{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2011:2LUU46PYJKOPZDSBK7B7C4LERN","short_pith_number":"pith:2LUU46PY","canonical_record":{"source":{"id":"1109.2355","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-09-11T21:39:21Z","cross_cats_sorted":[],"title_canon_sha256":"ff1bf749bb39c530d889576416645f90df83e76334c9e68859a9b5db7f772108","abstract_canon_sha256":"3bdf8f2c452a4583e0c2df5f490b5954afb5a8deeb821c01f5c67c1a1c9a2c93"},"schema_version":"1.0"},"canonical_sha256":"d2e94e79f84a9cfc8e4157c3f171648b4bc938db11ee20937cf6a4803a110ced","source":{"kind":"arxiv","id":"1109.2355","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1109.2355","created_at":"2026-05-18T04:13:37Z"},{"alias_kind":"arxiv_version","alias_value":"1109.2355v1","created_at":"2026-05-18T04:13:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1109.2355","created_at":"2026-05-18T04:13:37Z"},{"alias_kind":"pith_short_12","alias_value":"2LUU46PYJKOP","created_at":"2026-05-18T12:26:18Z"},{"alias_kind":"pith_short_16","alias_value":"2LUU46PYJKOPZDSB","created_at":"2026-05-18T12:26:18Z"},{"alias_kind":"pith_short_8","alias_value":"2LUU46PY","created_at":"2026-05-18T12:26:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2011:2LUU46PYJKOPZDSBK7B7C4LERN","target":"record","payload":{"canonical_record":{"source":{"id":"1109.2355","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-09-11T21:39:21Z","cross_cats_sorted":[],"title_canon_sha256":"ff1bf749bb39c530d889576416645f90df83e76334c9e68859a9b5db7f772108","abstract_canon_sha256":"3bdf8f2c452a4583e0c2df5f490b5954afb5a8deeb821c01f5c67c1a1c9a2c93"},"schema_version":"1.0"},"canonical_sha256":"d2e94e79f84a9cfc8e4157c3f171648b4bc938db11ee20937cf6a4803a110ced","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:13:37.870048Z","signature_b64":"csCAt3YOxQ69vfHnsO4se5shGZ8OtzfinNjubL16q/8WAfFnMyFgd3fu4TZBPA9ohTg6RIJYiD40pipuBFo/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2e94e79f84a9cfc8e4157c3f171648b4bc938db11ee20937cf6a4803a110ced","last_reissued_at":"2026-05-18T04:13:37.869339Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:13:37.869339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1109.2355","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T04:13:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vOYO09TdH9CryronjU5RDd2OBZrDq/GJZjGlG6vlSUZfJBLNDFGIHO4iN7fkeZ0jIADn7QSpY5GFpcBKSLhFBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T14:44:27.388502Z"},"content_sha256":"379ced468e4a235969f27e7b31b0a936acd97358a899565d10976a49efa24558","schema_version":"1.0","event_id":"sha256:379ced468e4a235969f27e7b31b0a936acd97358a899565d10976a49efa24558"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2011:2LUU46PYJKOPZDSBK7B7C4LERN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Decision-Theoretic Planning with non-Markovian Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"C. Gretton, D. Price, F. Kabanza, J. Slaney, S. Thiebaux","submitted_at":"2011-09-11T21:39:21Z","abstract_excerpt":"A decision process in which rewards depend on history rather than merely on the current state is called a decision process with non-Markovian rewards (NMRDP). In decision-theoretic planning, where many desirable behaviours are more naturally expressed as properties of execution sequences rather than as properties of states, NMRDPs form a more natural model than the commonly adopted fully Markovian decision process (MDP) model. While the more tractable solution methods developed for MDPs do not directly apply in the presence of non-Markovian rewards, a number of solution methods for NMRDPs have"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1109.2355","kind":"arxiv","version":1},"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":"2026-05-18T04:13:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2nZVOYStxgD7F5hhDzAMfVzYhStlkbTZjNkZ3nby5ckD3RVw0PYmZAtv9gXJGiWwkZs2E8ic1UUbwl1b1OEeCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T14:44:27.388843Z"},"content_sha256":"645bf065a852e38e5b39473ba2baf0d16b35f56eefd4f64bf4e4630ad7728986","schema_version":"1.0","event_id":"sha256:645bf065a852e38e5b39473ba2baf0d16b35f56eefd4f64bf4e4630ad7728986"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2LUU46PYJKOPZDSBK7B7C4LERN/bundle.json","state_url":"https://pith.science/pith/2LUU46PYJKOPZDSBK7B7C4LERN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2LUU46PYJKOPZDSBK7B7C4LERN/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":"2026-05-20T14:44:27Z","links":{"resolver":"https://pith.science/pith/2LUU46PYJKOPZDSBK7B7C4LERN","bundle":"https://pith.science/pith/2LUU46PYJKOPZDSBK7B7C4LERN/bundle.json","state":"https://pith.science/pith/2LUU46PYJKOPZDSBK7B7C4LERN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2LUU46PYJKOPZDSBK7B7C4LERN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2011:2LUU46PYJKOPZDSBK7B7C4LERN","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":"3bdf8f2c452a4583e0c2df5f490b5954afb5a8deeb821c01f5c67c1a1c9a2c93","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-09-11T21:39:21Z","title_canon_sha256":"ff1bf749bb39c530d889576416645f90df83e76334c9e68859a9b5db7f772108"},"schema_version":"1.0","source":{"id":"1109.2355","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1109.2355","created_at":"2026-05-18T04:13:37Z"},{"alias_kind":"arxiv_version","alias_value":"1109.2355v1","created_at":"2026-05-18T04:13:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1109.2355","created_at":"2026-05-18T04:13:37Z"},{"alias_kind":"pith_short_12","alias_value":"2LUU46PYJKOP","created_at":"2026-05-18T12:26:18Z"},{"alias_kind":"pith_short_16","alias_value":"2LUU46PYJKOPZDSB","created_at":"2026-05-18T12:26:18Z"},{"alias_kind":"pith_short_8","alias_value":"2LUU46PY","created_at":"2026-05-18T12:26:18Z"}],"graph_snapshots":[{"event_id":"sha256:645bf065a852e38e5b39473ba2baf0d16b35f56eefd4f64bf4e4630ad7728986","target":"graph","created_at":"2026-05-18T04:13:37Z","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":"A decision process in which rewards depend on history rather than merely on the current state is called a decision process with non-Markovian rewards (NMRDP). In decision-theoretic planning, where many desirable behaviours are more naturally expressed as properties of execution sequences rather than as properties of states, NMRDPs form a more natural model than the commonly adopted fully Markovian decision process (MDP) model. While the more tractable solution methods developed for MDPs do not directly apply in the presence of non-Markovian rewards, a number of solution methods for NMRDPs have","authors_text":"C. Gretton, D. Price, F. Kabanza, J. Slaney, S. Thiebaux","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-09-11T21:39:21Z","title":"Decision-Theoretic Planning with non-Markovian Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1109.2355","kind":"arxiv","version":1},"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":"sha256:379ced468e4a235969f27e7b31b0a936acd97358a899565d10976a49efa24558","target":"record","created_at":"2026-05-18T04:13:37Z","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":"3bdf8f2c452a4583e0c2df5f490b5954afb5a8deeb821c01f5c67c1a1c9a2c93","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-09-11T21:39:21Z","title_canon_sha256":"ff1bf749bb39c530d889576416645f90df83e76334c9e68859a9b5db7f772108"},"schema_version":"1.0","source":{"id":"1109.2355","kind":"arxiv","version":1}},"canonical_sha256":"d2e94e79f84a9cfc8e4157c3f171648b4bc938db11ee20937cf6a4803a110ced","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2e94e79f84a9cfc8e4157c3f171648b4bc938db11ee20937cf6a4803a110ced","first_computed_at":"2026-05-18T04:13:37.869339Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:13:37.869339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"csCAt3YOxQ69vfHnsO4se5shGZ8OtzfinNjubL16q/8WAfFnMyFgd3fu4TZBPA9ohTg6RIJYiD40pipuBFo/Ag==","signature_status":"signed_v1","signed_at":"2026-05-18T04:13:37.870048Z","signed_message":"canonical_sha256_bytes"},"source_id":"1109.2355","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:379ced468e4a235969f27e7b31b0a936acd97358a899565d10976a49efa24558","sha256:645bf065a852e38e5b39473ba2baf0d16b35f56eefd4f64bf4e4630ad7728986"],"state_sha256":"82d0928b4e171624e56d2f54b4a1a63c510207cd5927909c86d9ba22e6f1721e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D9MHzfqEKx921HFBn1XYOHODmqPjKb0n7UfK0aOOg5ONen/AZOWbUVW940xMp8/uTUqb1kCaUfQwknJ2f8hQAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T14:44:27.390917Z","bundle_sha256":"9178d6079b14e0dcfdc637961f91c45cf3e719e845b7e4f4a28bf3b9ccc9885e"}}