{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:6HKRO5CDW3OYMJQIGW7HOT6P7O","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":"b80b456b7643c1e6ff59ea052f1f66c7ac84edfe903a1768c494d1eb5e0fd7bd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-12-01T00:55:23Z","title_canon_sha256":"6af5eea7e1107b966fa909ad9f33b9de4d67816e03e53577646dd9984faca667"},"schema_version":"1.0","source":{"id":"1612.00094","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.00094","created_at":"2026-05-18T00:56:06Z"},{"alias_kind":"arxiv_version","alias_value":"1612.00094v1","created_at":"2026-05-18T00:56:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.00094","created_at":"2026-05-18T00:56:06Z"},{"alias_kind":"pith_short_12","alias_value":"6HKRO5CDW3OY","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_16","alias_value":"6HKRO5CDW3OYMJQI","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_8","alias_value":"6HKRO5CD","created_at":"2026-05-18T12:30:01Z"}],"graph_snapshots":[{"event_id":"sha256:1c82e4a3806eaab7a94da5b3451f2060c9ac5e29fc1acccc56d2122b010a82d5","target":"graph","created_at":"2026-05-18T00:56:06Z","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":"In the Markov decision process model, policies are usually evaluated by expected cumulative rewards. As this decision criterion is not always suitable, we propose in this paper an algorithm for computing a policy optimal for the quantile criterion. Both finite and infinite horizons are considered. Finally we experimentally evaluate our approach on random MDPs and on a data center control problem.","authors_text":"Hugo Gilbert, Paul Weng, Yan Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-12-01T00:55:23Z","title":"Optimizing Quantiles in Preference-based Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.00094","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":"sha256:5d2013b8ebea53009032c18b10e424797795a6f0967cd85913a043d2e066c1c3","target":"record","created_at":"2026-05-18T00:56:06Z","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":"b80b456b7643c1e6ff59ea052f1f66c7ac84edfe903a1768c494d1eb5e0fd7bd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-12-01T00:55:23Z","title_canon_sha256":"6af5eea7e1107b966fa909ad9f33b9de4d67816e03e53577646dd9984faca667"},"schema_version":"1.0","source":{"id":"1612.00094","kind":"arxiv","version":1}},"canonical_sha256":"f1d5177443b6dd86260835be774fcffba10edadff0a030619a630be7020f2aef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1d5177443b6dd86260835be774fcffba10edadff0a030619a630be7020f2aef","first_computed_at":"2026-05-18T00:56:06.840591Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:56:06.840591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Oz/rMKlI1J2h9Zayu5KXI1v07MKOnV5KmGcaRBlRKfUcH14MlwwHgJE35ZPnX28hhI4JGL4sfto0QeN6xYHMAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:56:06.841232Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.00094","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d2013b8ebea53009032c18b10e424797795a6f0967cd85913a043d2e066c1c3","sha256:1c82e4a3806eaab7a94da5b3451f2060c9ac5e29fc1acccc56d2122b010a82d5"],"state_sha256":"0b2c39367ec45330ad5c8e63535936038686062aadff0606294313f4680c324b"}