{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OWTECLP5DOBKWOFD5OBICO3ZZH","short_pith_number":"pith:OWTECLP5","schema_version":"1.0","canonical_sha256":"75a6412dfd1b82ab38a3eb82813b79c9f0f32730b157283b8a4b8938f5158d9c","source":{"kind":"arxiv","id":"2205.04195","version":1},"attestation_state":"computed","paper":{"title":"Disturbance-Injected Robust Imitation Learning with Task Achievement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Brendan Michael, Hanbit Oh, Hikaru Sasaki, Hirotaka Tahara, Takamitsu Matsubara","submitted_at":"2022-05-09T11:25:12Z","abstract_excerpt":"Robust imitation learning using disturbance injections overcomes issues of limited variation in demonstrations. However, these methods assume demonstrations are optimal, and that policy stabilization can be learned via simple augmentations. In real-world scenarios, demonstrations are often of diverse-quality, and disturbance injection instead learns sub-optimal policies that fail to replicate desired behavior. To address this issue, this paper proposes a novel imitation learning framework that combines both policy robustification and optimal demonstration learning. Specifically, this combinato"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2205.04195","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-05-09T11:25:12Z","cross_cats_sorted":[],"title_canon_sha256":"90f25259be8fc316e43a1c33ae975fd178346330d3b98ac13268383fba229183","abstract_canon_sha256":"5334695cc5b50679a3f0542c50da478b3e50db000db55759ea504f4a0b1b7c52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:21:22.351492Z","signature_b64":"PPsdPMC4gSQdydn9Z7egp4VvVnGa0ipTDrmNKMYzOTlXgq+//LtH0xz+kb6w4NLl/rQpdx/EfR7s1yTF/GsMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75a6412dfd1b82ab38a3eb82813b79c9f0f32730b157283b8a4b8938f5158d9c","last_reissued_at":"2026-07-05T04:21:22.351084Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:21:22.351084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disturbance-Injected Robust Imitation Learning with Task Achievement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Brendan Michael, Hanbit Oh, Hikaru Sasaki, Hirotaka Tahara, Takamitsu Matsubara","submitted_at":"2022-05-09T11:25:12Z","abstract_excerpt":"Robust imitation learning using disturbance injections overcomes issues of limited variation in demonstrations. However, these methods assume demonstrations are optimal, and that policy stabilization can be learned via simple augmentations. In real-world scenarios, demonstrations are often of diverse-quality, and disturbance injection instead learns sub-optimal policies that fail to replicate desired behavior. To address this issue, this paper proposes a novel imitation learning framework that combines both policy robustification and optimal demonstration learning. Specifically, this combinato"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.04195","kind":"arxiv","version":1},"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/2205.04195/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2205.04195","created_at":"2026-07-05T04:21:22.351143+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.04195v1","created_at":"2026-07-05T04:21:22.351143+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.04195","created_at":"2026-07-05T04:21:22.351143+00:00"},{"alias_kind":"pith_short_12","alias_value":"OWTECLP5DOBK","created_at":"2026-07-05T04:21:22.351143+00:00"},{"alias_kind":"pith_short_16","alias_value":"OWTECLP5DOBKWOFD","created_at":"2026-07-05T04:21:22.351143+00:00"},{"alias_kind":"pith_short_8","alias_value":"OWTECLP5","created_at":"2026-07-05T04:21:22.351143+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OWTECLP5DOBKWOFD5OBICO3ZZH","json":"https://pith.science/pith/OWTECLP5DOBKWOFD5OBICO3ZZH.json","graph_json":"https://pith.science/api/pith-number/OWTECLP5DOBKWOFD5OBICO3ZZH/graph.json","events_json":"https://pith.science/api/pith-number/OWTECLP5DOBKWOFD5OBICO3ZZH/events.json","paper":"https://pith.science/paper/OWTECLP5"},"agent_actions":{"view_html":"https://pith.science/pith/OWTECLP5DOBKWOFD5OBICO3ZZH","download_json":"https://pith.science/pith/OWTECLP5DOBKWOFD5OBICO3ZZH.json","view_paper":"https://pith.science/paper/OWTECLP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.04195&json=true","fetch_graph":"https://pith.science/api/pith-number/OWTECLP5DOBKWOFD5OBICO3ZZH/graph.json","fetch_events":"https://pith.science/api/pith-number/OWTECLP5DOBKWOFD5OBICO3ZZH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OWTECLP5DOBKWOFD5OBICO3ZZH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OWTECLP5DOBKWOFD5OBICO3ZZH/action/storage_attestation","attest_author":"https://pith.science/pith/OWTECLP5DOBKWOFD5OBICO3ZZH/action/author_attestation","sign_citation":"https://pith.science/pith/OWTECLP5DOBKWOFD5OBICO3ZZH/action/citation_signature","submit_replication":"https://pith.science/pith/OWTECLP5DOBKWOFD5OBICO3ZZH/action/replication_record"}},"created_at":"2026-07-05T04:21:22.351143+00:00","updated_at":"2026-07-05T04:21:22.351143+00:00"}