{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:INGFV7HYHBMJPZXXIDJ4CDCTPL","short_pith_number":"pith:INGFV7HY","schema_version":"1.0","canonical_sha256":"434c5afcf8385897e6f740d3c10c537afd9b7b2a841d4f02fb158c1347468cd0","source":{"kind":"arxiv","id":"2304.02364","version":2},"attestation_state":"computed","paper":{"title":"What's in a Name? Beyond Class Indices for Image Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jie Li, Kai Han, Sagar Vaze, Xiaohu Huang, Xuhui Jia, Yandong Li","submitted_at":"2023-04-05T11:01:23Z","abstract_excerpt":"Existing machine learning models demonstrate excellent performance in image object recognition after training on a large-scale dataset under full supervision. However, these models only learn to map an image to a predefined class index, without revealing the actual semantic meaning of the object in the image. In contrast, vision-language models like CLIP are able to assign semantic class names to unseen objects in a 'zero-shot' manner, though they are once again provided a pre-defined set of candidate names at test-time. In this paper, we reconsider the recognition problem and task a vision-la"},"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":"2304.02364","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-05T11:01:23Z","cross_cats_sorted":[],"title_canon_sha256":"43aed126429a2ee76d133ad2b1e64648c10db6df408cf328c831a7c1c94fbdf8","abstract_canon_sha256":"b539662c1e807632f5b585214f85c5a33d7fa21229f8b3db4baf4f724d2061b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:57.543633Z","signature_b64":"uXwJFPBqhc0/vz20ADoqemPap0kB8/JGQsIoq0r6hLj8VRCoZzJvBCseQquNvkXQ5IE6m4TEZDVSl55W6G5PDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"434c5afcf8385897e6f740d3c10c537afd9b7b2a841d4f02fb158c1347468cd0","last_reissued_at":"2026-07-05T08:48:57.543240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:57.543240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What's in a Name? Beyond Class Indices for Image Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jie Li, Kai Han, Sagar Vaze, Xiaohu Huang, Xuhui Jia, Yandong Li","submitted_at":"2023-04-05T11:01:23Z","abstract_excerpt":"Existing machine learning models demonstrate excellent performance in image object recognition after training on a large-scale dataset under full supervision. However, these models only learn to map an image to a predefined class index, without revealing the actual semantic meaning of the object in the image. In contrast, vision-language models like CLIP are able to assign semantic class names to unseen objects in a 'zero-shot' manner, though they are once again provided a pre-defined set of candidate names at test-time. In this paper, we reconsider the recognition problem and task a vision-la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.02364","kind":"arxiv","version":2},"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/2304.02364/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":"2304.02364","created_at":"2026-07-05T08:48:57.543294+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.02364v2","created_at":"2026-07-05T08:48:57.543294+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.02364","created_at":"2026-07-05T08:48:57.543294+00:00"},{"alias_kind":"pith_short_12","alias_value":"INGFV7HYHBMJ","created_at":"2026-07-05T08:48:57.543294+00:00"},{"alias_kind":"pith_short_16","alias_value":"INGFV7HYHBMJPZXX","created_at":"2026-07-05T08:48:57.543294+00:00"},{"alias_kind":"pith_short_8","alias_value":"INGFV7HY","created_at":"2026-07-05T08:48:57.543294+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/INGFV7HYHBMJPZXXIDJ4CDCTPL","json":"https://pith.science/pith/INGFV7HYHBMJPZXXIDJ4CDCTPL.json","graph_json":"https://pith.science/api/pith-number/INGFV7HYHBMJPZXXIDJ4CDCTPL/graph.json","events_json":"https://pith.science/api/pith-number/INGFV7HYHBMJPZXXIDJ4CDCTPL/events.json","paper":"https://pith.science/paper/INGFV7HY"},"agent_actions":{"view_html":"https://pith.science/pith/INGFV7HYHBMJPZXXIDJ4CDCTPL","download_json":"https://pith.science/pith/INGFV7HYHBMJPZXXIDJ4CDCTPL.json","view_paper":"https://pith.science/paper/INGFV7HY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.02364&json=true","fetch_graph":"https://pith.science/api/pith-number/INGFV7HYHBMJPZXXIDJ4CDCTPL/graph.json","fetch_events":"https://pith.science/api/pith-number/INGFV7HYHBMJPZXXIDJ4CDCTPL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/INGFV7HYHBMJPZXXIDJ4CDCTPL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/INGFV7HYHBMJPZXXIDJ4CDCTPL/action/storage_attestation","attest_author":"https://pith.science/pith/INGFV7HYHBMJPZXXIDJ4CDCTPL/action/author_attestation","sign_citation":"https://pith.science/pith/INGFV7HYHBMJPZXXIDJ4CDCTPL/action/citation_signature","submit_replication":"https://pith.science/pith/INGFV7HYHBMJPZXXIDJ4CDCTPL/action/replication_record"}},"created_at":"2026-07-05T08:48:57.543294+00:00","updated_at":"2026-07-05T08:48:57.543294+00:00"}