{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:5QBWH2GAHBTPPML34UD7UO2AR4","short_pith_number":"pith:5QBWH2GA","canonical_record":{"source":{"id":"1503.07206","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2015-03-24T21:07:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6cc0a35f5fe2659eb62b6f01f65948460c0f02c5206cfac718e7394cd1918a52","abstract_canon_sha256":"a7c9e06acc6cc83855d8843a7843d63402841e55cc1b25d72542caf3a8a8373e"},"schema_version":"1.0"},"canonical_sha256":"ec0363e8c03866f7b17be507fa3b408f272ba01ccf4a0585b7014c70ae744448","source":{"kind":"arxiv","id":"1503.07206","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1503.07206","created_at":"2026-05-18T01:20:53Z"},{"alias_kind":"arxiv_version","alias_value":"1503.07206v2","created_at":"2026-05-18T01:20:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.07206","created_at":"2026-05-18T01:20:53Z"},{"alias_kind":"pith_short_12","alias_value":"5QBWH2GAHBTP","created_at":"2026-05-18T12:29:05Z"},{"alias_kind":"pith_short_16","alias_value":"5QBWH2GAHBTPPML3","created_at":"2026-05-18T12:29:05Z"},{"alias_kind":"pith_short_8","alias_value":"5QBWH2GA","created_at":"2026-05-18T12:29:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:5QBWH2GAHBTPPML34UD7UO2AR4","target":"record","payload":{"canonical_record":{"source":{"id":"1503.07206","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2015-03-24T21:07:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6cc0a35f5fe2659eb62b6f01f65948460c0f02c5206cfac718e7394cd1918a52","abstract_canon_sha256":"a7c9e06acc6cc83855d8843a7843d63402841e55cc1b25d72542caf3a8a8373e"},"schema_version":"1.0"},"canonical_sha256":"ec0363e8c03866f7b17be507fa3b408f272ba01ccf4a0585b7014c70ae744448","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:53.880545Z","signature_b64":"lgHtoRFzdqrCq3n+wJ6t9ZNdHqc8/HaoIWCYoOakXFeMDuAYYdQgCq6KmuPUcxlerG953VkQxyORu24Zah+fCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec0363e8c03866f7b17be507fa3b408f272ba01ccf4a0585b7014c70ae744448","last_reissued_at":"2026-05-18T01:20:53.879965Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:53.879965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1503.07206","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":"2026-05-18T01:20:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C0NcreYGN/TrP115bXq9v6RhbA7TwX9MB142s78nU2PbEGpisgzqdziIcMsymNpTEsPpc3KiGSkmJYg0SINjBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T08:20:08.706368Z"},"content_sha256":"d4d82f7c55eee4669a36e4a12a591ac83a415c4fcda6ec6e69b96cdb2502cd45","schema_version":"1.0","event_id":"sha256:d4d82f7c55eee4669a36e4a12a591ac83a415c4fcda6ec6e69b96cdb2502cd45"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:5QBWH2GAHBTPPML34UD7UO2AR4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Geometry and Determinism of Optimal Stationary Control in Partially Observable Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"math.OC","authors_text":"Guido Montufar, Keyan Ghazi-Zahedi, Nihat Ay","submitted_at":"2015-03-24T21:07:11Z","abstract_excerpt":"It is well known that for any finite state Markov decision process (MDP) there is a memoryless deterministic policy that maximizes the expected reward. For partially observable Markov decision processes (POMDPs), optimal memoryless policies are generally stochastic. We study the expected reward optimization problem over the set of memoryless stochastic policies. We formulate this as a constrained linear optimization problem and develop a corresponding geometric framework. We show that any POMDP has an optimal memoryless policy of limited stochasticity, which allows us to reduce the dimensional"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.07206","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":""},"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":"2026-05-18T01:20:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VxPhOZ5H4buWDHCwxXV2cTwHPDNKyqfEDUhFvk6JEzh99Y7M1iaOCdDd3cVVykRxyMcYzDOBa86jKZagTru7CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T08:20:08.706998Z"},"content_sha256":"2591071b217273892f6cf152ee1f1a1518cbea697eccb6ed1397b64078a49042","schema_version":"1.0","event_id":"sha256:2591071b217273892f6cf152ee1f1a1518cbea697eccb6ed1397b64078a49042"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5QBWH2GAHBTPPML34UD7UO2AR4/bundle.json","state_url":"https://pith.science/pith/5QBWH2GAHBTPPML34UD7UO2AR4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5QBWH2GAHBTPPML34UD7UO2AR4/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":"2026-06-02T08:20:08Z","links":{"resolver":"https://pith.science/pith/5QBWH2GAHBTPPML34UD7UO2AR4","bundle":"https://pith.science/pith/5QBWH2GAHBTPPML34UD7UO2AR4/bundle.json","state":"https://pith.science/pith/5QBWH2GAHBTPPML34UD7UO2AR4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5QBWH2GAHBTPPML34UD7UO2AR4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:5QBWH2GAHBTPPML34UD7UO2AR4","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":"a7c9e06acc6cc83855d8843a7843d63402841e55cc1b25d72542caf3a8a8373e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2015-03-24T21:07:11Z","title_canon_sha256":"6cc0a35f5fe2659eb62b6f01f65948460c0f02c5206cfac718e7394cd1918a52"},"schema_version":"1.0","source":{"id":"1503.07206","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1503.07206","created_at":"2026-05-18T01:20:53Z"},{"alias_kind":"arxiv_version","alias_value":"1503.07206v2","created_at":"2026-05-18T01:20:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.07206","created_at":"2026-05-18T01:20:53Z"},{"alias_kind":"pith_short_12","alias_value":"5QBWH2GAHBTP","created_at":"2026-05-18T12:29:05Z"},{"alias_kind":"pith_short_16","alias_value":"5QBWH2GAHBTPPML3","created_at":"2026-05-18T12:29:05Z"},{"alias_kind":"pith_short_8","alias_value":"5QBWH2GA","created_at":"2026-05-18T12:29:05Z"}],"graph_snapshots":[{"event_id":"sha256:2591071b217273892f6cf152ee1f1a1518cbea697eccb6ed1397b64078a49042","target":"graph","created_at":"2026-05-18T01:20:53Z","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"},"paper":{"abstract_excerpt":"It is well known that for any finite state Markov decision process (MDP) there is a memoryless deterministic policy that maximizes the expected reward. For partially observable Markov decision processes (POMDPs), optimal memoryless policies are generally stochastic. We study the expected reward optimization problem over the set of memoryless stochastic policies. We formulate this as a constrained linear optimization problem and develop a corresponding geometric framework. We show that any POMDP has an optimal memoryless policy of limited stochasticity, which allows us to reduce the dimensional","authors_text":"Guido Montufar, Keyan Ghazi-Zahedi, Nihat Ay","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2015-03-24T21:07:11Z","title":"Geometry and Determinism of Optimal Stationary Control in Partially Observable Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.07206","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:d4d82f7c55eee4669a36e4a12a591ac83a415c4fcda6ec6e69b96cdb2502cd45","target":"record","created_at":"2026-05-18T01:20:53Z","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":"a7c9e06acc6cc83855d8843a7843d63402841e55cc1b25d72542caf3a8a8373e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2015-03-24T21:07:11Z","title_canon_sha256":"6cc0a35f5fe2659eb62b6f01f65948460c0f02c5206cfac718e7394cd1918a52"},"schema_version":"1.0","source":{"id":"1503.07206","kind":"arxiv","version":2}},"canonical_sha256":"ec0363e8c03866f7b17be507fa3b408f272ba01ccf4a0585b7014c70ae744448","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec0363e8c03866f7b17be507fa3b408f272ba01ccf4a0585b7014c70ae744448","first_computed_at":"2026-05-18T01:20:53.879965Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:20:53.879965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lgHtoRFzdqrCq3n+wJ6t9ZNdHqc8/HaoIWCYoOakXFeMDuAYYdQgCq6KmuPUcxlerG953VkQxyORu24Zah+fCw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:20:53.880545Z","signed_message":"canonical_sha256_bytes"},"source_id":"1503.07206","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4d82f7c55eee4669a36e4a12a591ac83a415c4fcda6ec6e69b96cdb2502cd45","sha256:2591071b217273892f6cf152ee1f1a1518cbea697eccb6ed1397b64078a49042"],"state_sha256":"ba3e1112849efcdf09ecb503941d067c9e29d074494f188fb3a336cf499302e2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ir2kCF/2Cwbzd3uejsTB7iUX0EYAgFdizg8Bq+HP6kp6HqxY32wIDpMkZ+HC6ycBvFU+5PCGb584oO/hz0rNBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T08:20:08.710179Z","bundle_sha256":"e342ce1cc31928cd77cc147c46764197a683ac1dfadb7319b74d8d454fa16591"}}