{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LROKOL23P3PWJNTM3JBDT6FLFC","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":"ccf4c2f3e2154891f540909f5d2889e944c0c96343081639e682767d81ecd672","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-27T17:59:33Z","title_canon_sha256":"449fa8b2ccda3cd4e013b988d24cd65d82fb1bae40d1134383762a31bee089ca"},"schema_version":"1.0","source":{"id":"2303.15441","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.15441","created_at":"2026-07-05T05:55:05Z"},{"alias_kind":"arxiv_version","alias_value":"2303.15441v1","created_at":"2026-07-05T05:55:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.15441","created_at":"2026-07-05T05:55:05Z"},{"alias_kind":"pith_short_12","alias_value":"LROKOL23P3PW","created_at":"2026-07-05T05:55:05Z"},{"alias_kind":"pith_short_16","alias_value":"LROKOL23P3PWJNTM","created_at":"2026-07-05T05:55:05Z"},{"alias_kind":"pith_short_8","alias_value":"LROKOL23","created_at":"2026-07-05T05:55:05Z"}],"graph_snapshots":[{"event_id":"sha256:a12c827ff03c98501efa9fd3fdf729290dc244fdcb162e1fb0361ebe5a5e0edf","target":"graph","created_at":"2026-07-05T05:55:05Z","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/2303.15441/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When it comes to deploying deep vision models, the behavior of these systems must be explicable to ensure confidence in their reliability and fairness. A common approach to evaluate deep learning models is to build a labeled test set with attributes of interest and assess how well it performs. However, creating a balanced test set (i.e., one that is uniformly sampled over all the important traits) is often time-consuming, expensive, and prone to mistakes. The question we try to address is: can we evaluate the sensitivity of deep learning models to arbitrary visual attributes without an annotat","authors_text":"Chen Henry Wu, Dong Huang, Fernando De la Torre, Jinqi Luo, Zhaoning Wang","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-27T17:59:33Z","title":"Zero-shot Model Diagnosis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.15441","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":"sha256:01503d3dabd4227ca9d15feac325942ef13fc1d4902bcff12fcbe683d8ef87c7","target":"record","created_at":"2026-07-05T05:55:05Z","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":"ccf4c2f3e2154891f540909f5d2889e944c0c96343081639e682767d81ecd672","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-27T17:59:33Z","title_canon_sha256":"449fa8b2ccda3cd4e013b988d24cd65d82fb1bae40d1134383762a31bee089ca"},"schema_version":"1.0","source":{"id":"2303.15441","kind":"arxiv","version":1}},"canonical_sha256":"5c5ca72f5b7edf64b66cda4239f8ab28869f568ff3634e1b2bfbd08e4022ff64","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c5ca72f5b7edf64b66cda4239f8ab28869f568ff3634e1b2bfbd08e4022ff64","first_computed_at":"2026-07-05T05:55:05.178358Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:55:05.178358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RoTiNGUNvO3ALeJEyK2hhn15eGlYgjOgQleR73DJwput+VeJc3hfGsB9b/HEInrDUGpnzR6Frm3xiBaM5wpaCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:55:05.178756Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.15441","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01503d3dabd4227ca9d15feac325942ef13fc1d4902bcff12fcbe683d8ef87c7","sha256:a12c827ff03c98501efa9fd3fdf729290dc244fdcb162e1fb0361ebe5a5e0edf"],"state_sha256":"757f020f5fc185caab5cf6c198b9e635206f64cc21351ca53f79c706ad544f59"}