{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4MXN7UML4KTMIUVAT2DPSQAPLC","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":"63507b7a6f4f499361b46de3aefaadedd973547866fbc8598af7b13d5ccfa4c1","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-31T18:54:36Z","title_canon_sha256":"84ac05a6a1c37a98184bc3e154ed13c67abd4916a887c5fd2a87cf7f745e488b"},"schema_version":"1.0","source":{"id":"2301.13857","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.13857","created_at":"2026-07-05T05:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2301.13857v2","created_at":"2026-07-05T05:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13857","created_at":"2026-07-05T05:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"4MXN7UML4KTM","created_at":"2026-07-05T05:38:46Z"},{"alias_kind":"pith_short_16","alias_value":"4MXN7UML4KTMIUVA","created_at":"2026-07-05T05:38:46Z"},{"alias_kind":"pith_short_8","alias_value":"4MXN7UML","created_at":"2026-07-05T05:38:46Z"}],"graph_snapshots":[{"event_id":"sha256:ff2eae4bbe43977333192242161ef28d8d6c6a799c970f3ce8acc71146cbe593","target":"graph","created_at":"2026-07-05T05:38:46Z","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/2301.13857/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"POMDPs capture a broad class of decision making problems, but hardness results suggest that learning is intractable even in simple settings due to the inherent partial observability. However, in many realistic problems, more information is either revealed or can be computed during some point of the learning process. Motivated by diverse applications ranging from robotics to data center scheduling, we formulate a Hindsight Observable Markov Decision Process (HOMDP) as a POMDP where the latent states are revealed to the learner in hindsight and only during training. We introduce new algorithms f","authors_text":"Alekh Agarwal, Christoph Dann, Jonathan N. Lee, Tong Zhang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-31T18:54:36Z","title":"Learning in POMDPs is Sample-Efficient with Hindsight Observability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13857","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":"sha256:3cba700e3d497ec6475ce467c8579a97c4aa5330c6ba3220f53eb3d408591bbc","target":"record","created_at":"2026-07-05T05:38:46Z","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":"63507b7a6f4f499361b46de3aefaadedd973547866fbc8598af7b13d5ccfa4c1","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-31T18:54:36Z","title_canon_sha256":"84ac05a6a1c37a98184bc3e154ed13c67abd4916a887c5fd2a87cf7f745e488b"},"schema_version":"1.0","source":{"id":"2301.13857","kind":"arxiv","version":2}},"canonical_sha256":"e32edfd18be2a6c452a09e86f9400f588ced8aac9e11128caae406f899b0dd54","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e32edfd18be2a6c452a09e86f9400f588ced8aac9e11128caae406f899b0dd54","first_computed_at":"2026-07-05T05:38:46.830696Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:38:46.830696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TPi/JHUm1I+dEmB9gIAOSSp5U4fnAnmoKgxBS2GtF55+IWznMlh41r6okbmxaaL5X1cDEqT12VMICicS21TKDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:38:46.831148Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.13857","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3cba700e3d497ec6475ce467c8579a97c4aa5330c6ba3220f53eb3d408591bbc","sha256:ff2eae4bbe43977333192242161ef28d8d6c6a799c970f3ce8acc71146cbe593"],"state_sha256":"b08965400689558016fa874f1cc3efbfbb06db4652df872cc130d801fe97bedb"}