{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NAAW6ZL7QRZZTBSV6AP2PFG5TD","short_pith_number":"pith:NAAW6ZL7","schema_version":"1.0","canonical_sha256":"68016f657f8473998655f01fa794dd98c9ad7b62a26e2efaa854921ae20b3422","source":{"kind":"arxiv","id":"2404.17753","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Cross-Modal Neighbor Representation for Improved CLIP Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chao Yi, De-Chuan Zhan, Han-Jia Ye, Lu Ren","submitted_at":"2024-04-27T02:04:36Z","abstract_excerpt":"CLIP showcases exceptional cross-modal matching capabilities due to its training on image-text contrastive learning tasks. However, without specific optimization for unimodal scenarios, its performance in single-modality feature extraction might be suboptimal. Despite this, some studies have directly used CLIP's image encoder for tasks like few-shot classification, introducing a misalignment between its pre-training objectives and feature extraction methods. This inconsistency can diminish the quality of the image's feature representation, adversely affecting CLIP's effectiveness in target tas"},"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":"2404.17753","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-27T02:04:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b47f22fb7865d9e646eabf84074706774dbc20378b1e8b26bde2a866b9f780ea","abstract_canon_sha256":"2d6cd285d5f03686e7cf1d4c82e4b3559ca9b82a16980397445c0ca9e9d77030"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:53.670676Z","signature_b64":"TOyBY8w7dpg2+Eu69ZXthUCg7/kjVZ1ZkwOPUpBD8H6hHw+mFmOSf6Fb5j/L14pbSogZO5npQzRi7xXIfAUwBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68016f657f8473998655f01fa794dd98c9ad7b62a26e2efaa854921ae20b3422","last_reissued_at":"2026-07-05T08:12:53.670202Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:53.670202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Cross-Modal Neighbor Representation for Improved CLIP Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chao Yi, De-Chuan Zhan, Han-Jia Ye, Lu Ren","submitted_at":"2024-04-27T02:04:36Z","abstract_excerpt":"CLIP showcases exceptional cross-modal matching capabilities due to its training on image-text contrastive learning tasks. However, without specific optimization for unimodal scenarios, its performance in single-modality feature extraction might be suboptimal. Despite this, some studies have directly used CLIP's image encoder for tasks like few-shot classification, introducing a misalignment between its pre-training objectives and feature extraction methods. This inconsistency can diminish the quality of the image's feature representation, adversely affecting CLIP's effectiveness in target tas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17753","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/2404.17753/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":"2404.17753","created_at":"2026-07-05T08:12:53.670261+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.17753v1","created_at":"2026-07-05T08:12:53.670261+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17753","created_at":"2026-07-05T08:12:53.670261+00:00"},{"alias_kind":"pith_short_12","alias_value":"NAAW6ZL7QRZZ","created_at":"2026-07-05T08:12:53.670261+00:00"},{"alias_kind":"pith_short_16","alias_value":"NAAW6ZL7QRZZTBSV","created_at":"2026-07-05T08:12:53.670261+00:00"},{"alias_kind":"pith_short_8","alias_value":"NAAW6ZL7","created_at":"2026-07-05T08:12:53.670261+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/NAAW6ZL7QRZZTBSV6AP2PFG5TD","json":"https://pith.science/pith/NAAW6ZL7QRZZTBSV6AP2PFG5TD.json","graph_json":"https://pith.science/api/pith-number/NAAW6ZL7QRZZTBSV6AP2PFG5TD/graph.json","events_json":"https://pith.science/api/pith-number/NAAW6ZL7QRZZTBSV6AP2PFG5TD/events.json","paper":"https://pith.science/paper/NAAW6ZL7"},"agent_actions":{"view_html":"https://pith.science/pith/NAAW6ZL7QRZZTBSV6AP2PFG5TD","download_json":"https://pith.science/pith/NAAW6ZL7QRZZTBSV6AP2PFG5TD.json","view_paper":"https://pith.science/paper/NAAW6ZL7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.17753&json=true","fetch_graph":"https://pith.science/api/pith-number/NAAW6ZL7QRZZTBSV6AP2PFG5TD/graph.json","fetch_events":"https://pith.science/api/pith-number/NAAW6ZL7QRZZTBSV6AP2PFG5TD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NAAW6ZL7QRZZTBSV6AP2PFG5TD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NAAW6ZL7QRZZTBSV6AP2PFG5TD/action/storage_attestation","attest_author":"https://pith.science/pith/NAAW6ZL7QRZZTBSV6AP2PFG5TD/action/author_attestation","sign_citation":"https://pith.science/pith/NAAW6ZL7QRZZTBSV6AP2PFG5TD/action/citation_signature","submit_replication":"https://pith.science/pith/NAAW6ZL7QRZZTBSV6AP2PFG5TD/action/replication_record"}},"created_at":"2026-07-05T08:12:53.670261+00:00","updated_at":"2026-07-05T08:12:53.670261+00:00"}