{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YUXHZBDOVSZF34RUXTCZFKPFEW","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":"54feba04233bc744cb811e2f7d5fe703dcf0a35a4777b766a11065e7dbeaaaca","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-19T16:08:28Z","title_canon_sha256":"64faebe0000572f77a290e8f11b4100f30bc8dc9de7e1a09bffbb7681dfd54c8"},"schema_version":"1.0","source":{"id":"2204.08967","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.08967","created_at":"2026-07-05T04:26:23Z"},{"alias_kind":"arxiv_version","alias_value":"2204.08967v2","created_at":"2026-07-05T04:26:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.08967","created_at":"2026-07-05T04:26:23Z"},{"alias_kind":"pith_short_12","alias_value":"YUXHZBDOVSZF","created_at":"2026-07-05T04:26:23Z"},{"alias_kind":"pith_short_16","alias_value":"YUXHZBDOVSZF34RU","created_at":"2026-07-05T04:26:23Z"},{"alias_kind":"pith_short_8","alias_value":"YUXHZBDO","created_at":"2026-07-05T04:26:23Z"}],"graph_snapshots":[{"event_id":"sha256:f63fd9edfdc78b93f1e427b85cb6add455c3522da6bcb27edf2717b45471d0a3","target":"graph","created_at":"2026-07-05T04:26:23Z","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/2204.08967/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Applications of Reinforcement Learning (RL), in which agents learn to make a sequence of decisions despite lacking complete information about the latent states of the controlled system, that is, they act under partial observability of the states, are ubiquitous. Partially observable RL can be notoriously difficult -- well-known information-theoretic results show that learning partially observable Markov decision processes (POMDPs) requires an exponential number of samples in the worst case. Yet, this does not rule out the existence of large subclasses of POMDPs over which learning is tractable","authors_text":"Alan Chung, Chi Jin, Csaba Szepesv\\'ari, Qinghua Liu","cross_cats":["cs.AI","cs.SY","eess.SY","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-19T16:08:28Z","title":"When Is Partially Observable Reinforcement Learning Not Scary?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.08967","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":"sha256:52156fc712ab63d706b10889d817b343ab07e90df6ff38af0759365d7f30b059","target":"record","created_at":"2026-07-05T04:26:23Z","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":"54feba04233bc744cb811e2f7d5fe703dcf0a35a4777b766a11065e7dbeaaaca","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-19T16:08:28Z","title_canon_sha256":"64faebe0000572f77a290e8f11b4100f30bc8dc9de7e1a09bffbb7681dfd54c8"},"schema_version":"1.0","source":{"id":"2204.08967","kind":"arxiv","version":2}},"canonical_sha256":"c52e7c846eacb25df234bcc592a9e5258163eca6505c7006926f3a4419f3e6fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c52e7c846eacb25df234bcc592a9e5258163eca6505c7006926f3a4419f3e6fa","first_computed_at":"2026-07-05T04:26:23.372349Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:26:23.372349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AQYPdnzauwKg0Q/m3ddSBiT7HBuli9XcZbf1fP6dsx7edSbPGE1B7NA8SgIUkIi1z7ayMSA22LW9Dh6odob1AA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:26:23.372805Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.08967","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52156fc712ab63d706b10889d817b343ab07e90df6ff38af0759365d7f30b059","sha256:f63fd9edfdc78b93f1e427b85cb6add455c3522da6bcb27edf2717b45471d0a3"],"state_sha256":"3b42349c2614272caf3bf2e9fca531e2f4dddb308974a729a09cbc359a27f3b3"}