{"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"}