{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZBTYB3SOUOKIKHN2NPBJCFYAB5","short_pith_number":"pith:ZBTYB3SO","canonical_record":{"source":{"id":"2409.14557","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-09-22T18:45:38Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"6b16f950db4a2a81a603ff131cd8dc5d526c208ceae45b624622cf0d116189fd","abstract_canon_sha256":"aee95221ddb547e18fa9f17ee113696f0e4d7cebf38e50d5ecb9c3566cc14d4d"},"schema_version":"1.0"},"canonical_sha256":"c86780ee4ea394851dba6bc29117000f5efd433246ac361c177cbe638ef6ae0b","source":{"kind":"arxiv","id":"2409.14557","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.14557","created_at":"2026-07-05T10:09:47Z"},{"alias_kind":"arxiv_version","alias_value":"2409.14557v3","created_at":"2026-07-05T10:09:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14557","created_at":"2026-07-05T10:09:47Z"},{"alias_kind":"pith_short_12","alias_value":"ZBTYB3SOUOKI","created_at":"2026-07-05T10:09:47Z"},{"alias_kind":"pith_short_16","alias_value":"ZBTYB3SOUOKIKHN2","created_at":"2026-07-05T10:09:47Z"},{"alias_kind":"pith_short_8","alias_value":"ZBTYB3SO","created_at":"2026-07-05T10:09:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZBTYB3SOUOKIKHN2NPBJCFYAB5","target":"record","payload":{"canonical_record":{"source":{"id":"2409.14557","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-09-22T18:45:38Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"6b16f950db4a2a81a603ff131cd8dc5d526c208ceae45b624622cf0d116189fd","abstract_canon_sha256":"aee95221ddb547e18fa9f17ee113696f0e4d7cebf38e50d5ecb9c3566cc14d4d"},"schema_version":"1.0"},"canonical_sha256":"c86780ee4ea394851dba6bc29117000f5efd433246ac361c177cbe638ef6ae0b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:47.986773Z","signature_b64":"hGdVQbI1iE02GZKvu5QAc92ejtIR8zVVRuwmHoLwdrkQq9Llbfv7RxKbtxXI65P4d4z+o/UVypYhQprJ1T1RAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c86780ee4ea394851dba6bc29117000f5efd433246ac361c177cbe638ef6ae0b","last_reissued_at":"2026-07-05T10:09:47.986242Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:47.986242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.14557","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":"2026-07-05T10:09:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"agiM/eGyb13IKRIsEFUt9rOrfJVxmhEbZRM3tD2g+tzLI479+rxWZ36dGo+cOu3baaB0czSpiv2E64PP0R5jDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T10:20:29.948554Z"},"content_sha256":"d5e5d230c085ef2fe7867336c4558b7c54361f043cef4b8a26a069185382591c","schema_version":"1.0","event_id":"sha256:d5e5d230c085ef2fe7867336c4558b7c54361f043cef4b8a26a069185382591c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZBTYB3SOUOKIKHN2NPBJCFYAB5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploiting Exogenous Structure for Sample-Efficient Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Devavrat Shah, Jia Wan, Martin J. Wainwright, Sean R. Sinclair","submitted_at":"2024-09-22T18:45:38Z","abstract_excerpt":"We study Exo-MDPs, a structured class of Markov Decision Processes (MDPs) where the state space is partitioned into exogenous and endogenous components. Exogenous states evolve stochastically, independent of the agent's actions, while endogenous states evolve deterministically based on both state components and actions. Exo-MDPs are useful for applications including inventory control, portfolio management, and ride-sharing. Our first result is structural, establishing a representational equivalence between the classes of discrete MDPs, Exo-MDPs, and discrete linear mixture MDPs. Specifically, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14557","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/2409.14557/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":"2026-07-05T10:09:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ED+nQy20awzhDTgGPRfcEC9N0FZJ6wf+3B3QIatjZ38Cfgs5aMpiw0N6x2fdVzJfFa+UFo5eL4EocVDUKb/9Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T10:20:29.948868Z"},"content_sha256":"7138605aa2c8d23f6a656c940c4e722b526dffeb068e63e94dff038720e65a88","schema_version":"1.0","event_id":"sha256:7138605aa2c8d23f6a656c940c4e722b526dffeb068e63e94dff038720e65a88"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZBTYB3SOUOKIKHN2NPBJCFYAB5/bundle.json","state_url":"https://pith.science/pith/ZBTYB3SOUOKIKHN2NPBJCFYAB5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZBTYB3SOUOKIKHN2NPBJCFYAB5/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":"2026-08-14T10:20:29Z","links":{"resolver":"https://pith.science/pith/ZBTYB3SOUOKIKHN2NPBJCFYAB5","bundle":"https://pith.science/pith/ZBTYB3SOUOKIKHN2NPBJCFYAB5/bundle.json","state":"https://pith.science/pith/ZBTYB3SOUOKIKHN2NPBJCFYAB5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZBTYB3SOUOKIKHN2NPBJCFYAB5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZBTYB3SOUOKIKHN2NPBJCFYAB5","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":"aee95221ddb547e18fa9f17ee113696f0e4d7cebf38e50d5ecb9c3566cc14d4d","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-09-22T18:45:38Z","title_canon_sha256":"6b16f950db4a2a81a603ff131cd8dc5d526c208ceae45b624622cf0d116189fd"},"schema_version":"1.0","source":{"id":"2409.14557","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.14557","created_at":"2026-07-05T10:09:47Z"},{"alias_kind":"arxiv_version","alias_value":"2409.14557v3","created_at":"2026-07-05T10:09:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14557","created_at":"2026-07-05T10:09:47Z"},{"alias_kind":"pith_short_12","alias_value":"ZBTYB3SOUOKI","created_at":"2026-07-05T10:09:47Z"},{"alias_kind":"pith_short_16","alias_value":"ZBTYB3SOUOKIKHN2","created_at":"2026-07-05T10:09:47Z"},{"alias_kind":"pith_short_8","alias_value":"ZBTYB3SO","created_at":"2026-07-05T10:09:47Z"}],"graph_snapshots":[{"event_id":"sha256:7138605aa2c8d23f6a656c940c4e722b526dffeb068e63e94dff038720e65a88","target":"graph","created_at":"2026-07-05T10:09:47Z","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/2409.14557/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study Exo-MDPs, a structured class of Markov Decision Processes (MDPs) where the state space is partitioned into exogenous and endogenous components. Exogenous states evolve stochastically, independent of the agent's actions, while endogenous states evolve deterministically based on both state components and actions. Exo-MDPs are useful for applications including inventory control, portfolio management, and ride-sharing. Our first result is structural, establishing a representational equivalence between the classes of discrete MDPs, Exo-MDPs, and discrete linear mixture MDPs. Specifically, ","authors_text":"Devavrat Shah, Jia Wan, Martin J. Wainwright, Sean R. Sinclair","cross_cats":["cs.LG","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-09-22T18:45:38Z","title":"Exploiting Exogenous Structure for Sample-Efficient Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14557","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:d5e5d230c085ef2fe7867336c4558b7c54361f043cef4b8a26a069185382591c","target":"record","created_at":"2026-07-05T10:09:47Z","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":"aee95221ddb547e18fa9f17ee113696f0e4d7cebf38e50d5ecb9c3566cc14d4d","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-09-22T18:45:38Z","title_canon_sha256":"6b16f950db4a2a81a603ff131cd8dc5d526c208ceae45b624622cf0d116189fd"},"schema_version":"1.0","source":{"id":"2409.14557","kind":"arxiv","version":3}},"canonical_sha256":"c86780ee4ea394851dba6bc29117000f5efd433246ac361c177cbe638ef6ae0b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c86780ee4ea394851dba6bc29117000f5efd433246ac361c177cbe638ef6ae0b","first_computed_at":"2026-07-05T10:09:47.986242Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:47.986242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hGdVQbI1iE02GZKvu5QAc92ejtIR8zVVRuwmHoLwdrkQq9Llbfv7RxKbtxXI65P4d4z+o/UVypYhQprJ1T1RAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:47.986773Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.14557","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5e5d230c085ef2fe7867336c4558b7c54361f043cef4b8a26a069185382591c","sha256:7138605aa2c8d23f6a656c940c4e722b526dffeb068e63e94dff038720e65a88"],"state_sha256":"faf22dc5dc6c62db966189b04a53167a687cbe97919637fcdd60b8034010f56a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EecgKJ5y4l4NO41GnbuYEyz4Zjl31AWWs1fCe0CrN2NARW07XGjybjbBxVgiXip+HoR82Zhcc1HvVvStRaLoAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T10:20:29.951214Z","bundle_sha256":"dadf597bad259ef971a669a75df513291802a91c5b4188095f803a79149ed302"}}