{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7GQMUX5RMYMQZQ3KJIK3EBGRTW","short_pith_number":"pith:7GQMUX5R","schema_version":"1.0","canonical_sha256":"f9a0ca5fb166190cc36a4a15b204d19d9c7ee324a62e46d1714c7fb02b70abd9","source":{"kind":"arxiv","id":"2404.16717","version":1},"attestation_state":"computed","paper":{"title":"Embracing Diversity: Interpretable Zero-shot classification beyond one vector per class","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CV","authors_text":"Diane Bouchacourt, Mark Ibrahim, Mazda Moayeri, Michael Rabbat","submitted_at":"2024-04-25T16:29:06Z","abstract_excerpt":"Vision-language models enable open-world classification of objects without the need for any retraining. While this zero-shot paradigm marks a significant advance, even today's best models exhibit skewed performance when objects are dissimilar from their typical depiction. Real world objects such as pears appear in a variety of forms -- from diced to whole, on a table or in a bowl -- yet standard VLM classifiers map all instances of a class to a \\it{single vector based on the class label}. We argue that to represent this rich diversity within a class, zero-shot classification should move beyond"},"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":"2404.16717","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-25T16:29:06Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"982d3d7216f7d29fb517ec897453377ee31a3f60e848290dceb0b01642af48b8","abstract_canon_sha256":"adbc5303fa8cbf7277f1658d4e5abd305bdf9307cdb9326220d68f1a4857f6cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:11.706405Z","signature_b64":"j4lA6rWhPvYqP1NFZd4VXKpKu9NJz6N7lZMHi8q5nCbARvSHkSnEtn2YLtQNyB99Al2kObIFy7970bvohFvaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9a0ca5fb166190cc36a4a15b204d19d9c7ee324a62e46d1714c7fb02b70abd9","last_reissued_at":"2026-07-05T08:12:11.705973Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:11.705973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Embracing Diversity: Interpretable Zero-shot classification beyond one vector per class","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CV","authors_text":"Diane Bouchacourt, Mark Ibrahim, Mazda Moayeri, Michael Rabbat","submitted_at":"2024-04-25T16:29:06Z","abstract_excerpt":"Vision-language models enable open-world classification of objects without the need for any retraining. While this zero-shot paradigm marks a significant advance, even today's best models exhibit skewed performance when objects are dissimilar from their typical depiction. Real world objects such as pears appear in a variety of forms -- from diced to whole, on a table or in a bowl -- yet standard VLM classifiers map all instances of a class to a \\it{single vector based on the class label}. We argue that to represent this rich diversity within a class, zero-shot classification should move beyond"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.16717","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/2404.16717/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":"2404.16717","created_at":"2026-07-05T08:12:11.706037+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.16717v1","created_at":"2026-07-05T08:12:11.706037+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16717","created_at":"2026-07-05T08:12:11.706037+00:00"},{"alias_kind":"pith_short_12","alias_value":"7GQMUX5RMYMQ","created_at":"2026-07-05T08:12:11.706037+00:00"},{"alias_kind":"pith_short_16","alias_value":"7GQMUX5RMYMQZQ3K","created_at":"2026-07-05T08:12:11.706037+00:00"},{"alias_kind":"pith_short_8","alias_value":"7GQMUX5R","created_at":"2026-07-05T08:12:11.706037+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/7GQMUX5RMYMQZQ3KJIK3EBGRTW","json":"https://pith.science/pith/7GQMUX5RMYMQZQ3KJIK3EBGRTW.json","graph_json":"https://pith.science/api/pith-number/7GQMUX5RMYMQZQ3KJIK3EBGRTW/graph.json","events_json":"https://pith.science/api/pith-number/7GQMUX5RMYMQZQ3KJIK3EBGRTW/events.json","paper":"https://pith.science/paper/7GQMUX5R"},"agent_actions":{"view_html":"https://pith.science/pith/7GQMUX5RMYMQZQ3KJIK3EBGRTW","download_json":"https://pith.science/pith/7GQMUX5RMYMQZQ3KJIK3EBGRTW.json","view_paper":"https://pith.science/paper/7GQMUX5R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.16717&json=true","fetch_graph":"https://pith.science/api/pith-number/7GQMUX5RMYMQZQ3KJIK3EBGRTW/graph.json","fetch_events":"https://pith.science/api/pith-number/7GQMUX5RMYMQZQ3KJIK3EBGRTW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7GQMUX5RMYMQZQ3KJIK3EBGRTW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7GQMUX5RMYMQZQ3KJIK3EBGRTW/action/storage_attestation","attest_author":"https://pith.science/pith/7GQMUX5RMYMQZQ3KJIK3EBGRTW/action/author_attestation","sign_citation":"https://pith.science/pith/7GQMUX5RMYMQZQ3KJIK3EBGRTW/action/citation_signature","submit_replication":"https://pith.science/pith/7GQMUX5RMYMQZQ3KJIK3EBGRTW/action/replication_record"}},"created_at":"2026-07-05T08:12:11.706037+00:00","updated_at":"2026-07-05T08:12:11.706037+00:00"}