{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WYYWY7YWS7IGPZP542MMQIUQ6F","short_pith_number":"pith:WYYWY7YW","schema_version":"1.0","canonical_sha256":"b6316c7f1697d067e5fde698c82290f17585b2ce284aeb8de9c4e86d8c77ca56","source":{"kind":"arxiv","id":"2311.12244","version":3},"attestation_state":"computed","paper":{"title":"Provable Representation with Efficient Planning for Partial Observable Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Dai, Chenjun Xiao, Dale Schuurmans, Hongming Zhang, Tongzheng Ren","submitted_at":"2023-11-20T23:56:58Z","abstract_excerpt":"In most real-world reinforcement learning applications, state information is only partially observable, which breaks the Markov decision process assumption and leads to inferior performance for algorithms that conflate observations with state. Partially Observable Markov Decision Processes (POMDPs), on the other hand, provide a general framework that allows for partial observability to be accounted for in learning, exploration and planning, but presents significant computational and statistical challenges. To address these difficulties, we develop a representation-based perspective that leads "},"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":"2311.12244","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-20T23:56:58Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"011c4d062b694918d689acfaf21487467a47e1429cd2df23fef0c3f55bc5bf74","abstract_canon_sha256":"81f4a48ef37e68411029320ff643a0b809dd862dfa984c1b5bde1d437d032517"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:06.168231Z","signature_b64":"wizpGUMDqrHuiK07OYvJiiZn1A+E4gJtYFpuqsx5efvnxr7uMnRiC5qThTkRQ3O591TopK1Z0ZgrnFeBjsaTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6316c7f1697d067e5fde698c82290f17585b2ce284aeb8de9c4e86d8c77ca56","last_reissued_at":"2026-07-05T08:30:06.167739Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:06.167739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provable Representation with Efficient Planning for Partial Observable Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Dai, Chenjun Xiao, Dale Schuurmans, Hongming Zhang, Tongzheng Ren","submitted_at":"2023-11-20T23:56:58Z","abstract_excerpt":"In most real-world reinforcement learning applications, state information is only partially observable, which breaks the Markov decision process assumption and leads to inferior performance for algorithms that conflate observations with state. Partially Observable Markov Decision Processes (POMDPs), on the other hand, provide a general framework that allows for partial observability to be accounted for in learning, exploration and planning, but presents significant computational and statistical challenges. To address these difficulties, we develop a representation-based perspective that leads "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.12244","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/2311.12244/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":"2311.12244","created_at":"2026-07-05T08:30:06.167794+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.12244v3","created_at":"2026-07-05T08:30:06.167794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.12244","created_at":"2026-07-05T08:30:06.167794+00:00"},{"alias_kind":"pith_short_12","alias_value":"WYYWY7YWS7IG","created_at":"2026-07-05T08:30:06.167794+00:00"},{"alias_kind":"pith_short_16","alias_value":"WYYWY7YWS7IGPZP5","created_at":"2026-07-05T08:30:06.167794+00:00"},{"alias_kind":"pith_short_8","alias_value":"WYYWY7YW","created_at":"2026-07-05T08:30:06.167794+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20408","citing_title":"Spectral Souping: A Unified Framework for Online Preference Alignment","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WYYWY7YWS7IGPZP542MMQIUQ6F","json":"https://pith.science/pith/WYYWY7YWS7IGPZP542MMQIUQ6F.json","graph_json":"https://pith.science/api/pith-number/WYYWY7YWS7IGPZP542MMQIUQ6F/graph.json","events_json":"https://pith.science/api/pith-number/WYYWY7YWS7IGPZP542MMQIUQ6F/events.json","paper":"https://pith.science/paper/WYYWY7YW"},"agent_actions":{"view_html":"https://pith.science/pith/WYYWY7YWS7IGPZP542MMQIUQ6F","download_json":"https://pith.science/pith/WYYWY7YWS7IGPZP542MMQIUQ6F.json","view_paper":"https://pith.science/paper/WYYWY7YW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.12244&json=true","fetch_graph":"https://pith.science/api/pith-number/WYYWY7YWS7IGPZP542MMQIUQ6F/graph.json","fetch_events":"https://pith.science/api/pith-number/WYYWY7YWS7IGPZP542MMQIUQ6F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WYYWY7YWS7IGPZP542MMQIUQ6F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WYYWY7YWS7IGPZP542MMQIUQ6F/action/storage_attestation","attest_author":"https://pith.science/pith/WYYWY7YWS7IGPZP542MMQIUQ6F/action/author_attestation","sign_citation":"https://pith.science/pith/WYYWY7YWS7IGPZP542MMQIUQ6F/action/citation_signature","submit_replication":"https://pith.science/pith/WYYWY7YWS7IGPZP542MMQIUQ6F/action/replication_record"}},"created_at":"2026-07-05T08:30:06.167794+00:00","updated_at":"2026-07-05T08:30:06.167794+00:00"}