{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:WYN2UXNGBCTKYZJQPGCLUHM6XC","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":"9cf5cf56ae82bc9b9b5f6ab545c32a362b496e45b767eeabaad5a996b3a0f603","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-10-17T18:30:30Z","title_canon_sha256":"e0fe5c6d2bccc47c5a2c945c9c1e9a1bcc5f2b3979200d73bc320ded94ad5951"},"schema_version":"1.0","source":{"id":"2010.08843","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.08843","created_at":"2026-07-05T03:11:26Z"},{"alias_kind":"arxiv_version","alias_value":"2010.08843v2","created_at":"2026-07-05T03:11:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.08843","created_at":"2026-07-05T03:11:26Z"},{"alias_kind":"pith_short_12","alias_value":"WYN2UXNGBCTK","created_at":"2026-07-05T03:11:26Z"},{"alias_kind":"pith_short_16","alias_value":"WYN2UXNGBCTKYZJQ","created_at":"2026-07-05T03:11:26Z"},{"alias_kind":"pith_short_8","alias_value":"WYN2UXNG","created_at":"2026-07-05T03:11:26Z"}],"graph_snapshots":[{"event_id":"sha256:a6b7d92a939eeba8a48dc3263d6cf203270ce389c85cfdfc0239626542321ce6","target":"graph","created_at":"2026-07-05T03:11:26Z","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/2010.08843/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a theoretical framework for approximate planning and learning in partially observed systems. Our framework is based on the fundamental notion of information state. We provide two equivalent definitions of information state -- i) a function of history which is sufficient to compute the expected reward and predict its next value; ii) equivalently, a function of the history which can be recursively updated and is sufficient to compute the expected reward and predict the next observation. An information state always leads to a dynamic programming decomposition. Our key result is to show","authors_text":"Aditya Mahajan, Amit Sinha, Jayakumar Subramanian, Raihan Seraj","cross_cats":["cs.SY","eess.SY","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-10-17T18:30:30Z","title":"Approximate information state for approximate planning and reinforcement learning in partially observed systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.08843","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":"sha256:1dd01e5df436f45bb5937d43ca475e712ab760610e7bd016f0edd3f4bcc1e673","target":"record","created_at":"2026-07-05T03:11:26Z","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":"9cf5cf56ae82bc9b9b5f6ab545c32a362b496e45b767eeabaad5a996b3a0f603","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-10-17T18:30:30Z","title_canon_sha256":"e0fe5c6d2bccc47c5a2c945c9c1e9a1bcc5f2b3979200d73bc320ded94ad5951"},"schema_version":"1.0","source":{"id":"2010.08843","kind":"arxiv","version":2}},"canonical_sha256":"b61baa5da608a6ac65307984ba1d9eb88dbdde50217493c3405e169e3f49fbdc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b61baa5da608a6ac65307984ba1d9eb88dbdde50217493c3405e169e3f49fbdc","first_computed_at":"2026-07-05T03:11:26.286803Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:11:26.286803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uvhvMqcS+zLvMweGkpZTHUncwGba2ehwfrPGoo++XjHjRzaU4W55UDk3gNJj8OAJJDX+kMTPW7cuVHV/6oaPDA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:11:26.287327Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.08843","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1dd01e5df436f45bb5937d43ca475e712ab760610e7bd016f0edd3f4bcc1e673","sha256:a6b7d92a939eeba8a48dc3263d6cf203270ce389c85cfdfc0239626542321ce6"],"state_sha256":"97dd93b5865a1a127c8462e3e3fa09761e6081d35df0981becacf26b6a3d1861"}