{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2D55NG6XDGKQ7MUBUEU54HGW62","short_pith_number":"pith:2D55NG6X","schema_version":"1.0","canonical_sha256":"d0fbd69bd719950fb281a129de1cd6f683d176ced7e35606902d32a32823e22f","source":{"kind":"arxiv","id":"2108.03706","version":3},"attestation_state":"computed","paper":{"title":"Online Bootstrap Inference For Policy Evaluation in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Guang Cheng, Pratik Ramprasad, Will Wei Sun, Yuantong Li, Zhaoran Wang, Zhuoran Yang","submitted_at":"2021-08-08T18:26:35Z","abstract_excerpt":"The recent emergence of reinforcement learning has created a demand for robust statistical inference methods for the parameter estimates computed using these algorithms. Existing methods for statistical inference in online learning are restricted to settings involving independently sampled observations, while existing statistical inference methods in reinforcement learning (RL) are limited to the batch setting. The online bootstrap is a flexible and efficient approach for statistical inference in linear stochastic approximation algorithms, but its efficacy in settings involving Markov noise, s"},"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":"2108.03706","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-08-08T18:26:35Z","cross_cats_sorted":["cs.AI","cs.LG","math.ST","stat.TH"],"title_canon_sha256":"adcdae44b8ecd8f3dfd7c5d6d23f1ecfbc2b73a196bdc674bd8a5e1355a7c54b","abstract_canon_sha256":"de1943cc1ff47b1c2668ebf972501c403361c50cde22840cc8ca8e8e80302b30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:35:37.151038Z","signature_b64":"eW9wER8fVVKu47gPb/6pLPNSsp9Saf1j/JB7uN3fMacqNRPOQdkdFS3o8ovqKAQULFptENyVD5rgg0RIF24fBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0fbd69bd719950fb281a129de1cd6f683d176ced7e35606902d32a32823e22f","last_reissued_at":"2026-07-05T04:35:37.150578Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:35:37.150578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Bootstrap Inference For Policy Evaluation in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Guang Cheng, Pratik Ramprasad, Will Wei Sun, Yuantong Li, Zhaoran Wang, Zhuoran Yang","submitted_at":"2021-08-08T18:26:35Z","abstract_excerpt":"The recent emergence of reinforcement learning has created a demand for robust statistical inference methods for the parameter estimates computed using these algorithms. Existing methods for statistical inference in online learning are restricted to settings involving independently sampled observations, while existing statistical inference methods in reinforcement learning (RL) are limited to the batch setting. The online bootstrap is a flexible and efficient approach for statistical inference in linear stochastic approximation algorithms, but its efficacy in settings involving Markov noise, s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.03706","kind":"arxiv","version":3},"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/2108.03706/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":"2108.03706","created_at":"2026-07-05T04:35:37.150635+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.03706v3","created_at":"2026-07-05T04:35:37.150635+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.03706","created_at":"2026-07-05T04:35:37.150635+00:00"},{"alias_kind":"pith_short_12","alias_value":"2D55NG6XDGKQ","created_at":"2026-07-05T04:35:37.150635+00:00"},{"alias_kind":"pith_short_16","alias_value":"2D55NG6XDGKQ7MUB","created_at":"2026-07-05T04:35:37.150635+00:00"},{"alias_kind":"pith_short_8","alias_value":"2D55NG6X","created_at":"2026-07-05T04:35:37.150635+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/2D55NG6XDGKQ7MUBUEU54HGW62","json":"https://pith.science/pith/2D55NG6XDGKQ7MUBUEU54HGW62.json","graph_json":"https://pith.science/api/pith-number/2D55NG6XDGKQ7MUBUEU54HGW62/graph.json","events_json":"https://pith.science/api/pith-number/2D55NG6XDGKQ7MUBUEU54HGW62/events.json","paper":"https://pith.science/paper/2D55NG6X"},"agent_actions":{"view_html":"https://pith.science/pith/2D55NG6XDGKQ7MUBUEU54HGW62","download_json":"https://pith.science/pith/2D55NG6XDGKQ7MUBUEU54HGW62.json","view_paper":"https://pith.science/paper/2D55NG6X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.03706&json=true","fetch_graph":"https://pith.science/api/pith-number/2D55NG6XDGKQ7MUBUEU54HGW62/graph.json","fetch_events":"https://pith.science/api/pith-number/2D55NG6XDGKQ7MUBUEU54HGW62/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2D55NG6XDGKQ7MUBUEU54HGW62/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2D55NG6XDGKQ7MUBUEU54HGW62/action/storage_attestation","attest_author":"https://pith.science/pith/2D55NG6XDGKQ7MUBUEU54HGW62/action/author_attestation","sign_citation":"https://pith.science/pith/2D55NG6XDGKQ7MUBUEU54HGW62/action/citation_signature","submit_replication":"https://pith.science/pith/2D55NG6XDGKQ7MUBUEU54HGW62/action/replication_record"}},"created_at":"2026-07-05T04:35:37.150635+00:00","updated_at":"2026-07-05T04:35:37.150635+00:00"}