{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZP3MM47FMIRL5DKODJRKVUXYFM","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":"04be3c3da5557ab4494ab82497c1a5c4c85e7a3ec554f89752abcf697cbedabe","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-16T16:16:54Z","title_canon_sha256":"ebb4212c9d1b9b3e3460248ea8eed288f52c738987863e46c0de3de4e8657cb4"},"schema_version":"1.0","source":{"id":"2606.18111","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.18111","created_at":"2026-06-19T16:10:48Z"},{"alias_kind":"arxiv_version","alias_value":"2606.18111v1","created_at":"2026-06-19T16:10:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18111","created_at":"2026-06-19T16:10:48Z"},{"alias_kind":"pith_short_12","alias_value":"ZP3MM47FMIRL","created_at":"2026-06-19T16:10:48Z"},{"alias_kind":"pith_short_16","alias_value":"ZP3MM47FMIRL5DKO","created_at":"2026-06-19T16:10:48Z"},{"alias_kind":"pith_short_8","alias_value":"ZP3MM47F","created_at":"2026-06-19T16:10:48Z"}],"graph_snapshots":[{"event_id":"sha256:912f4b5410dbb0b849c4d5beec53e0dbbc39cd41d6e7d7dc61149783d25d2cc3","target":"graph","created_at":"2026-06-19T16:10:48Z","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/2606.18111/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fairness is an important aspect of decision-making in multi-objective reinforcement learning (MORL), where policies must ensure both optimality and equity across multiple, potentially conflicting objectives. While single-policy MORL methods can learn fair policies for fixed user preferences using welfare functions such as the generalized Gini welfare function (GGF), they fail to provide the diverse set of policies necessary for dynamic or unknown user preferences. To address this limitation, we formalize the fair optimization problem in multi-policy MORL, where the goal is to learn a set of Pa","authors_text":"Peilang Li, Umer Siddique, Yongcan Cao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-16T16:16:54Z","title":"Learning Fair Pareto-Optimal Policies in Multi-Objective Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18111","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":"sha256:68d02d86a25213dc25306d83206cb45ba32170567e8a1174f8c8865382334257","target":"record","created_at":"2026-06-19T16:10:48Z","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":"04be3c3da5557ab4494ab82497c1a5c4c85e7a3ec554f89752abcf697cbedabe","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-16T16:16:54Z","title_canon_sha256":"ebb4212c9d1b9b3e3460248ea8eed288f52c738987863e46c0de3de4e8657cb4"},"schema_version":"1.0","source":{"id":"2606.18111","kind":"arxiv","version":1}},"canonical_sha256":"cbf6c673e56222be8d4e1a62aad2f82b1f9cc3d875b3d05090db00c97d721c5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cbf6c673e56222be8d4e1a62aad2f82b1f9cc3d875b3d05090db00c97d721c5f","first_computed_at":"2026-06-19T16:10:48.747879Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:10:48.747879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FqQaiNVtz/OslEcGe4+sV1B7ByFR4nCL5mshM1+9vX0W8LBpD3Xx+yOP3O+206K2mpEn5vUt8AvEudeLYYEuAw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:10:48.748218Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.18111","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68d02d86a25213dc25306d83206cb45ba32170567e8a1174f8c8865382334257","sha256:912f4b5410dbb0b849c4d5beec53e0dbbc39cd41d6e7d7dc61149783d25d2cc3"],"state_sha256":"44895819c1df81ef09b28be0a92842f063ada6ad206a7fad4c51f32ae71f8186"}