{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XESYBCRATBDVURGBCVT223CVPV","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":"94e89f0306108b21090ec7e957b50b97de7ec95dad661bf3339bb2cfdd4b1e8a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-16T19:23:02Z","title_canon_sha256":"8581c8db545f923c37e9c1a122abe7824236c8d595e46235cd0ae528be55f12b"},"schema_version":"1.0","source":{"id":"2208.07914","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.07914","created_at":"2026-07-05T06:14:56Z"},{"alias_kind":"arxiv_version","alias_value":"2208.07914v3","created_at":"2026-07-05T06:14:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.07914","created_at":"2026-07-05T06:14:56Z"},{"alias_kind":"pith_short_12","alias_value":"XESYBCRATBDV","created_at":"2026-07-05T06:14:56Z"},{"alias_kind":"pith_short_16","alias_value":"XESYBCRATBDVURGB","created_at":"2026-07-05T06:14:56Z"},{"alias_kind":"pith_short_8","alias_value":"XESYBCRA","created_at":"2026-07-05T06:14:56Z"}],"graph_snapshots":[{"event_id":"sha256:ed0063de32a15157c1ac0479f858ecc35b77ff50d8f2185c6369c3b24c1457cf","target":"graph","created_at":"2026-07-05T06:14:56Z","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/2208.07914/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-objective reinforcement learning (MORL) approaches have emerged to tackle many real-world problems with multiple conflicting objectives by maximizing a joint objective function weighted by a preference vector. These approaches find fixed customized policies corresponding to preference vectors specified during training. However, the design constraints and objectives typically change dynamically in real-life scenarios. Furthermore, storing a policy for each potential preference is not scalable. Hence, obtaining a set of Pareto front solutions for the entire preference space in a given doma","authors_text":"Suat Gumussoy, Toygun Basaklar, Umit Y. Ogras","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-16T19:23:02Z","title":"PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.07914","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:f0b892712b130d7cbb3540fad4f2542e1d6b798fbff23dcd8558be8c5745701b","target":"record","created_at":"2026-07-05T06:14:56Z","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":"94e89f0306108b21090ec7e957b50b97de7ec95dad661bf3339bb2cfdd4b1e8a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-16T19:23:02Z","title_canon_sha256":"8581c8db545f923c37e9c1a122abe7824236c8d595e46235cd0ae528be55f12b"},"schema_version":"1.0","source":{"id":"2208.07914","kind":"arxiv","version":3}},"canonical_sha256":"b925808a2098475a44c11567ad6c557d715889bf066708455ecac0710f429756","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b925808a2098475a44c11567ad6c557d715889bf066708455ecac0710f429756","first_computed_at":"2026-07-05T06:14:56.354660Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:56.354660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T8+aNQc4L2brpQXMyNAwYCthy74YBAxiI+26UVWT/VUgV7FjgGIXIojzb/PdguUdtnXS6XNuVD0DQBLUpTC4DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:56.355187Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.07914","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0b892712b130d7cbb3540fad4f2542e1d6b798fbff23dcd8558be8c5745701b","sha256:ed0063de32a15157c1ac0479f858ecc35b77ff50d8f2185c6369c3b24c1457cf"],"state_sha256":"eec49ab39bed20e1f573fc00b29253434a79e8f2ff8bf91fe6942af1c8ba0d2d"}