{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:SV4N353277EQBPGV6NATVED4CK","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":"e8c345ad80dea104e45e0e001ce502222aa202bfd7fc89b52af17bdd9df7fbbf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-02T09:42:42Z","title_canon_sha256":"eb7b78753708a235f3747aa2b21b4f3a200bf12961dba4b969e8e6a771132656"},"schema_version":"1.0","source":{"id":"2106.01048","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.01048","created_at":"2026-07-05T04:37:16Z"},{"alias_kind":"arxiv_version","alias_value":"2106.01048v3","created_at":"2026-07-05T04:37:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.01048","created_at":"2026-07-05T04:37:16Z"},{"alias_kind":"pith_short_12","alias_value":"SV4N353277EQ","created_at":"2026-07-05T04:37:16Z"},{"alias_kind":"pith_short_16","alias_value":"SV4N353277EQBPGV","created_at":"2026-07-05T04:37:16Z"},{"alias_kind":"pith_short_8","alias_value":"SV4N3532","created_at":"2026-07-05T04:37:16Z"}],"graph_snapshots":[{"event_id":"sha256:c77642e998c11454865f69c9886ae83afeee9d818f916f148e4977d9a394b992","target":"graph","created_at":"2026-07-05T04:37:16Z","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/2106.01048/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In many real-world scenarios, the utility of a user is derived from the single execution of a policy. In this case, to apply multi-objective reinforcement learning, the expected utility of the returns must be optimised. Various scenarios exist where a user's preferences over objectives (also known as the utility function) are unknown or difficult to specify. In such scenarios, a set of optimal policies must be learned. However, settings where the expected utility must be maximised have been largely overlooked by the multi-objective reinforcement learning community and, as a consequence, a set ","authors_text":"Conor F. Hayes, Diederik M. Roijers, Enda Howley, Patrick Mannion, Timothy Verstraeten","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-02T09:42:42Z","title":"Expected Scalarised Returns Dominance: A New Solution Concept for Multi-Objective Decision Making"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.01048","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":"sha256:115d26f94af9f23b9a32ed681ea01c5f289246c9d58a3d0a4f64ae14d3a5cc9f","target":"record","created_at":"2026-07-05T04:37:16Z","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":"e8c345ad80dea104e45e0e001ce502222aa202bfd7fc89b52af17bdd9df7fbbf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-02T09:42:42Z","title_canon_sha256":"eb7b78753708a235f3747aa2b21b4f3a200bf12961dba4b969e8e6a771132656"},"schema_version":"1.0","source":{"id":"2106.01048","kind":"arxiv","version":3}},"canonical_sha256":"9578ddf77affc900bcd5f3413a907c1291fffb4fe889a0aaed1a35b236b60e12","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9578ddf77affc900bcd5f3413a907c1291fffb4fe889a0aaed1a35b236b60e12","first_computed_at":"2026-07-05T04:37:16.780306Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:37:16.780306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Opf9RZOUTrPbWjXbjjwDyY/MZQp9zKjzKKLTsFzYYgLNiHzxEq1CzQ5w+lDFFWJExKrRD0zfKTCRCID514yfCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:37:16.780850Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.01048","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:115d26f94af9f23b9a32ed681ea01c5f289246c9d58a3d0a4f64ae14d3a5cc9f","sha256:c77642e998c11454865f69c9886ae83afeee9d818f916f148e4977d9a394b992"],"state_sha256":"edcfe4c6bd1915442b6346b6a9b1ba034a152e739bca99f4aeb72bcc165a5be2"}