{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UUCP6PEI5VZXWYJZMP5GTP7LKP","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":"46a101eade2cd8a0d3b24d98a9fc2db70ada886ec6b7988956ad03c3402bd905","cross_cats_sorted":["cs.DS","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-12T23:16:37Z","title_canon_sha256":"8d81224a244934877fba1e32ca170e567de7926fb06cb0f40562eafb60c05028"},"schema_version":"1.0","source":{"id":"2201.04735","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.04735","created_at":"2026-07-05T04:07:43Z"},{"alias_kind":"arxiv_version","alias_value":"2201.04735v2","created_at":"2026-07-05T04:07:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.04735","created_at":"2026-07-05T04:07:43Z"},{"alias_kind":"pith_short_12","alias_value":"UUCP6PEI5VZX","created_at":"2026-07-05T04:07:43Z"},{"alias_kind":"pith_short_16","alias_value":"UUCP6PEI5VZXWYJZ","created_at":"2026-07-05T04:07:43Z"},{"alias_kind":"pith_short_8","alias_value":"UUCP6PEI","created_at":"2026-07-05T04:07:43Z"}],"graph_snapshots":[{"event_id":"sha256:a55484c33e182c3285987d9d44e08a154238fa7286c28575bbab8f80967a56f2","target":"graph","created_at":"2026-07-05T04:07:43Z","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/2201.04735/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Partially Observable Markov Decision Processes (POMDPs) are a natural and general model in reinforcement learning that take into account the agent's uncertainty about its current state. In the literature on POMDPs, it is customary to assume access to a planning oracle that computes an optimal policy when the parameters are known, even though the problem is known to be computationally hard. Almost all existing planning algorithms either run in exponential time, lack provable performance guarantees, or require placing strong assumptions on the transition dynamics under every possible policy. In ","authors_text":"Ankur Moitra, Dhruv Rohatgi, Noah Golowich","cross_cats":["cs.DS","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-12T23:16:37Z","title":"Planning in Observable POMDPs in Quasipolynomial Time"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.04735","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":"sha256:065b847124477d82f953d6cfc5ea0cdd8f07c3822216a0c3a1d51e5735047e6e","target":"record","created_at":"2026-07-05T04:07:43Z","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":"46a101eade2cd8a0d3b24d98a9fc2db70ada886ec6b7988956ad03c3402bd905","cross_cats_sorted":["cs.DS","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-12T23:16:37Z","title_canon_sha256":"8d81224a244934877fba1e32ca170e567de7926fb06cb0f40562eafb60c05028"},"schema_version":"1.0","source":{"id":"2201.04735","kind":"arxiv","version":2}},"canonical_sha256":"a504ff3c88ed737b613963fa69bfeb53d5a092619a29f56637ee5ebf306909a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a504ff3c88ed737b613963fa69bfeb53d5a092619a29f56637ee5ebf306909a0","first_computed_at":"2026-07-05T04:07:43.479338Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:07:43.479338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/0wr3Tqm7QPfn0ub4VhkRr4cyNGHLRyAMF8rHPbgeUFnVhimHfrRuGJ2nfVH6+GPcZlZzsak2jZaP/tNQg90Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T04:07:43.479857Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.04735","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:065b847124477d82f953d6cfc5ea0cdd8f07c3822216a0c3a1d51e5735047e6e","sha256:a55484c33e182c3285987d9d44e08a154238fa7286c28575bbab8f80967a56f2"],"state_sha256":"9f5ba54c5eaf5a3cac8d3d8da6d619439021370fc9fd5dc8b4de524907fc44ea"}