{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:APAY47CJFEP72RE3YIDKGGNCDA","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":"e1e2f0f4d814aeec889a3f5c7ad33e31e0eda8bba2a8ce18ff295cb71096e0ee","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-27T20:29:38Z","title_canon_sha256":"36d28a95b69368294b6a618d1e414ab1ad884a968deb6c10963d25467706b7f8"},"schema_version":"1.0","source":{"id":"2110.14754","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.14754","created_at":"2026-07-05T03:51:45Z"},{"alias_kind":"arxiv_version","alias_value":"2110.14754v2","created_at":"2026-07-05T03:51:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.14754","created_at":"2026-07-05T03:51:45Z"},{"alias_kind":"pith_short_12","alias_value":"APAY47CJFEP7","created_at":"2026-07-05T03:51:45Z"},{"alias_kind":"pith_short_16","alias_value":"APAY47CJFEP72RE3","created_at":"2026-07-05T03:51:45Z"},{"alias_kind":"pith_short_8","alias_value":"APAY47CJ","created_at":"2026-07-05T03:51:45Z"}],"graph_snapshots":[{"event_id":"sha256:fd42b8b9279740669e1f5e7fc2dc26d2868834ceb5e8eb88dca21d66bf097669","target":"graph","created_at":"2026-07-05T03:51:45Z","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/2110.14754/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most existing imitation learning approaches assume the demonstrations are drawn from experts who are optimal, but relaxing this assumption enables us to use a wider range of data. Standard imitation learning may learn a suboptimal policy from demonstrations with varying optimality. Prior works use confidence scores or rankings to capture beneficial information from demonstrations with varying optimality, but they suffer from many limitations, e.g., manually annotated confidence scores or high average optimality of demonstrations. In this paper, we propose a general framework to learn from demo","authors_text":"Dorsa Sadigh, Songyuan Zhang, Yanan Sui, Zhangjie Cao","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-27T20:29:38Z","title":"Confidence-Aware Imitation Learning from Demonstrations with Varying Optimality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.14754","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":"sha256:6803f7438fc91db062a8de61f6ac19e955de8e02b71301b6172923d9ac735156","target":"record","created_at":"2026-07-05T03:51:45Z","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":"e1e2f0f4d814aeec889a3f5c7ad33e31e0eda8bba2a8ce18ff295cb71096e0ee","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-27T20:29:38Z","title_canon_sha256":"36d28a95b69368294b6a618d1e414ab1ad884a968deb6c10963d25467706b7f8"},"schema_version":"1.0","source":{"id":"2110.14754","kind":"arxiv","version":2}},"canonical_sha256":"03c18e7c49291ffd449bc206a319a2181a1cafbf166c375f70f20228278bb965","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03c18e7c49291ffd449bc206a319a2181a1cafbf166c375f70f20228278bb965","first_computed_at":"2026-07-05T03:51:45.246991Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:51:45.246991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nHRlUJweYFjXCsQTauGH8y2ZTb2aNuFarQVbsqAik/ii21eYUT4i/3rVfpTpSqZJQaDjGss9NsKkPp8zMJ5wDg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:51:45.247435Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.14754","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6803f7438fc91db062a8de61f6ac19e955de8e02b71301b6172923d9ac735156","sha256:fd42b8b9279740669e1f5e7fc2dc26d2868834ceb5e8eb88dca21d66bf097669"],"state_sha256":"e7a42c2fd10852106c646d96043ffc598466e5bf32821afc322a8a8622b8f611"}