{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:D7CG5SPWNXG63ZTVHZ76BAYBNJ","short_pith_number":"pith:D7CG5SPW","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"},"canonical_sha256":"1fc46ec9f66dcdede6753e7fe083016a457fa437d04af02ce9e5e2f88c86d583","source":{"kind":"arxiv","id":"2603.03454","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.03454","created_at":"2026-05-22T01:03:59Z"},{"alias_kind":"arxiv_version","alias_value":"2603.03454v2","created_at":"2026-05-22T01:03:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.03454","created_at":"2026-05-22T01:03:59Z"},{"alias_kind":"pith_short_12","alias_value":"D7CG5SPWNXG6","created_at":"2026-05-22T01:03:59Z"},{"alias_kind":"pith_short_16","alias_value":"D7CG5SPWNXG63ZTV","created_at":"2026-05-22T01:03:59Z"},{"alias_kind":"pith_short_8","alias_value":"D7CG5SPW","created_at":"2026-05-22T01:03:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:D7CG5SPWNXG63ZTVHZ76BAYBNJ","target":"record","payload":{"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"},"canonical_sha256":"1fc46ec9f66dcdede6753e7fe083016a457fa437d04af02ce9e5e2f88c86d583","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"},"source_kind":"arxiv","source_id":"2603.03454","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T01:03:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RhwiT43gfZBt2XHunRdA/xtQu+fDuyZKYx1NeOM4bBuucAx+4bnb0Q9zYUGumo9RuAl72hi5SK3RsWSdn8okDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T04:00:54.695631Z"},"content_sha256":"69d83ee40ebb2465d0c981a92eb29406f6ec1bdf4e23f937c60bce1cc0ee5edb","schema_version":"1.0","event_id":"sha256:69d83ee40ebb2465d0c981a92eb29406f6ec1bdf4e23f937c60bce1cc0ee5edb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:D7CG5SPWNXG63ZTVHZ76BAYBNJ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T01:03:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ddR27+lbNxB1eyEBpQquLuB62bBwsuMSNOpjtu62KyVA2Oahev52Ez8SxjIevkW/nqVlkN9Ny7u58jshy5yBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T04:00:54.696070Z"},"content_sha256":"333284788f05f4bc214f1ba556d6ee0c34ed735065133d0f80dc52b8c03ddaf1","schema_version":"1.0","event_id":"sha256:333284788f05f4bc214f1ba556d6ee0c34ed735065133d0f80dc52b8c03ddaf1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D7CG5SPWNXG63ZTVHZ76BAYBNJ/bundle.json","state_url":"https://pith.science/pith/D7CG5SPWNXG63ZTVHZ76BAYBNJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D7CG5SPWNXG63ZTVHZ76BAYBNJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-30T04:00:54Z","links":{"resolver":"https://pith.science/pith/D7CG5SPWNXG63ZTVHZ76BAYBNJ","bundle":"https://pith.science/pith/D7CG5SPWNXG63ZTVHZ76BAYBNJ/bundle.json","state":"https://pith.science/pith/D7CG5SPWNXG63ZTVHZ76BAYBNJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D7CG5SPWNXG63ZTVHZ76BAYBNJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:D7CG5SPWNXG63ZTVHZ76BAYBNJ","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":"efecc985fb489d26a3f5b4e7101d36e9a53257a5bc7f6fb25ecc8f90a955e299","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-03T19:12:06Z","title_canon_sha256":"22a2d6d90585d5fd3d21ca16e0d8f3299217906e40d8b2eb4997012b62011958"},"schema_version":"1.0","source":{"id":"2603.03454","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.03454","created_at":"2026-05-22T01:03:59Z"},{"alias_kind":"arxiv_version","alias_value":"2603.03454v2","created_at":"2026-05-22T01:03:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.03454","created_at":"2026-05-22T01:03:59Z"},{"alias_kind":"pith_short_12","alias_value":"D7CG5SPWNXG6","created_at":"2026-05-22T01:03:59Z"},{"alias_kind":"pith_short_16","alias_value":"D7CG5SPWNXG63ZTV","created_at":"2026-05-22T01:03:59Z"},{"alias_kind":"pith_short_8","alias_value":"D7CG5SPW","created_at":"2026-05-22T01:03:59Z"}],"graph_snapshots":[{"event_id":"sha256:333284788f05f4bc214f1ba556d6ee0c34ed735065133d0f80dc52b8c03ddaf1","target":"graph","created_at":"2026-05-22T01:03:59Z","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/2603.03454/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aleksey Evstratovskiy, Karim Galliamov, Peter Adema, Ross Geurts","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-03T19:12:06Z","title":"[Re] FairDICE: A Fair Tradeoff in Multi-objective Offline RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.03454","kind":"arxiv","version":2},"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":"sha256:69d83ee40ebb2465d0c981a92eb29406f6ec1bdf4e23f937c60bce1cc0ee5edb","target":"record","created_at":"2026-05-22T01:03:59Z","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":"efecc985fb489d26a3f5b4e7101d36e9a53257a5bc7f6fb25ecc8f90a955e299","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-03T19:12:06Z","title_canon_sha256":"22a2d6d90585d5fd3d21ca16e0d8f3299217906e40d8b2eb4997012b62011958"},"schema_version":"1.0","source":{"id":"2603.03454","kind":"arxiv","version":2}},"canonical_sha256":"1fc46ec9f66dcdede6753e7fe083016a457fa437d04af02ce9e5e2f88c86d583","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1fc46ec9f66dcdede6753e7fe083016a457fa437d04af02ce9e5e2f88c86d583","first_computed_at":"2026-05-22T01:03:59.459695Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:59.459695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3M2DtzenvpdIEbdEJ0cdTWmKEbx3/021QfBDczMfVcmYNkNz3E9JKjfUNoObYf2HGfeK0RdiIP98crYn7em1DQ==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:59.460498Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.03454","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69d83ee40ebb2465d0c981a92eb29406f6ec1bdf4e23f937c60bce1cc0ee5edb","sha256:333284788f05f4bc214f1ba556d6ee0c34ed735065133d0f80dc52b8c03ddaf1"],"state_sha256":"9cc695e7a34cd8a5e3fd34837bed37641fb9eb44701738a3f6bd1920c842d87a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fqaMr2p4PSRLXkolsEKApfKON0Xr6JqpgkaKW0zV4qGBOzWAemAsA5W/BrH1c8GlA1js3bpV8WdvzaodAHs8Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T04:00:54.698356Z","bundle_sha256":"f01d5e0d535731ce8f0c9a20041d88bf4b14d5ca4d2088ee869ff1384ea8813d"}}