{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:WBDY2OWY6EZWSEGAIW2QA53UDM","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":"d51ff6f7800535574eca076607013c52676bad8c3e7a9f77b04c44f0aa9c5e3e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-05-09T18:23:30Z","title_canon_sha256":"3c098a73875e50cde252bcac4bedc421067c6b375ae0487eb014c1c071516442"},"schema_version":"1.0","source":{"id":"1205.2619","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1205.2619","created_at":"2026-05-18T03:55:47Z"},{"alias_kind":"arxiv_version","alias_value":"1205.2619v1","created_at":"2026-05-18T03:55:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1205.2619","created_at":"2026-05-18T03:55:47Z"},{"alias_kind":"pith_short_12","alias_value":"WBDY2OWY6EZW","created_at":"2026-05-18T12:27:25Z"},{"alias_kind":"pith_short_16","alias_value":"WBDY2OWY6EZWSEGA","created_at":"2026-05-18T12:27:25Z"},{"alias_kind":"pith_short_8","alias_value":"WBDY2OWY","created_at":"2026-05-18T12:27:25Z"}],"graph_snapshots":[{"event_id":"sha256:e3805d949a1579ac7d26700756bf022874eba3731636eb154a96f25d261c9e75","target":"graph","created_at":"2026-05-18T03:55:47Z","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"},"paper":{"abstract_excerpt":"The specification of aMarkov decision process (MDP) can be difficult. Reward function specification is especially problematic; in practice, it is often cognitively complex and time-consuming for users to precisely specify rewards. This work casts the problem of specifying rewards as one of preference elicitation and aims to minimize the degree of precision with which a reward function must be specified while still allowing optimal or near-optimal policies to be produced. We first discuss how robust policies can be computed for MDPs given only partial reward information using the minimax regret","authors_text":"Craig Boutilier, Kevin Regan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-05-09T18:23:30Z","title":"Regret-based Reward Elicitation for Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1205.2619","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":"sha256:3ddbe01258b46cb640c464e873d4b768de373e41a740bcc450af5fd0313939ca","target":"record","created_at":"2026-05-18T03:55:47Z","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":"d51ff6f7800535574eca076607013c52676bad8c3e7a9f77b04c44f0aa9c5e3e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-05-09T18:23:30Z","title_canon_sha256":"3c098a73875e50cde252bcac4bedc421067c6b375ae0487eb014c1c071516442"},"schema_version":"1.0","source":{"id":"1205.2619","kind":"arxiv","version":1}},"canonical_sha256":"b0478d3ad8f1336910c045b50077741b2597e71bbb274f1543a5b024c55f797f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0478d3ad8f1336910c045b50077741b2597e71bbb274f1543a5b024c55f797f","first_computed_at":"2026-05-18T03:55:47.879831Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:55:47.879831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jt61hCMWaxCoezNW4kF0W4CcOWuJk6BjC/BsoPZEOUkjvufCc2z9jzS061DTbhb2onsiCfu9kRbxnQv8QmTqAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:55:47.880334Z","signed_message":"canonical_sha256_bytes"},"source_id":"1205.2619","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ddbe01258b46cb640c464e873d4b768de373e41a740bcc450af5fd0313939ca","sha256:e3805d949a1579ac7d26700756bf022874eba3731636eb154a96f25d261c9e75"],"state_sha256":"0de6c83e6a7384b606dab4a2ea5c12ab9eb9b2369f63cbbaa558748b587838f2"}