{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HXLXWFAMWL7HQGT4P36BJIW4RT","short_pith_number":"pith:HXLXWFAM","schema_version":"1.0","canonical_sha256":"3dd77b140cb2fe781a7c7efc14a2dc8ce092fff44a2805ec0faf01a45b064677","source":{"kind":"arxiv","id":"2411.05357","version":2},"attestation_state":"computed","paper":{"title":"Enhancing Visual Classification using Comparative Descriptors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gawon Seo, Geunyoung Jung, Hankyeol Lee, Jiyoung Jung, Kyungwoo Song, Wonseok Choi","submitted_at":"2024-11-08T06:28:02Z","abstract_excerpt":"The performance of vision-language models (VLMs), such as CLIP, in visual classification tasks, has been enhanced by leveraging semantic knowledge from large language models (LLMs), including GPT. Recent studies have shown that in zero-shot classification tasks, descriptors incorporating additional cues, high-level concepts, or even random characters often outperform those using only the category name. In many classification tasks, while the top-1 accuracy may be relatively low, the top-5 accuracy is often significantly higher. This gap implies that most misclassifications occur among a few si"},"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":"2411.05357","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-08T06:28:02Z","cross_cats_sorted":[],"title_canon_sha256":"2b10bd6b55c3b0b9fcc8acff371444f62cd7af37746091304c6ff10eda63034d","abstract_canon_sha256":"70b03e91f63218b26bddef351abcf372eea810334eac26ea57d2414c298883d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:41.017354Z","signature_b64":"q1w+DmVK0/8vxgsgDR2nmIYUW/ssULo+RgSIUyjUH621D8fy1eFVuoSgFqWNkn0sFhFvm9fH625KoI3TET2tDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3dd77b140cb2fe781a7c7efc14a2dc8ce092fff44a2805ec0faf01a45b064677","last_reissued_at":"2026-07-05T09:33:41.016852Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:41.016852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Visual Classification using Comparative Descriptors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gawon Seo, Geunyoung Jung, Hankyeol Lee, Jiyoung Jung, Kyungwoo Song, Wonseok Choi","submitted_at":"2024-11-08T06:28:02Z","abstract_excerpt":"The performance of vision-language models (VLMs), such as CLIP, in visual classification tasks, has been enhanced by leveraging semantic knowledge from large language models (LLMs), including GPT. Recent studies have shown that in zero-shot classification tasks, descriptors incorporating additional cues, high-level concepts, or even random characters often outperform those using only the category name. In many classification tasks, while the top-1 accuracy may be relatively low, the top-5 accuracy is often significantly higher. This gap implies that most misclassifications occur among a few si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05357","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/2411.05357/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":"2411.05357","created_at":"2026-07-05T09:33:41.016910+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.05357v2","created_at":"2026-07-05T09:33:41.016910+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05357","created_at":"2026-07-05T09:33:41.016910+00:00"},{"alias_kind":"pith_short_12","alias_value":"HXLXWFAMWL7H","created_at":"2026-07-05T09:33:41.016910+00:00"},{"alias_kind":"pith_short_16","alias_value":"HXLXWFAMWL7HQGT4","created_at":"2026-07-05T09:33:41.016910+00:00"},{"alias_kind":"pith_short_8","alias_value":"HXLXWFAM","created_at":"2026-07-05T09:33:41.016910+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/HXLXWFAMWL7HQGT4P36BJIW4RT","json":"https://pith.science/pith/HXLXWFAMWL7HQGT4P36BJIW4RT.json","graph_json":"https://pith.science/api/pith-number/HXLXWFAMWL7HQGT4P36BJIW4RT/graph.json","events_json":"https://pith.science/api/pith-number/HXLXWFAMWL7HQGT4P36BJIW4RT/events.json","paper":"https://pith.science/paper/HXLXWFAM"},"agent_actions":{"view_html":"https://pith.science/pith/HXLXWFAMWL7HQGT4P36BJIW4RT","download_json":"https://pith.science/pith/HXLXWFAMWL7HQGT4P36BJIW4RT.json","view_paper":"https://pith.science/paper/HXLXWFAM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.05357&json=true","fetch_graph":"https://pith.science/api/pith-number/HXLXWFAMWL7HQGT4P36BJIW4RT/graph.json","fetch_events":"https://pith.science/api/pith-number/HXLXWFAMWL7HQGT4P36BJIW4RT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HXLXWFAMWL7HQGT4P36BJIW4RT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HXLXWFAMWL7HQGT4P36BJIW4RT/action/storage_attestation","attest_author":"https://pith.science/pith/HXLXWFAMWL7HQGT4P36BJIW4RT/action/author_attestation","sign_citation":"https://pith.science/pith/HXLXWFAMWL7HQGT4P36BJIW4RT/action/citation_signature","submit_replication":"https://pith.science/pith/HXLXWFAMWL7HQGT4P36BJIW4RT/action/replication_record"}},"created_at":"2026-07-05T09:33:41.016910+00:00","updated_at":"2026-07-05T09:33:41.016910+00:00"}