{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:D7CG5SPWNXG63ZTVHZ76BAYBNJ","short_pith_number":"pith:D7CG5SPW","schema_version":"1.0","canonical_sha256":"1fc46ec9f66dcdede6753e7fe083016a457fa437d04af02ce9e5e2f88c86d583","source":{"kind":"arxiv","id":"2603.03454","version":2},"attestation_state":"computed","paper":{"title":"[Re] FairDICE: A Fair Tradeoff in Multi-objective Offline RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aleksey Evstratovskiy, Karim Galliamov, Peter Adema, Ross Geurts","submitted_at":"2026-03-03T19:12:06Z","abstract_excerpt":"Offline Reinforcement Learning (RL) is an emerging field of RL in which policies are learned solely from demonstrations. Within offline RL, some environments involve balancing multiple objectives, but existing multi-objective offline RL algorithms do not provide an efficient way to find a fair compromise. FairDICE (see arXiv:2506.08062v2) seeks to fill this gap by adapting OptiDICE (an offline RL algorithm) to automatically learn weights for multiple objectives to e.g. incentivise fairness among objectives. As this would be a valuable contribution, this replication study examines the replicabi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2603.03454","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-03T19:12:06Z","cross_cats_sorted":[],"title_canon_sha256":"22a2d6d90585d5fd3d21ca16e0d8f3299217906e40d8b2eb4997012b62011958","abstract_canon_sha256":"efecc985fb489d26a3f5b4e7101d36e9a53257a5bc7f6fb25ecc8f90a955e299"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:59.460498Z","signature_b64":"3M2DtzenvpdIEbdEJ0cdTWmKEbx3/021QfBDczMfVcmYNkNz3E9JKjfUNoObYf2HGfeK0RdiIP98crYn7em1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fc46ec9f66dcdede6753e7fe083016a457fa437d04af02ce9e5e2f88c86d583","last_reissued_at":"2026-05-22T01:03:59.459695Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:59.459695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"[Re] FairDICE: A Fair Tradeoff in Multi-objective Offline RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aleksey Evstratovskiy, Karim Galliamov, Peter Adema, Ross Geurts","submitted_at":"2026-03-03T19:12:06Z","abstract_excerpt":"Offline Reinforcement Learning (RL) is an emerging field of RL in which policies are learned solely from demonstrations. Within offline RL, some environments involve balancing multiple objectives, but existing multi-objective offline RL algorithms do not provide an efficient way to find a fair compromise. FairDICE (see arXiv:2506.08062v2) seeks to fill this gap by adapting OptiDICE (an offline RL algorithm) to automatically learn weights for multiple objectives to e.g. incentivise fairness among objectives. As this would be a valuable contribution, this replication study examines the replicabi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.03454","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.03454/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2603.03454","created_at":"2026-05-22T01:03:59.459799+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.03454v2","created_at":"2026-05-22T01:03:59.459799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.03454","created_at":"2026-05-22T01:03:59.459799+00:00"},{"alias_kind":"pith_short_12","alias_value":"D7CG5SPWNXG6","created_at":"2026-05-22T01:03:59.459799+00:00"},{"alias_kind":"pith_short_16","alias_value":"D7CG5SPWNXG63ZTV","created_at":"2026-05-22T01:03:59.459799+00:00"},{"alias_kind":"pith_short_8","alias_value":"D7CG5SPW","created_at":"2026-05-22T01:03:59.459799+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D7CG5SPWNXG63ZTVHZ76BAYBNJ","json":"https://pith.science/pith/D7CG5SPWNXG63ZTVHZ76BAYBNJ.json","graph_json":"https://pith.science/api/pith-number/D7CG5SPWNXG63ZTVHZ76BAYBNJ/graph.json","events_json":"https://pith.science/api/pith-number/D7CG5SPWNXG63ZTVHZ76BAYBNJ/events.json","paper":"https://pith.science/paper/D7CG5SPW"},"agent_actions":{"view_html":"https://pith.science/pith/D7CG5SPWNXG63ZTVHZ76BAYBNJ","download_json":"https://pith.science/pith/D7CG5SPWNXG63ZTVHZ76BAYBNJ.json","view_paper":"https://pith.science/paper/D7CG5SPW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.03454&json=true","fetch_graph":"https://pith.science/api/pith-number/D7CG5SPWNXG63ZTVHZ76BAYBNJ/graph.json","fetch_events":"https://pith.science/api/pith-number/D7CG5SPWNXG63ZTVHZ76BAYBNJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D7CG5SPWNXG63ZTVHZ76BAYBNJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D7CG5SPWNXG63ZTVHZ76BAYBNJ/action/storage_attestation","attest_author":"https://pith.science/pith/D7CG5SPWNXG63ZTVHZ76BAYBNJ/action/author_attestation","sign_citation":"https://pith.science/pith/D7CG5SPWNXG63ZTVHZ76BAYBNJ/action/citation_signature","submit_replication":"https://pith.science/pith/D7CG5SPWNXG63ZTVHZ76BAYBNJ/action/replication_record"}},"created_at":"2026-05-22T01:03:59.459799+00:00","updated_at":"2026-05-22T01:03:59.459799+00:00"}