{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:POIOR3BVCWLJXIRXSCHCEVB735","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":"2960b92e917c4277f6ee00a47ea50483e62396144aff1783f8f0c2c5c4aa54bd","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-15T09:42:33Z","title_canon_sha256":"6409228447b56229ff0a436bb63e80a8932ecdff2b068263bf62bf5d85dfa08f"},"schema_version":"1.0","source":{"id":"1909.06769","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.06769","created_at":"2026-07-05T00:04:49Z"},{"alias_kind":"arxiv_version","alias_value":"1909.06769v1","created_at":"2026-07-05T00:04:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.06769","created_at":"2026-07-05T00:04:49Z"},{"alias_kind":"pith_short_12","alias_value":"POIOR3BVCWLJ","created_at":"2026-07-05T00:04:49Z"},{"alias_kind":"pith_short_16","alias_value":"POIOR3BVCWLJXIRX","created_at":"2026-07-05T00:04:49Z"},{"alias_kind":"pith_short_8","alias_value":"POIOR3BV","created_at":"2026-07-05T00:04:49Z"}],"graph_snapshots":[{"event_id":"sha256:5750fa6651d08def0c8d6f049daddb9a71e6d8eb32f48e92a2382c791acadb59","target":"graph","created_at":"2026-07-05T00:04:49Z","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/1909.06769/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of imitation learning (IL) is to learn a good policy from high-quality demonstrations. However, the quality of demonstrations in reality can be diverse, since it is easier and cheaper to collect demonstrations from a mix of experts and amateurs. IL in such situations can be challenging, especially when the level of demonstrators' expertise is unknown. We propose a new IL method called \\underline{v}ariational \\underline{i}mitation \\underline{l}earning with \\underline{d}iverse-quality demonstrations (VILD), where we explicitly model the level of demonstrators' expertise with a probabili","authors_text":"Bo Han, Masashi Sugiyama, Mohammad Emtiyaz Khan, Voot Tangkaratt","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-15T09:42:33Z","title":"VILD: Variational Imitation Learning with Diverse-quality Demonstrations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.06769","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":"sha256:40e852812de2cdb3f624ced11cfc455ed2ab42a03ec55806cdd3931f5837d4f8","target":"record","created_at":"2026-07-05T00:04:49Z","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":"2960b92e917c4277f6ee00a47ea50483e62396144aff1783f8f0c2c5c4aa54bd","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-15T09:42:33Z","title_canon_sha256":"6409228447b56229ff0a436bb63e80a8932ecdff2b068263bf62bf5d85dfa08f"},"schema_version":"1.0","source":{"id":"1909.06769","kind":"arxiv","version":1}},"canonical_sha256":"7b90e8ec3515969ba237908e22543fdf4ae8ce23bec445533db8acc56fec4563","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b90e8ec3515969ba237908e22543fdf4ae8ce23bec445533db8acc56fec4563","first_computed_at":"2026-07-05T00:04:49.906083Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:04:49.906083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xQcsWZFcHzEn9+0PumI9c73oWTTskr2FITmxdxC1bOPYuv6MOuhw9WAGBN8pLm0GQ9FQUvjaN12vcjq4feybAA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:04:49.906474Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.06769","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40e852812de2cdb3f624ced11cfc455ed2ab42a03ec55806cdd3931f5837d4f8","sha256:5750fa6651d08def0c8d6f049daddb9a71e6d8eb32f48e92a2382c791acadb59"],"state_sha256":"dd81ba2f2d0b55df975008c4b82410d3713db8097c95f37b2d27dc362de40aea"}