{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:T7RUDNGAWLKXEL66XMEOSZQKGR","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":"a35440902201cd5fc51176f3f947cc7372ae423fe764d19665f41320c7e5b358","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":"2022-05-26T16:34:46Z","title_canon_sha256":"ec08d15d08d41f1c8485a704dd2cfcb075f57d504ac62df4e73f6a05914e1f75"},"schema_version":"1.0","source":{"id":"2205.13476","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.13476","created_at":"2026-07-05T08:02:41Z"},{"alias_kind":"arxiv_version","alias_value":"2205.13476v2","created_at":"2026-07-05T08:02:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.13476","created_at":"2026-07-05T08:02:41Z"},{"alias_kind":"pith_short_12","alias_value":"T7RUDNGAWLKX","created_at":"2026-07-05T08:02:41Z"},{"alias_kind":"pith_short_16","alias_value":"T7RUDNGAWLKXEL66","created_at":"2026-07-05T08:02:41Z"},{"alias_kind":"pith_short_8","alias_value":"T7RUDNGA","created_at":"2026-07-05T08:02:41Z"}],"graph_snapshots":[{"event_id":"sha256:4183a81c50ffdbad7b2051dc5d7330cc24f6464d80f1a53e13406b61cbc95394","target":"graph","created_at":"2026-07-05T08:02:41Z","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/2205.13476/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning in partially observed Markov decision processes (POMDPs) faces two challenges. (i) It often takes the full history to predict the future, which induces a sample complexity that scales exponentially with the horizon. (ii) The observation and state spaces are often continuous, which induces a sample complexity that scales exponentially with the extrinsic dimension. Addressing such challenges requires learning a minimal but sufficient representation of the observation and state histories by exploiting the structure of the POMDP.\n  To this end, we propose a reinforcement lea","authors_text":"Lingxiao Wang, Qi Cai, Zhaoran Wang, Zhuoran Yang","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":"2022-05-26T16:34:46Z","title":"Embed to Control Partially Observed Systems: Representation Learning with Provable Sample Efficiency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.13476","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:d995ae1fd96385d43967124d5a3069250312f5f2a0b311e2726da4658fa77452","target":"record","created_at":"2026-07-05T08:02:41Z","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":"a35440902201cd5fc51176f3f947cc7372ae423fe764d19665f41320c7e5b358","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":"2022-05-26T16:34:46Z","title_canon_sha256":"ec08d15d08d41f1c8485a704dd2cfcb075f57d504ac62df4e73f6a05914e1f75"},"schema_version":"1.0","source":{"id":"2205.13476","kind":"arxiv","version":2}},"canonical_sha256":"9fe341b4c0b2d5722fdebb08e9660a34439944ea06079d4f24957ad724e338f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9fe341b4c0b2d5722fdebb08e9660a34439944ea06079d4f24957ad724e338f6","first_computed_at":"2026-07-05T08:02:41.124486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:41.124486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j8llOUcy+cQoxmuBBip0HuSP8rsI2nNbTBLDLArlj8BgC3bf3I+z7zyW6R0fWjYBqnhRDZwukg9HOi+bDznaDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:41.124891Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.13476","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d995ae1fd96385d43967124d5a3069250312f5f2a0b311e2726da4658fa77452","sha256:4183a81c50ffdbad7b2051dc5d7330cc24f6464d80f1a53e13406b61cbc95394"],"state_sha256":"b63375960b802eef160435058a2df4098e0fcd51113cb132c8ce48cbdeb7faf6"}