{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4MXN7UML4KTMIUVAT2DPSQAPLC","short_pith_number":"pith:4MXN7UML","canonical_record":{"source":{"id":"2301.13857","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-31T18:54:36Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"84ac05a6a1c37a98184bc3e154ed13c67abd4916a887c5fd2a87cf7f745e488b","abstract_canon_sha256":"63507b7a6f4f499361b46de3aefaadedd973547866fbc8598af7b13d5ccfa4c1"},"schema_version":"1.0"},"canonical_sha256":"e32edfd18be2a6c452a09e86f9400f588ced8aac9e11128caae406f899b0dd54","source":{"kind":"arxiv","id":"2301.13857","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4MXN7UML4KTMIUVAT2DPSQAPLC","target":"record","payload":{"canonical_record":{"source":{"id":"2301.13857","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-31T18:54:36Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"84ac05a6a1c37a98184bc3e154ed13c67abd4916a887c5fd2a87cf7f745e488b","abstract_canon_sha256":"63507b7a6f4f499361b46de3aefaadedd973547866fbc8598af7b13d5ccfa4c1"},"schema_version":"1.0"},"canonical_sha256":"e32edfd18be2a6c452a09e86f9400f588ced8aac9e11128caae406f899b0dd54","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:46.831148Z","signature_b64":"TPi/JHUm1I+dEmB9gIAOSSp5U4fnAnmoKgxBS2GtF55+IWznMlh41r6okbmxaaL5X1cDEqT12VMICicS21TKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e32edfd18be2a6c452a09e86f9400f588ced8aac9e11128caae406f899b0dd54","last_reissued_at":"2026-07-05T05:38:46.830696Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:46.830696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.13857","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:38:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y0um/ZwBlAvdMfb7n5A10kA/cXcP9q78bZkAdr5jXQhWd8N5xpNHNGYIMvBKWJQjy7EDg7RaK3LLSE2udNU2Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T23:58:01.496071Z"},"content_sha256":"3cba700e3d497ec6475ce467c8579a97c4aa5330c6ba3220f53eb3d408591bbc","schema_version":"1.0","event_id":"sha256:3cba700e3d497ec6475ce467c8579a97c4aa5330c6ba3220f53eb3d408591bbc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4MXN7UML4KTMIUVAT2DPSQAPLC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning in POMDPs is Sample-Efficient with Hindsight Observability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alekh Agarwal, Christoph Dann, Jonathan N. Lee, Tong Zhang","submitted_at":"2023-01-31T18:54:36Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13857","kind":"arxiv","version":2},"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/2301.13857/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:38:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y3J836ptNrdKZ+wkWX2fnU6KU5ite2WgGXbKIzBFnh79gES5ggpYf4qkPBGUgSQATSqV82RJARq/59+lcg1yAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T23:58:01.496523Z"},"content_sha256":"ff2eae4bbe43977333192242161ef28d8d6c6a799c970f3ce8acc71146cbe593","schema_version":"1.0","event_id":"sha256:ff2eae4bbe43977333192242161ef28d8d6c6a799c970f3ce8acc71146cbe593"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4MXN7UML4KTMIUVAT2DPSQAPLC/bundle.json","state_url":"https://pith.science/pith/4MXN7UML4KTMIUVAT2DPSQAPLC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4MXN7UML4KTMIUVAT2DPSQAPLC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T23:58:01Z","links":{"resolver":"https://pith.science/pith/4MXN7UML4KTMIUVAT2DPSQAPLC","bundle":"https://pith.science/pith/4MXN7UML4KTMIUVAT2DPSQAPLC/bundle.json","state":"https://pith.science/pith/4MXN7UML4KTMIUVAT2DPSQAPLC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4MXN7UML4KTMIUVAT2DPSQAPLC/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VUNfAJkC7jk6RPV7rsbSegdqVedESgYceq7I0s8cfITgXmDQ9ifRYVa5PZZL3OmjUGS4bqgbFm5eOTuUMGp3Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T23:58:01.500716Z","bundle_sha256":"90e8b88005e685999721952ead7b791a82997058ddb7064cf3adaab0f8b9cce6"}}