{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:QXKTLSM6CFSG3OTGPGXUZSWZUY","short_pith_number":"pith:QXKTLSM6","canonical_record":{"source":{"id":"2209.10579","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-21T18:10:28Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"3427e28384ce67f481b2315922dbafff2e4aae9cef56353ee02c151033bb55f4","abstract_canon_sha256":"ddd4c5bd5a6e03ecb13030c2eaaaa3db68fa5cb6ab39e90b0228b5463c1a1fce"},"schema_version":"1.0"},"canonical_sha256":"85d535c99e11646dba6679af4ccad9a61d8d790da15908b24e3c76b8b297551b","source":{"kind":"arxiv","id":"2209.10579","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.10579","created_at":"2026-07-05T06:19:16Z"},{"alias_kind":"arxiv_version","alias_value":"2209.10579v2","created_at":"2026-07-05T06:19:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.10579","created_at":"2026-07-05T06:19:16Z"},{"alias_kind":"pith_short_12","alias_value":"QXKTLSM6CFSG","created_at":"2026-07-05T06:19:16Z"},{"alias_kind":"pith_short_16","alias_value":"QXKTLSM6CFSG3OTG","created_at":"2026-07-05T06:19:16Z"},{"alias_kind":"pith_short_8","alias_value":"QXKTLSM6","created_at":"2026-07-05T06:19:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:QXKTLSM6CFSG3OTGPGXUZSWZUY","target":"record","payload":{"canonical_record":{"source":{"id":"2209.10579","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-21T18:10:28Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"3427e28384ce67f481b2315922dbafff2e4aae9cef56353ee02c151033bb55f4","abstract_canon_sha256":"ddd4c5bd5a6e03ecb13030c2eaaaa3db68fa5cb6ab39e90b0228b5463c1a1fce"},"schema_version":"1.0"},"canonical_sha256":"85d535c99e11646dba6679af4ccad9a61d8d790da15908b24e3c76b8b297551b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:16.437244Z","signature_b64":"B/eBrt0HAIzdXIpRjynBkYH5BCNYUwWe7syO6Dou1/c6vOTofIPYnpM9uIf4EaxFifYLIqvqyeHzufZBzVtuCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85d535c99e11646dba6679af4ccad9a61d8d790da15908b24e3c76b8b297551b","last_reissued_at":"2026-07-05T06:19:16.436765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:16.436765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.10579","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":"2026-07-05T06:19:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HHL5UZrw90udAXfFVXxyXgv91wz49KHpeNsQmQ2o1gxN9mdaQsrQ2RlW1M4ze2xJF21jcDYAwG0L6q0AMpHJBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:48:40.878714Z"},"content_sha256":"96ee7031b8adc4801a15709f0457188591a26b401f1b5b73fe342998ec2ac6d5","schema_version":"1.0","event_id":"sha256:96ee7031b8adc4801a15709f0457188591a26b401f1b5b73fe342998ec2ac6d5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:QXKTLSM6CFSG3OTGPGXUZSWZUY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"First-order Policy Optimization for Robust Markov Decision Process","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Guanghui Lan, Tuo Zhao, Yan Li","submitted_at":"2022-09-21T18:10:28Z","abstract_excerpt":"We consider the problem of solving robust Markov decision process (MDP), which involves a set of discounted, finite state, finite action space MDPs with uncertain transition kernels. The goal of planning is to find a robust policy that optimizes the worst-case values against the transition uncertainties, and thus encompasses the standard MDP planning as a special case. For $(\\mathbf{s},\\mathbf{a})$-rectangular uncertainty sets, we establish several structural observations on the robust objective, which facilitates the development of a policy-based first-order method, namely the robust policy m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.10579","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/2209.10579/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":"2026-07-05T06:19:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6oeoRuC7yVSsQlIb86xZMJ0jpZnMEZP37RMMXep07wLRpRZdvpdnCcsvzm8pDKhNKGeIqcUaCc44ny1WBjzJAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:48:40.879206Z"},"content_sha256":"f49286143a4f8c6152ec608bcaafe0541fe3c894e011294088165e9bc90f391f","schema_version":"1.0","event_id":"sha256:f49286143a4f8c6152ec608bcaafe0541fe3c894e011294088165e9bc90f391f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QXKTLSM6CFSG3OTGPGXUZSWZUY/bundle.json","state_url":"https://pith.science/pith/QXKTLSM6CFSG3OTGPGXUZSWZUY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QXKTLSM6CFSG3OTGPGXUZSWZUY/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":"2026-08-05T20:48:40Z","links":{"resolver":"https://pith.science/pith/QXKTLSM6CFSG3OTGPGXUZSWZUY","bundle":"https://pith.science/pith/QXKTLSM6CFSG3OTGPGXUZSWZUY/bundle.json","state":"https://pith.science/pith/QXKTLSM6CFSG3OTGPGXUZSWZUY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QXKTLSM6CFSG3OTGPGXUZSWZUY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:QXKTLSM6CFSG3OTGPGXUZSWZUY","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":"ddd4c5bd5a6e03ecb13030c2eaaaa3db68fa5cb6ab39e90b0228b5463c1a1fce","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-21T18:10:28Z","title_canon_sha256":"3427e28384ce67f481b2315922dbafff2e4aae9cef56353ee02c151033bb55f4"},"schema_version":"1.0","source":{"id":"2209.10579","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.10579","created_at":"2026-07-05T06:19:16Z"},{"alias_kind":"arxiv_version","alias_value":"2209.10579v2","created_at":"2026-07-05T06:19:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.10579","created_at":"2026-07-05T06:19:16Z"},{"alias_kind":"pith_short_12","alias_value":"QXKTLSM6CFSG","created_at":"2026-07-05T06:19:16Z"},{"alias_kind":"pith_short_16","alias_value":"QXKTLSM6CFSG3OTG","created_at":"2026-07-05T06:19:16Z"},{"alias_kind":"pith_short_8","alias_value":"QXKTLSM6","created_at":"2026-07-05T06:19:16Z"}],"graph_snapshots":[{"event_id":"sha256:f49286143a4f8c6152ec608bcaafe0541fe3c894e011294088165e9bc90f391f","target":"graph","created_at":"2026-07-05T06:19:16Z","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/2209.10579/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the problem of solving robust Markov decision process (MDP), which involves a set of discounted, finite state, finite action space MDPs with uncertain transition kernels. The goal of planning is to find a robust policy that optimizes the worst-case values against the transition uncertainties, and thus encompasses the standard MDP planning as a special case. For $(\\mathbf{s},\\mathbf{a})$-rectangular uncertainty sets, we establish several structural observations on the robust objective, which facilitates the development of a policy-based first-order method, namely the robust policy m","authors_text":"Guanghui Lan, Tuo Zhao, Yan Li","cross_cats":["cs.AI","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-21T18:10:28Z","title":"First-order Policy Optimization for Robust Markov Decision Process"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.10579","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":"sha256:96ee7031b8adc4801a15709f0457188591a26b401f1b5b73fe342998ec2ac6d5","target":"record","created_at":"2026-07-05T06:19:16Z","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":"ddd4c5bd5a6e03ecb13030c2eaaaa3db68fa5cb6ab39e90b0228b5463c1a1fce","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-21T18:10:28Z","title_canon_sha256":"3427e28384ce67f481b2315922dbafff2e4aae9cef56353ee02c151033bb55f4"},"schema_version":"1.0","source":{"id":"2209.10579","kind":"arxiv","version":2}},"canonical_sha256":"85d535c99e11646dba6679af4ccad9a61d8d790da15908b24e3c76b8b297551b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85d535c99e11646dba6679af4ccad9a61d8d790da15908b24e3c76b8b297551b","first_computed_at":"2026-07-05T06:19:16.436765Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:19:16.436765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B/eBrt0HAIzdXIpRjynBkYH5BCNYUwWe7syO6Dou1/c6vOTofIPYnpM9uIf4EaxFifYLIqvqyeHzufZBzVtuCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:19:16.437244Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.10579","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96ee7031b8adc4801a15709f0457188591a26b401f1b5b73fe342998ec2ac6d5","sha256:f49286143a4f8c6152ec608bcaafe0541fe3c894e011294088165e9bc90f391f"],"state_sha256":"7136544b3891160d1b2aded1a4379d9a43627c148b7195b8ea6280809674aca3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VY8cl/VrT2KfhUKnV5u2utvxCYXQuZO3OJHiUvsWgAl4eq1oZxVREB2geDI47L+XQoq4ub5G3n+wXS6H0FaxAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T20:48:40.882706Z","bundle_sha256":"34117fcc0da13b4802133c1a59965e2b3c1b0877673580c84967afe6c86e64d2"}}