{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NCBYM3HOLGHTXJIRV5UBBFY7X3","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":"4dcc6f19ccdef0bc3dc2834879e120e7fe657b65c8c47818b2fa1f24ad1ddc40","cross_cats_sorted":["cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T18:59:30Z","title_canon_sha256":"b146ea1eb6ad926b42b784a401e586908ab22f43f8f67883fb4c2614584134f7"},"schema_version":"1.0","source":{"id":"2302.01333","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.01333","created_at":"2026-07-05T05:38:25Z"},{"alias_kind":"arxiv_version","alias_value":"2302.01333v1","created_at":"2026-07-05T05:38:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.01333","created_at":"2026-07-05T05:38:25Z"},{"alias_kind":"pith_short_12","alias_value":"NCBYM3HOLGHT","created_at":"2026-07-05T05:38:25Z"},{"alias_kind":"pith_short_16","alias_value":"NCBYM3HOLGHTXJIR","created_at":"2026-07-05T05:38:25Z"},{"alias_kind":"pith_short_8","alias_value":"NCBYM3HO","created_at":"2026-07-05T05:38:25Z"}],"graph_snapshots":[{"event_id":"sha256:7e19c7bb8b9992d93e209c69b825b0568d2ff10ae0b849124e00e8f26ad28390","target":"graph","created_at":"2026-07-05T05:38:25Z","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/2302.01333/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Caiming Xiong, Fan Chen, Huan Wang, Song Mei, Yu Bai","cross_cats":["cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T18:59:30Z","title":"Lower Bounds for Learning in Revealing POMDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.01333","kind":"arxiv","version":1},"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":"sha256:40d05a31a51b5048a6080e7065ce63eb5f04d97f8bd5cfdd52fe62bc587674d7","target":"record","created_at":"2026-07-05T05:38:25Z","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":"4dcc6f19ccdef0bc3dc2834879e120e7fe657b65c8c47818b2fa1f24ad1ddc40","cross_cats_sorted":["cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T18:59:30Z","title_canon_sha256":"b146ea1eb6ad926b42b784a401e586908ab22f43f8f67883fb4c2614584134f7"},"schema_version":"1.0","source":{"id":"2302.01333","kind":"arxiv","version":1}},"canonical_sha256":"6883866cee598f3ba511af6810971fbef3dcd46f716874004d5cf1ea2bbfb77b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6883866cee598f3ba511af6810971fbef3dcd46f716874004d5cf1ea2bbfb77b","first_computed_at":"2026-07-05T05:38:25.118062Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:38:25.118062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jGY9pK3djW1pDQDJEj8xSEXMOEFxKM99O8VKVdzVCtYyzvZ8rN8QQ8toR+iFyNY1iqan1Eb7Dmc4JdwW+mZNDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:38:25.118595Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.01333","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40d05a31a51b5048a6080e7065ce63eb5f04d97f8bd5cfdd52fe62bc587674d7","sha256:7e19c7bb8b9992d93e209c69b825b0568d2ff10ae0b849124e00e8f26ad28390"],"state_sha256":"2766f973bcd4b9cb1411f932d9f73397a7e02ffaca4c924c747929af27ef3467"}