{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:A3Q7R62LJCWDZT7NUDX4EZDYA7","short_pith_number":"pith:A3Q7R62L","schema_version":"1.0","canonical_sha256":"06e1f8fb4b48ac3ccfeda0efc2647807e95b699c8792d48e30b154b499f58680","source":{"kind":"arxiv","id":"2302.04269","version":1},"attestation_state":"computed","paper":{"title":"Diagnosing and Rectifying Vision Models using Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"James Zou, Jeff Z. HaoChen, Kuan-Chieh Wang, Serena Yeung, Shih-Cheng Huang, Yuhui Zhang","submitted_at":"2023-02-08T18:59:42Z","abstract_excerpt":"Recent multi-modal contrastive learning models have demonstrated the ability to learn an embedding space suitable for building strong vision classifiers, by leveraging the rich information in large-scale image-caption datasets. Our work highlights a distinct advantage of this multi-modal embedding space: the ability to diagnose vision classifiers through natural language. The traditional process of diagnosing model behaviors in deployment settings involves labor-intensive data acquisition and annotation. Our proposed method can discover high-error data slices, identify influential attributes a"},"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":"2302.04269","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-08T18:59:42Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"5d777786d050a28694ac9d1a1a352c7f600c965e81b3e73c749949894f592dcd","abstract_canon_sha256":"f5729bc36a8b6a30164c4865ef97e1fc989b14cd8a1d4caa06006c09d9a4bd92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:02.685063Z","signature_b64":"etND4w11lPgwmhAID1ItQ4bdcrzyp3F+iiJwYR/ZIEVyG0foeriTVjfwnrr/hmm/rUrTzKs+68dgnvt622zEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06e1f8fb4b48ac3ccfeda0efc2647807e95b699c8792d48e30b154b499f58680","last_reissued_at":"2026-07-05T05:40:02.684678Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:02.684678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diagnosing and Rectifying Vision Models using Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"James Zou, Jeff Z. HaoChen, Kuan-Chieh Wang, Serena Yeung, Shih-Cheng Huang, Yuhui Zhang","submitted_at":"2023-02-08T18:59:42Z","abstract_excerpt":"Recent multi-modal contrastive learning models have demonstrated the ability to learn an embedding space suitable for building strong vision classifiers, by leveraging the rich information in large-scale image-caption datasets. Our work highlights a distinct advantage of this multi-modal embedding space: the ability to diagnose vision classifiers through natural language. The traditional process of diagnosing model behaviors in deployment settings involves labor-intensive data acquisition and annotation. Our proposed method can discover high-error data slices, identify influential attributes a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04269","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/2302.04269/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":"2302.04269","created_at":"2026-07-05T05:40:02.684736+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.04269v1","created_at":"2026-07-05T05:40:02.684736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04269","created_at":"2026-07-05T05:40:02.684736+00:00"},{"alias_kind":"pith_short_12","alias_value":"A3Q7R62LJCWD","created_at":"2026-07-05T05:40:02.684736+00:00"},{"alias_kind":"pith_short_16","alias_value":"A3Q7R62LJCWDZT7N","created_at":"2026-07-05T05:40:02.684736+00:00"},{"alias_kind":"pith_short_8","alias_value":"A3Q7R62L","created_at":"2026-07-05T05:40:02.684736+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/A3Q7R62LJCWDZT7NUDX4EZDYA7","json":"https://pith.science/pith/A3Q7R62LJCWDZT7NUDX4EZDYA7.json","graph_json":"https://pith.science/api/pith-number/A3Q7R62LJCWDZT7NUDX4EZDYA7/graph.json","events_json":"https://pith.science/api/pith-number/A3Q7R62LJCWDZT7NUDX4EZDYA7/events.json","paper":"https://pith.science/paper/A3Q7R62L"},"agent_actions":{"view_html":"https://pith.science/pith/A3Q7R62LJCWDZT7NUDX4EZDYA7","download_json":"https://pith.science/pith/A3Q7R62LJCWDZT7NUDX4EZDYA7.json","view_paper":"https://pith.science/paper/A3Q7R62L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.04269&json=true","fetch_graph":"https://pith.science/api/pith-number/A3Q7R62LJCWDZT7NUDX4EZDYA7/graph.json","fetch_events":"https://pith.science/api/pith-number/A3Q7R62LJCWDZT7NUDX4EZDYA7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A3Q7R62LJCWDZT7NUDX4EZDYA7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A3Q7R62LJCWDZT7NUDX4EZDYA7/action/storage_attestation","attest_author":"https://pith.science/pith/A3Q7R62LJCWDZT7NUDX4EZDYA7/action/author_attestation","sign_citation":"https://pith.science/pith/A3Q7R62LJCWDZT7NUDX4EZDYA7/action/citation_signature","submit_replication":"https://pith.science/pith/A3Q7R62LJCWDZT7NUDX4EZDYA7/action/replication_record"}},"created_at":"2026-07-05T05:40:02.684736+00:00","updated_at":"2026-07-05T05:40:02.684736+00:00"}