{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JYNFBQ5WS4OO6KDFKX5AVDIUYD","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":"005f7061a9180227ce65e340023ff2473c71a6ca1a524449b1c46f03735ed9d4","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-10T18:56:39Z","title_canon_sha256":"aa2371392950a38a029f7f98bafc6cbeccce59aac0df1cf25bd0107be3a565a1"},"schema_version":"1.0","source":{"id":"2509.08933","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.08933","created_at":"2026-05-22T02:04:36Z"},{"alias_kind":"arxiv_version","alias_value":"2509.08933v2","created_at":"2026-05-22T02:04:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08933","created_at":"2026-05-22T02:04:36Z"},{"alias_kind":"pith_short_12","alias_value":"JYNFBQ5WS4OO","created_at":"2026-05-22T02:04:36Z"},{"alias_kind":"pith_short_16","alias_value":"JYNFBQ5WS4OO6KDF","created_at":"2026-05-22T02:04:36Z"},{"alias_kind":"pith_short_8","alias_value":"JYNFBQ5W","created_at":"2026-05-22T02:04:36Z"}],"graph_snapshots":[{"event_id":"sha256:8c9a292f97805ad61595b21830f87574980067e2571514e45d43b1ea3b1110eb","target":"graph","created_at":"2026-05-22T02:04:36Z","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/2509.08933/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of learning the optimal policy in a discounted, infinite-horizon reinforcement learning (RL) setting in the presence of adversarially corrupted rewards. To address this problem, we develop a novel robust variant of the \\(Q\\)-learning algorithm and analyze it under the challenging asynchronous sampling model with time-correlated data. Despite corruption, we prove that the finite-time guarantees of our approach match existing bounds, up to an additive term that scales with the fraction of corrupted samples. We also establish an information-theoretic lower bound, revealing th","authors_text":"Aritra Mitra, Sreejeet Maity","cross_cats":["cs.SY","eess.SY","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-10T18:56:39Z","title":"Corruption-Tolerant Asynchronous Q-Learning with Near-Optimal Rates"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08933","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":"sha256:24e90b8d9af2e9e5dfa32bddd2d3a6b87c3edbe65a9344e24868e164d3732b49","target":"record","created_at":"2026-05-22T02:04:36Z","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":"005f7061a9180227ce65e340023ff2473c71a6ca1a524449b1c46f03735ed9d4","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-10T18:56:39Z","title_canon_sha256":"aa2371392950a38a029f7f98bafc6cbeccce59aac0df1cf25bd0107be3a565a1"},"schema_version":"1.0","source":{"id":"2509.08933","kind":"arxiv","version":2}},"canonical_sha256":"4e1a50c3b6971cef286555fa0a8d14c0c99ed43271277b67810c8236ba8eecda","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4e1a50c3b6971cef286555fa0a8d14c0c99ed43271277b67810c8236ba8eecda","first_computed_at":"2026-05-22T02:04:36.887949Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T02:04:36.887949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"18jNc3jzR8a7LERNZzieScbjWEIrlzsaRyl6g7rjDcoKccdgXOsc6i1jUpZKZi1Kg/LcElCHgnvDQn+DJwkEAA==","signature_status":"signed_v1","signed_at":"2026-05-22T02:04:36.888981Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.08933","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24e90b8d9af2e9e5dfa32bddd2d3a6b87c3edbe65a9344e24868e164d3732b49","sha256:8c9a292f97805ad61595b21830f87574980067e2571514e45d43b1ea3b1110eb"],"state_sha256":"3817eb7f0b53f468b730a134b0bfb527b9e706817252b4fb5753d7f68816d0b4"}