{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QVLOQRR2E5DGY6SFJJAHF6GLPV","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":"ac922139df4f2df036bcae549bdb0ea4bca040ff4f317c5a5e97c29370c852c7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-22T03:51:39Z","title_canon_sha256":"9a647296498246dd9298cda6ccaa1a052f72449a2c68e9ba164cf4950815ac7e"},"schema_version":"1.0","source":{"id":"2408.12110","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.12110","created_at":"2026-07-05T08:58:04Z"},{"alias_kind":"arxiv_version","alias_value":"2408.12110v1","created_at":"2026-07-05T08:58:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12110","created_at":"2026-07-05T08:58:04Z"},{"alias_kind":"pith_short_12","alias_value":"QVLOQRR2E5DG","created_at":"2026-07-05T08:58:04Z"},{"alias_kind":"pith_short_16","alias_value":"QVLOQRR2E5DGY6SF","created_at":"2026-07-05T08:58:04Z"},{"alias_kind":"pith_short_8","alias_value":"QVLOQRR2","created_at":"2026-07-05T08:58:04Z"}],"graph_snapshots":[{"event_id":"sha256:ab044af09e8c1c0d9f7150203acfd818e7409996ed80663f4cf4a00b682d38ab","target":"graph","created_at":"2026-07-05T08:58:04Z","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/2408.12110/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data-driven offline reinforcement learning and imitation learning approaches have been gaining popularity in addressing sequential decision-making problems. Yet, these approaches rarely consider learning Pareto-optimal policies from a limited pool of expert datasets. This becomes particularly marked due to practical limitations in obtaining comprehensive datasets for all preferences, where multiple conflicting objectives exist and each expert might hold a unique optimization preference for these objectives. In this paper, we adapt inverse reinforcement learning (IRL) by using reward distance e","authors_text":"Honguk Woo, Minjong Yoo, Woo Kyung Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-22T03:51:39Z","title":"Pareto Inverse Reinforcement Learning for Diverse Expert Policy Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12110","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":"sha256:91354ae062e02f2e2522d816806569da341e796a9eeda5d16abce7e401e06575","target":"record","created_at":"2026-07-05T08:58:04Z","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":"ac922139df4f2df036bcae549bdb0ea4bca040ff4f317c5a5e97c29370c852c7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-22T03:51:39Z","title_canon_sha256":"9a647296498246dd9298cda6ccaa1a052f72449a2c68e9ba164cf4950815ac7e"},"schema_version":"1.0","source":{"id":"2408.12110","kind":"arxiv","version":1}},"canonical_sha256":"8556e8463a27466c7a454a4072f8cb7d4814ac6cc4856ebee8192430b6ff1bf9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8556e8463a27466c7a454a4072f8cb7d4814ac6cc4856ebee8192430b6ff1bf9","first_computed_at":"2026-07-05T08:58:04.217245Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:58:04.217245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6/tkb2h91CnYQrPFHPF7R/fY2Etp9XU2Mp/96yGJVDl74PpBvGJpA49E7F3tvGzQ2xjVcq8L47wVRriK8qxjCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:58:04.217661Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.12110","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91354ae062e02f2e2522d816806569da341e796a9eeda5d16abce7e401e06575","sha256:ab044af09e8c1c0d9f7150203acfd818e7409996ed80663f4cf4a00b682d38ab"],"state_sha256":"06b1c57e3c181bb66a2e373c34ca6531a66e1e1644332ae6953a80c9e03abb6d"}