{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UYYA2O237NREFAYGHWQXI67BZC","short_pith_number":"pith:UYYA2O23","schema_version":"1.0","canonical_sha256":"a6300d3b5bfb624283063da1747be1c8a0025d997b21034ce897b25c2d4fb199","source":{"kind":"arxiv","id":"2606.05588","version":1},"attestation_state":"computed","paper":{"title":"Auditing Demonstration Curation Metrics: Action-Only Scorers Fail on the Structural Defects That Degrade Imitation Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Aarav Bedi (University of California, Berkeley)","submitted_at":"2026-06-04T02:07:27Z","abstract_excerpt":"Imitation-learning policies inherit the quality of the demonstrations they are trained on, and a growing set of curation metrics promise to score and filter low-quality demonstrations automatically. These metrics are each validated on different data with different protocols, so it is unclear which of them actually identify the demonstrations that harm a policy. We build a controlled testbed in which demonstration defects are injected with known type, and audit seven curation metrics along two axes: how well each separates defective from clean demonstrations, and whether training a behavior-clo"},"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":"2606.05588","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-04T02:07:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3b3fe8ca02dcb3c695ba26f32bef98a4eae446380b0db698acf61c76426ec687","abstract_canon_sha256":"a6bcdff296d236d02f97fa361b7173ac102f52e30515a4fe5fcdefda0d7ae973"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:14:55.676412Z","signature_b64":"mGNjhyt0kaJb+8BD+eRY2rdXP4Qk6u5fmAzCBaNI4DZKDwrahFzx3kMsFimX1Gxy5X0/7s5Lqx/s7CXEbyzLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6300d3b5bfb624283063da1747be1c8a0025d997b21034ce897b25c2d4fb199","last_reissued_at":"2026-06-05T01:14:55.675967Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:14:55.675967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Auditing Demonstration Curation Metrics: Action-Only Scorers Fail on the Structural Defects That Degrade Imitation Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Aarav Bedi (University of California, Berkeley)","submitted_at":"2026-06-04T02:07:27Z","abstract_excerpt":"Imitation-learning policies inherit the quality of the demonstrations they are trained on, and a growing set of curation metrics promise to score and filter low-quality demonstrations automatically. These metrics are each validated on different data with different protocols, so it is unclear which of them actually identify the demonstrations that harm a policy. We build a controlled testbed in which demonstration defects are injected with known type, and audit seven curation metrics along two axes: how well each separates defective from clean demonstrations, and whether training a behavior-clo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05588","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/2606.05588/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":"2606.05588","created_at":"2026-06-05T01:14:55.676029+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05588v1","created_at":"2026-06-05T01:14:55.676029+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05588","created_at":"2026-06-05T01:14:55.676029+00:00"},{"alias_kind":"pith_short_12","alias_value":"UYYA2O237NRE","created_at":"2026-06-05T01:14:55.676029+00:00"},{"alias_kind":"pith_short_16","alias_value":"UYYA2O237NREFAYG","created_at":"2026-06-05T01:14:55.676029+00:00"},{"alias_kind":"pith_short_8","alias_value":"UYYA2O23","created_at":"2026-06-05T01:14:55.676029+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/UYYA2O237NREFAYGHWQXI67BZC","json":"https://pith.science/pith/UYYA2O237NREFAYGHWQXI67BZC.json","graph_json":"https://pith.science/api/pith-number/UYYA2O237NREFAYGHWQXI67BZC/graph.json","events_json":"https://pith.science/api/pith-number/UYYA2O237NREFAYGHWQXI67BZC/events.json","paper":"https://pith.science/paper/UYYA2O23"},"agent_actions":{"view_html":"https://pith.science/pith/UYYA2O237NREFAYGHWQXI67BZC","download_json":"https://pith.science/pith/UYYA2O237NREFAYGHWQXI67BZC.json","view_paper":"https://pith.science/paper/UYYA2O23","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05588&json=true","fetch_graph":"https://pith.science/api/pith-number/UYYA2O237NREFAYGHWQXI67BZC/graph.json","fetch_events":"https://pith.science/api/pith-number/UYYA2O237NREFAYGHWQXI67BZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UYYA2O237NREFAYGHWQXI67BZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UYYA2O237NREFAYGHWQXI67BZC/action/storage_attestation","attest_author":"https://pith.science/pith/UYYA2O237NREFAYGHWQXI67BZC/action/author_attestation","sign_citation":"https://pith.science/pith/UYYA2O237NREFAYGHWQXI67BZC/action/citation_signature","submit_replication":"https://pith.science/pith/UYYA2O237NREFAYGHWQXI67BZC/action/replication_record"}},"created_at":"2026-06-05T01:14:55.676029+00:00","updated_at":"2026-06-05T01:14:55.676029+00:00"}