{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:PYV2XK5YMDQTWBJY6HYIUUGOUB","short_pith_number":"pith:PYV2XK5Y","canonical_record":{"source":{"id":"2207.05738","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-12T17:57:17Z","cross_cats_sorted":[],"title_canon_sha256":"4a534302888de0b2824d81fc1fdf40df322ff8071be0bfdd78a9cd3381993cb2","abstract_canon_sha256":"62d09fdd53c1731bc9b050b0930fc4dd775eec6508201edc61705bc2104bc7cf"},"schema_version":"1.0"},"canonical_sha256":"7e2bababb860e13b0538f1f08a50cea04da5c81c1ac5df1bd88d2b8dda2fe02e","source":{"kind":"arxiv","id":"2207.05738","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.05738","created_at":"2026-07-05T04:48:14Z"},{"alias_kind":"arxiv_version","alias_value":"2207.05738v3","created_at":"2026-07-05T04:48:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.05738","created_at":"2026-07-05T04:48:14Z"},{"alias_kind":"pith_short_12","alias_value":"PYV2XK5YMDQT","created_at":"2026-07-05T04:48:14Z"},{"alias_kind":"pith_short_16","alias_value":"PYV2XK5YMDQTWBJY","created_at":"2026-07-05T04:48:14Z"},{"alias_kind":"pith_short_8","alias_value":"PYV2XK5Y","created_at":"2026-07-05T04:48:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:PYV2XK5YMDQTWBJY6HYIUUGOUB","target":"record","payload":{"canonical_record":{"source":{"id":"2207.05738","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-12T17:57:17Z","cross_cats_sorted":[],"title_canon_sha256":"4a534302888de0b2824d81fc1fdf40df322ff8071be0bfdd78a9cd3381993cb2","abstract_canon_sha256":"62d09fdd53c1731bc9b050b0930fc4dd775eec6508201edc61705bc2104bc7cf"},"schema_version":"1.0"},"canonical_sha256":"7e2bababb860e13b0538f1f08a50cea04da5c81c1ac5df1bd88d2b8dda2fe02e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:48:14.861432Z","signature_b64":"zBvIjxh5EpZDamNua8NkzNmd5c9pQ1xroI99Ybx2UczxF5OJF4WTN70XKnnszzT/ShXf3VdHOAB2jekQyvGVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e2bababb860e13b0538f1f08a50cea04da5c81c1ac5df1bd88d2b8dda2fe02e","last_reissued_at":"2026-07-05T04:48:14.860922Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:48:14.860922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.05738","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:48:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fFiyTtyG132sGm8PdS0nTpZ/N7dYden7h90RLkVM+jSkaTeL93BavcXKAzc7jo/rRrGTFeGa7TWwm4gULlvMBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:36:52.150666Z"},"content_sha256":"b45823da04cda14d2e29f6a7875eaffbdfd38cc808a2c1035356bf7ea779efea","schema_version":"1.0","event_id":"sha256:b45823da04cda14d2e29f6a7875eaffbdfd38cc808a2c1035356bf7ea779efea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:PYV2XK5YMDQTWBJY6HYIUUGOUB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PAC Reinforcement Learning for Predictive State Representations","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jason D. Lee, Masatoshi Uehara, Wenhao Zhan, Wen Sun","submitted_at":"2022-07-12T17:57:17Z","abstract_excerpt":"In this paper we study online Reinforcement Learning (RL) in partially observable dynamical systems. We focus on the Predictive State Representations (PSRs) model, which is an expressive model that captures other well-known models such as Partially Observable Markov Decision Processes (POMDP). PSR represents the states using a set of predictions of future observations and is defined entirely using observable quantities. We develop a novel model-based algorithm for PSRs that can learn a near optimal policy in sample complexity scaling polynomially with respect to all the relevant parameters of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.05738","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/2207.05738/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":"2026-07-05T04:48:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2BrUAUrLaoTiVzJtZKBkOIQXdbTMrOWAmiJJE/EKVfK5b4eJ+n3r7ViCDwLsobbIxz1fc6rMVLU+P6MZO9ifAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:36:52.151147Z"},"content_sha256":"ae87d9d137fef3a4a3fd007cd6391c375b70de9867eca4fdf8b46b3147a187ef","schema_version":"1.0","event_id":"sha256:ae87d9d137fef3a4a3fd007cd6391c375b70de9867eca4fdf8b46b3147a187ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PYV2XK5YMDQTWBJY6HYIUUGOUB/bundle.json","state_url":"https://pith.science/pith/PYV2XK5YMDQTWBJY6HYIUUGOUB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PYV2XK5YMDQTWBJY6HYIUUGOUB/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":"2026-08-05T18:36:52Z","links":{"resolver":"https://pith.science/pith/PYV2XK5YMDQTWBJY6HYIUUGOUB","bundle":"https://pith.science/pith/PYV2XK5YMDQTWBJY6HYIUUGOUB/bundle.json","state":"https://pith.science/pith/PYV2XK5YMDQTWBJY6HYIUUGOUB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PYV2XK5YMDQTWBJY6HYIUUGOUB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:PYV2XK5YMDQTWBJY6HYIUUGOUB","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":"62d09fdd53c1731bc9b050b0930fc4dd775eec6508201edc61705bc2104bc7cf","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-12T17:57:17Z","title_canon_sha256":"4a534302888de0b2824d81fc1fdf40df322ff8071be0bfdd78a9cd3381993cb2"},"schema_version":"1.0","source":{"id":"2207.05738","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.05738","created_at":"2026-07-05T04:48:14Z"},{"alias_kind":"arxiv_version","alias_value":"2207.05738v3","created_at":"2026-07-05T04:48:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.05738","created_at":"2026-07-05T04:48:14Z"},{"alias_kind":"pith_short_12","alias_value":"PYV2XK5YMDQT","created_at":"2026-07-05T04:48:14Z"},{"alias_kind":"pith_short_16","alias_value":"PYV2XK5YMDQTWBJY","created_at":"2026-07-05T04:48:14Z"},{"alias_kind":"pith_short_8","alias_value":"PYV2XK5Y","created_at":"2026-07-05T04:48:14Z"}],"graph_snapshots":[{"event_id":"sha256:ae87d9d137fef3a4a3fd007cd6391c375b70de9867eca4fdf8b46b3147a187ef","target":"graph","created_at":"2026-07-05T04:48:14Z","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/2207.05738/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper we study online Reinforcement Learning (RL) in partially observable dynamical systems. We focus on the Predictive State Representations (PSRs) model, which is an expressive model that captures other well-known models such as Partially Observable Markov Decision Processes (POMDP). PSR represents the states using a set of predictions of future observations and is defined entirely using observable quantities. We develop a novel model-based algorithm for PSRs that can learn a near optimal policy in sample complexity scaling polynomially with respect to all the relevant parameters of ","authors_text":"Jason D. Lee, Masatoshi Uehara, Wenhao Zhan, Wen Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-12T17:57:17Z","title":"PAC Reinforcement Learning for Predictive State Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.05738","kind":"arxiv","version":3},"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:b45823da04cda14d2e29f6a7875eaffbdfd38cc808a2c1035356bf7ea779efea","target":"record","created_at":"2026-07-05T04:48:14Z","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":"62d09fdd53c1731bc9b050b0930fc4dd775eec6508201edc61705bc2104bc7cf","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-12T17:57:17Z","title_canon_sha256":"4a534302888de0b2824d81fc1fdf40df322ff8071be0bfdd78a9cd3381993cb2"},"schema_version":"1.0","source":{"id":"2207.05738","kind":"arxiv","version":3}},"canonical_sha256":"7e2bababb860e13b0538f1f08a50cea04da5c81c1ac5df1bd88d2b8dda2fe02e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e2bababb860e13b0538f1f08a50cea04da5c81c1ac5df1bd88d2b8dda2fe02e","first_computed_at":"2026-07-05T04:48:14.860922Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:48:14.860922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zBvIjxh5EpZDamNua8NkzNmd5c9pQ1xroI99Ybx2UczxF5OJF4WTN70XKnnszzT/ShXf3VdHOAB2jekQyvGVBw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:48:14.861432Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.05738","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b45823da04cda14d2e29f6a7875eaffbdfd38cc808a2c1035356bf7ea779efea","sha256:ae87d9d137fef3a4a3fd007cd6391c375b70de9867eca4fdf8b46b3147a187ef"],"state_sha256":"cc0d4ce32a5f61133e7c0e6247bae0879f74ec29a411ceabd03e558d6aa083e5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wG0CeWZGQLOrmfoYBE6fJWDbHSm/WazdR4uuRqjog7ZcWf1ecmreoz5gwbFeJ2x0yJojtL1EFhS4mzjay4WhDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T18:36:52.154403Z","bundle_sha256":"04c70e9dd224c4097ef9680cfff0eeed3ba56e38f0f94cb3535bafd9d99e0e58"}}