{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YYMSSVLXWL7AUJ6B22W4L3MIJB","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":"5933640695d918aa61b5f25cdd304102a292f66cadcd86bf1a0414151fe7b743","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-02T20:21:09Z","title_canon_sha256":"65791ec8512f6fbce543b929fffd0f2d989081bdd27b4ea27e5d42e773e97547"},"schema_version":"1.0","source":{"id":"2402.01886","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01886","created_at":"2026-07-05T09:48:53Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01886v2","created_at":"2026-07-05T09:48:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01886","created_at":"2026-07-05T09:48:53Z"},{"alias_kind":"pith_short_12","alias_value":"YYMSSVLXWL7A","created_at":"2026-07-05T09:48:53Z"},{"alias_kind":"pith_short_16","alias_value":"YYMSSVLXWL7AUJ6B","created_at":"2026-07-05T09:48:53Z"},{"alias_kind":"pith_short_8","alias_value":"YYMSSVLX","created_at":"2026-07-05T09:48:53Z"}],"graph_snapshots":[{"event_id":"sha256:8e243966009cb072c008e26b4cfcbff837bf33f73441809f28c5945b408dfb72","target":"graph","created_at":"2026-07-05T09:48:53Z","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/2402.01886/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In Imitation Learning (IL), utilizing suboptimal and heterogeneous demonstrations presents a substantial challenge due to the varied nature of real-world data. However, standard IL algorithms consider these datasets as homogeneous, thereby inheriting the deficiencies of suboptimal demonstrators. Previous approaches to this issue rely on impractical assumptions like high-quality data subsets, confidence rankings, or explicit environmental knowledge. This paper introduces IRLEED, Inverse Reinforcement Learning by Estimating Expertise of Demonstrators, a novel framework that overcomes these hurdl","authors_text":"Mark Beliaev, Ramtin Pedarsani","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-02T20:21:09Z","title":"Inverse Reinforcement Learning by Estimating Expertise of Demonstrators"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01886","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":"sha256:534af3b1bb47b272292bd9140dbf3e0fd5f45e02e99ef40409b526c21a62df04","target":"record","created_at":"2026-07-05T09:48:53Z","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":"5933640695d918aa61b5f25cdd304102a292f66cadcd86bf1a0414151fe7b743","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-02T20:21:09Z","title_canon_sha256":"65791ec8512f6fbce543b929fffd0f2d989081bdd27b4ea27e5d42e773e97547"},"schema_version":"1.0","source":{"id":"2402.01886","kind":"arxiv","version":2}},"canonical_sha256":"c619295577b2fe0a27c1d6adc5ed88487a9cbe2ef442602b78e58b4f1158709d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c619295577b2fe0a27c1d6adc5ed88487a9cbe2ef442602b78e58b4f1158709d","first_computed_at":"2026-07-05T09:48:53.852771Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:53.852771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MGaL5ve7SNHB7t1Zr+Sfm7vAdhyYbBpwPaHQ83bJDo7k9PE8PIyQFZ9V0yJrZzAoQiRlIiJVNCaBndqEFVZGAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:53.853242Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.01886","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:534af3b1bb47b272292bd9140dbf3e0fd5f45e02e99ef40409b526c21a62df04","sha256:8e243966009cb072c008e26b4cfcbff837bf33f73441809f28c5945b408dfb72"],"state_sha256":"a47d96fefff3bb4165f6146abcaf75ff5391fbc066cd9933e022b0435bbdbf6d"}