{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BAFCOJBBULDCMJK6NBSZQHPLTV","short_pith_number":"pith:BAFCOJBB","schema_version":"1.0","canonical_sha256":"080a272421a2c626255e6865981deb9d7d60f12bab21112922934390e5035d9a","source":{"kind":"arxiv","id":"2401.07457","version":1},"attestation_state":"computed","paper":{"title":"Concept-Guided Prompt Learning for Generalization in Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ce Zhang, Ke Yu, Yi Zhang, Yushun Tang, Zhihai He","submitted_at":"2024-01-15T04:04:47Z","abstract_excerpt":"Contrastive Language-Image Pretraining (CLIP) model has exhibited remarkable efficacy in establishing cross-modal connections between texts and images, yielding impressive performance across a broad spectrum of downstream applications through fine-tuning. However, for generalization tasks, the current fine-tuning methods for CLIP, such as CoOp and CoCoOp, demonstrate relatively low performance on some fine-grained datasets. We recognize the underlying reason is that these previous methods only projected global features into the prompt, neglecting the various visual concepts, such as colors, sh"},"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":"2401.07457","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-15T04:04:47Z","cross_cats_sorted":[],"title_canon_sha256":"063e8bc95abb39e73516af808384681e9069991665923c44c1a8fdc458005994","abstract_canon_sha256":"5ec4fbff6d13f30b44eeebdd8ef23cbdeb734f61be881296fb4e8d842b9c75a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:33:37.490641Z","signature_b64":"DmIQGt/KX8LVK+KuIrL35VYOfCEnGE2ykEaIKnzz1BO9dOzQs7di+0e5fSaLx119NiO8vXtQdtWw/nRYAnrNCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"080a272421a2c626255e6865981deb9d7d60f12bab21112922934390e5035d9a","last_reissued_at":"2026-07-05T07:33:37.490209Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:33:37.490209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Concept-Guided Prompt Learning for Generalization in Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ce Zhang, Ke Yu, Yi Zhang, Yushun Tang, Zhihai He","submitted_at":"2024-01-15T04:04:47Z","abstract_excerpt":"Contrastive Language-Image Pretraining (CLIP) model has exhibited remarkable efficacy in establishing cross-modal connections between texts and images, yielding impressive performance across a broad spectrum of downstream applications through fine-tuning. However, for generalization tasks, the current fine-tuning methods for CLIP, such as CoOp and CoCoOp, demonstrate relatively low performance on some fine-grained datasets. We recognize the underlying reason is that these previous methods only projected global features into the prompt, neglecting the various visual concepts, such as colors, sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.07457","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/2401.07457/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":"2401.07457","created_at":"2026-07-05T07:33:37.490267+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.07457v1","created_at":"2026-07-05T07:33:37.490267+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.07457","created_at":"2026-07-05T07:33:37.490267+00:00"},{"alias_kind":"pith_short_12","alias_value":"BAFCOJBBULDC","created_at":"2026-07-05T07:33:37.490267+00:00"},{"alias_kind":"pith_short_16","alias_value":"BAFCOJBBULDCMJK6","created_at":"2026-07-05T07:33:37.490267+00:00"},{"alias_kind":"pith_short_8","alias_value":"BAFCOJBB","created_at":"2026-07-05T07:33:37.490267+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.01225","citing_title":"Multi-Cache Enhanced Prototype Learning for Test-Time Generalization of Vision-Language Models","ref_index":77,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BAFCOJBBULDCMJK6NBSZQHPLTV","json":"https://pith.science/pith/BAFCOJBBULDCMJK6NBSZQHPLTV.json","graph_json":"https://pith.science/api/pith-number/BAFCOJBBULDCMJK6NBSZQHPLTV/graph.json","events_json":"https://pith.science/api/pith-number/BAFCOJBBULDCMJK6NBSZQHPLTV/events.json","paper":"https://pith.science/paper/BAFCOJBB"},"agent_actions":{"view_html":"https://pith.science/pith/BAFCOJBBULDCMJK6NBSZQHPLTV","download_json":"https://pith.science/pith/BAFCOJBBULDCMJK6NBSZQHPLTV.json","view_paper":"https://pith.science/paper/BAFCOJBB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.07457&json=true","fetch_graph":"https://pith.science/api/pith-number/BAFCOJBBULDCMJK6NBSZQHPLTV/graph.json","fetch_events":"https://pith.science/api/pith-number/BAFCOJBBULDCMJK6NBSZQHPLTV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BAFCOJBBULDCMJK6NBSZQHPLTV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BAFCOJBBULDCMJK6NBSZQHPLTV/action/storage_attestation","attest_author":"https://pith.science/pith/BAFCOJBBULDCMJK6NBSZQHPLTV/action/author_attestation","sign_citation":"https://pith.science/pith/BAFCOJBBULDCMJK6NBSZQHPLTV/action/citation_signature","submit_replication":"https://pith.science/pith/BAFCOJBBULDCMJK6NBSZQHPLTV/action/replication_record"}},"created_at":"2026-07-05T07:33:37.490267+00:00","updated_at":"2026-07-05T07:33:37.490267+00:00"}