{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NCBYM3HOLGHTXJIRV5UBBFY7X3","short_pith_number":"pith:NCBYM3HO","schema_version":"1.0","canonical_sha256":"6883866cee598f3ba511af6810971fbef3dcd46f716874004d5cf1ea2bbfb77b","source":{"kind":"arxiv","id":"2302.01333","version":1},"attestation_state":"computed","paper":{"title":"Lower Bounds for Learning in Revealing POMDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Caiming Xiong, Fan Chen, Huan Wang, Song Mei, Yu Bai","submitted_at":"2023-02-02T18:59:30Z","abstract_excerpt":"This paper studies the fundamental limits of reinforcement learning (RL) in the challenging \\emph{partially observable} setting. While it is well-established that learning in Partially Observable Markov Decision Processes (POMDPs) requires exponentially many samples in the worst case, a surge of recent work shows that polynomial sample complexities are achievable under the \\emph{revealing condition} -- A natural condition that requires the observables to reveal some information about the unobserved latent states. However, the fundamental limits for learning in revealing POMDPs are much less un"},"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":"2302.01333","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T18:59:30Z","cross_cats_sorted":["cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"b146ea1eb6ad926b42b784a401e586908ab22f43f8f67883fb4c2614584134f7","abstract_canon_sha256":"4dcc6f19ccdef0bc3dc2834879e120e7fe657b65c8c47818b2fa1f24ad1ddc40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:25.118595Z","signature_b64":"jGY9pK3djW1pDQDJEj8xSEXMOEFxKM99O8VKVdzVCtYyzvZ8rN8QQ8toR+iFyNY1iqan1Eb7Dmc4JdwW+mZNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6883866cee598f3ba511af6810971fbef3dcd46f716874004d5cf1ea2bbfb77b","last_reissued_at":"2026-07-05T05:38:25.118062Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:25.118062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lower Bounds for Learning in Revealing POMDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Caiming Xiong, Fan Chen, Huan Wang, Song Mei, Yu Bai","submitted_at":"2023-02-02T18:59:30Z","abstract_excerpt":"This paper studies the fundamental limits of reinforcement learning (RL) in the challenging \\emph{partially observable} setting. While it is well-established that learning in Partially Observable Markov Decision Processes (POMDPs) requires exponentially many samples in the worst case, a surge of recent work shows that polynomial sample complexities are achievable under the \\emph{revealing condition} -- A natural condition that requires the observables to reveal some information about the unobserved latent states. However, the fundamental limits for learning in revealing POMDPs are much less un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.01333","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/2302.01333/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":"2302.01333","created_at":"2026-07-05T05:38:25.118119+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.01333v1","created_at":"2026-07-05T05:38:25.118119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.01333","created_at":"2026-07-05T05:38:25.118119+00:00"},{"alias_kind":"pith_short_12","alias_value":"NCBYM3HOLGHT","created_at":"2026-07-05T05:38:25.118119+00:00"},{"alias_kind":"pith_short_16","alias_value":"NCBYM3HOLGHTXJIR","created_at":"2026-07-05T05:38:25.118119+00:00"},{"alias_kind":"pith_short_8","alias_value":"NCBYM3HO","created_at":"2026-07-05T05:38:25.118119+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/NCBYM3HOLGHTXJIRV5UBBFY7X3","json":"https://pith.science/pith/NCBYM3HOLGHTXJIRV5UBBFY7X3.json","graph_json":"https://pith.science/api/pith-number/NCBYM3HOLGHTXJIRV5UBBFY7X3/graph.json","events_json":"https://pith.science/api/pith-number/NCBYM3HOLGHTXJIRV5UBBFY7X3/events.json","paper":"https://pith.science/paper/NCBYM3HO"},"agent_actions":{"view_html":"https://pith.science/pith/NCBYM3HOLGHTXJIRV5UBBFY7X3","download_json":"https://pith.science/pith/NCBYM3HOLGHTXJIRV5UBBFY7X3.json","view_paper":"https://pith.science/paper/NCBYM3HO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.01333&json=true","fetch_graph":"https://pith.science/api/pith-number/NCBYM3HOLGHTXJIRV5UBBFY7X3/graph.json","fetch_events":"https://pith.science/api/pith-number/NCBYM3HOLGHTXJIRV5UBBFY7X3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NCBYM3HOLGHTXJIRV5UBBFY7X3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NCBYM3HOLGHTXJIRV5UBBFY7X3/action/storage_attestation","attest_author":"https://pith.science/pith/NCBYM3HOLGHTXJIRV5UBBFY7X3/action/author_attestation","sign_citation":"https://pith.science/pith/NCBYM3HOLGHTXJIRV5UBBFY7X3/action/citation_signature","submit_replication":"https://pith.science/pith/NCBYM3HOLGHTXJIRV5UBBFY7X3/action/replication_record"}},"created_at":"2026-07-05T05:38:25.118119+00:00","updated_at":"2026-07-05T05:38:25.118119+00:00"}