YYyssyj9IWSDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T11:21:25.484225Z"},"content_sha256":"672d42a51b03280038c33b453cb3a8f3b9de7f7b2a24333fce864e50f4669e1e","schema_version":"1.0","event_id":"sha256:672d42a51b03280038c33b453cb3a8f3b9de7f7b2a24333fce864e50f4669e1e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:D26ZTUJYDZK636ZMPBRXEHDKPN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Regret and Sample Complexity of Online Q-Learning via Concentration of Stochastic Approximation with Time-Inhomogeneous Markov Chains","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Eric Moulines, Nicholas Bambos, Rahul Singh, Siddharth Chandak, Vivek S. Borkar","submitted_at":"2026-02-18T08:47:07Z","abstract_excerpt":"We present the first regret bound for classical online Q-learning in infinite-horizon discounted Markov decision processes (MDPs), without relying on optimism or bonus terms. We first analyze Boltzmann Q-learning with decaying temperature and show that its regret depends critically on the suboptimality gap of the MDP: for sufficiently large gaps, the regret is sublinear, while for small gaps it deteriorates and can approach linear growth. To address this limitation, we study a Smoothed $\\epsilon_n$-Greedy exploration scheme that combines $\\epsilon_n$-greedy and Boltzmann exploration, for which"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.16274","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/2602.16274/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":"2026-05-20T00:00:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oia6ASXlzIN79yBCAbDh+jVxxksC1bdvCWn9Dd7WEcbDyHLtOuX69g0c0bXVTrEnwFJZFzDjNLKnPAXnYN1mDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T11:21:25.484642Z"},"content_sha256":"0e8c8b255c5560722b730157bd87c6b3e2847615ae8df00a2f3a2665829077a2","schema_version":"1.0","event_id":"sha256:0e8c8b255c5560722b730157bd87c6b3e2847615ae8df00a2f3a2665829077a2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D26ZTUJYDZK636ZMPBRXEHDKPN/bundle.json","state_url":"https://pith.science/pith/D26ZTUJYDZK636ZMPBRXEHDKPN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D26ZTUJYDZK636ZMPBRXEHDKPN/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":"2026-06-04T11:21:25Z","links":{"resolver":"https://pith.science/pith/D26ZTUJYDZK636ZMPBRXEHDKPN","bundle":"https://pith.science/pith/D26ZTUJYDZK636ZMPBRXEHDKPN/bundle.json","state":"https://pith.science/pith/D26ZTUJYDZK636ZMPBRXEHDKPN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D26ZTUJYDZK636ZMPBRXEHDKPN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:D26ZTUJYDZK636ZMPBRXEHDKPN","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":"5a795a1f0da2669b865991759010c00e455ba1edf72d11ac63760ab8b8311789","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-18T08:47:07Z","title_canon_sha256":"14cebc80d9c8b1d4ee8118afa2dbdcf352d29d05efc507f2a8b61e499244cfb4"},"schema_version":"1.0","source":{"id":"2602.16274","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.16274","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"arxiv_version","alias_value":"2602.16274v2","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.16274","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"pith_short_12","alias_value":"D26ZTUJYDZK6","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"pith_short_16","alias_value":"D26ZTUJYDZK636ZM","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"pith_short_8","alias_value":"D26ZTUJY","created_at":"2026-05-20T00:00:34Z"}],"graph_snapshots":[{"event_id":"sha256:0e8c8b255c5560722b730157bd87c6b3e2847615ae8df00a2f3a2665829077a2","target":"graph","created_at":"2026-05-20T00:00:34Z","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/2602.16274/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present the first regret bound for classical online Q-learning in infinite-horizon discounted Markov decision processes (MDPs), without relying on optimism or bonus terms. We first analyze Boltzmann Q-learning with decaying temperature and show that its regret depends critically on the suboptimality gap of the MDP: for sufficiently large gaps, the regret is sublinear, while for small gaps it deteriorates and can approach linear growth. To address this limitation, we study a Smoothed $\\epsilon_n$-Greedy exploration scheme that combines $\\epsilon_n$-greedy and Boltzmann exploration, for which","authors_text":"Eric Moulines, Nicholas Bambos, Rahul Singh, Siddharth Chandak, Vivek S. Borkar","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-18T08:47:07Z","title":"Regret and Sample Complexity of Online Q-Learning via Concentration of Stochastic Approximation with Time-Inhomogeneous Markov Chains"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.16274","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":"sha256:672d42a51b03280038c33b453cb3a8f3b9de7f7b2a24333fce864e50f4669e1e","target":"record","created_at":"2026-05-20T00:00:34Z","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":"5a795a1f0da2669b865991759010c00e455ba1edf72d11ac63760ab8b8311789","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-18T08:47:07Z","title_canon_sha256":"14cebc80d9c8b1d4ee8118afa2dbdcf352d29d05efc507f2a8b61e499244cfb4"},"schema_version":"1.0","source":{"id":"2602.16274","kind":"arxiv","version":2}},"canonical_sha256":"1ebd99d1381e55edfb2c7863721c6a7b5f360e1058ec5d7371e6cede0a7ef068","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ebd99d1381e55edfb2c7863721c6a7b5f360e1058ec5d7371e6cede0a7ef068","first_computed_at":"2026-05-20T00:00:34.698272Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:34.698272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8rzXM/sLZVcH54gGPseg5eIU42zGs7L3k61UzDRoJyAI7YHJctQPTcAiZcWkwGOmoqtoCKzEF6z4NUoGj2GADA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:34.699025Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.16274","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:672d42a51b03280038c33b453cb3a8f3b9de7f7b2a24333fce864e50f4669e1e","sha256:0e8c8b255c5560722b730157bd87c6b3e2847615ae8df00a2f3a2665829077a2"],"state_sha256":"8a1d24c7a030cf460d221b88a2d391493c9c638bbafb1245d977ad3a5d3546bf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GZuyncsS2p+ZFkjQox33W2VjXWguJ/Tifn50i6kTgGdX6B9mYoQFb0UT604mEZsooLKY9vYqANZobYKeD5ItBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T11:21:25.486764Z","bundle_sha256":"f7e336e916b7e5f7185b022a5d833d13fbb8cab83c8f135c66830eb69ddf753c"}}