{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HHXWOCTFVPOAFC4LAIM2TS4H2G","short_pith_number":"pith:HHXWOCTF","schema_version":"1.0","canonical_sha256":"39ef670a65abdc028b8b0219a9cb87d191124ab77e5f8771d9e3d2b73bb08e9b","source":{"kind":"arxiv","id":"2201.08536","version":1},"attestation_state":"computed","paper":{"title":"Instance-Dependent Confidence and Early Stopping for Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Eric Xia, Koulik Khamaru, Martin J. Wainwright, Michael I. Jordan","submitted_at":"2022-01-21T04:25:35Z","abstract_excerpt":"Various algorithms for reinforcement learning (RL) exhibit dramatic variation in their convergence rates as a function of problem structure. Such problem-dependent behavior is not captured by worst-case analyses and has accordingly inspired a growing effort in obtaining instance-dependent guarantees and deriving instance-optimal algorithms for RL problems. This research has been carried out, however, primarily within the confines of theory, providing guarantees that explain \\textit{ex post} the performance differences observed. A natural next step is to convert these theoretical guarantees int"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2201.08536","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-01-21T04:25:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"578cc133a00b6f8f9ac5c6422a8f3eb0f964dbcc0400468339dee1b02c28bfde","abstract_canon_sha256":"e0f874ceb50e859aee4aade952b2be7c157970cbb300bc9b563ae7f0e58742af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:50:29.431720Z","signature_b64":"HBp6FDHAKWC3Q0QCtCPk8sC/+83R2Kth0iy7tJ+Z6q+NPzRfnYnfPL4DDPz/cxBnFNLzpjXqiksBAJGYEu3vDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39ef670a65abdc028b8b0219a9cb87d191124ab77e5f8771d9e3d2b73bb08e9b","last_reissued_at":"2026-07-05T03:50:29.431299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:50:29.431299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Instance-Dependent Confidence and Early Stopping for Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Eric Xia, Koulik Khamaru, Martin J. Wainwright, Michael I. Jordan","submitted_at":"2022-01-21T04:25:35Z","abstract_excerpt":"Various algorithms for reinforcement learning (RL) exhibit dramatic variation in their convergence rates as a function of problem structure. Such problem-dependent behavior is not captured by worst-case analyses and has accordingly inspired a growing effort in obtaining instance-dependent guarantees and deriving instance-optimal algorithms for RL problems. This research has been carried out, however, primarily within the confines of theory, providing guarantees that explain \\textit{ex post} the performance differences observed. A natural next step is to convert these theoretical guarantees int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.08536","kind":"arxiv","version":1},"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/2201.08536/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2201.08536","created_at":"2026-07-05T03:50:29.431382+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.08536v1","created_at":"2026-07-05T03:50:29.431382+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.08536","created_at":"2026-07-05T03:50:29.431382+00:00"},{"alias_kind":"pith_short_12","alias_value":"HHXWOCTFVPOA","created_at":"2026-07-05T03:50:29.431382+00:00"},{"alias_kind":"pith_short_16","alias_value":"HHXWOCTFVPOAFC4L","created_at":"2026-07-05T03:50:29.431382+00:00"},{"alias_kind":"pith_short_8","alias_value":"HHXWOCTF","created_at":"2026-07-05T03:50:29.431382+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HHXWOCTFVPOAFC4LAIM2TS4H2G","json":"https://pith.science/pith/HHXWOCTFVPOAFC4LAIM2TS4H2G.json","graph_json":"https://pith.science/api/pith-number/HHXWOCTFVPOAFC4LAIM2TS4H2G/graph.json","events_json":"https://pith.science/api/pith-number/HHXWOCTFVPOAFC4LAIM2TS4H2G/events.json","paper":"https://pith.science/paper/HHXWOCTF"},"agent_actions":{"view_html":"https://pith.science/pith/HHXWOCTFVPOAFC4LAIM2TS4H2G","download_json":"https://pith.science/pith/HHXWOCTFVPOAFC4LAIM2TS4H2G.json","view_paper":"https://pith.science/paper/HHXWOCTF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.08536&json=true","fetch_graph":"https://pith.science/api/pith-number/HHXWOCTFVPOAFC4LAIM2TS4H2G/graph.json","fetch_events":"https://pith.science/api/pith-number/HHXWOCTFVPOAFC4LAIM2TS4H2G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HHXWOCTFVPOAFC4LAIM2TS4H2G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HHXWOCTFVPOAFC4LAIM2TS4H2G/action/storage_attestation","attest_author":"https://pith.science/pith/HHXWOCTFVPOAFC4LAIM2TS4H2G/action/author_attestation","sign_citation":"https://pith.science/pith/HHXWOCTFVPOAFC4LAIM2TS4H2G/action/citation_signature","submit_replication":"https://pith.science/pith/HHXWOCTFVPOAFC4LAIM2TS4H2G/action/replication_record"}},"created_at":"2026-07-05T03:50:29.431382+00:00","updated_at":"2026-07-05T03:50:29.431382+00:00"}