{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YJDZQQQJKQS44UG5YXTKE4MHW5","short_pith_number":"pith:YJDZQQQJ","schema_version":"1.0","canonical_sha256":"c2479842095425ce50ddc5e6a27187b771f8428d25df34b3cc2f11e74123a4e4","source":{"kind":"arxiv","id":"2110.04544","version":2},"attestation_state":"computed","paper":{"title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Hongsheng Li, Peng Gao, Renrui Zhang, Rongyao Fang, Shijie Geng, Teli Ma, Yongfeng Zhang, Yu Qiao","submitted_at":"2021-10-09T11:39:30Z","abstract_excerpt":"Large-scale contrastive vision-language pre-training has shown significant progress in visual representation learning. Unlike traditional visual systems trained by a fixed set of discrete labels, a new paradigm was introduced in \\cite{radford2021learning} to directly learn to align images with raw texts in an open-vocabulary setting. On downstream tasks, a carefully chosen text prompt is employed to make zero-shot predictions.~To avoid non-trivial prompt engineering, context optimization \\cite{zhou2021coop} has been proposed to learn continuous vectors as task-specific prompts with few-shot tr"},"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":"2110.04544","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-09T11:39:30Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d344d6686ad54f4e29336feef6371d55e09a70f5da35d1863edd34adbeee0490","abstract_canon_sha256":"56a5a73db248dcf64f465e2909d4fde316feef4f0a252ee32d123e87bb63a035"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:29.173335Z","signature_b64":"zSn2oeh0pR0LSZ+wvzpUhwtUADWo1ByB7XaiBtZmWGmZdRSbvUFGX/YhIJ6cwQGxPELJq1JMRfHXJg6r0kY3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2479842095425ce50ddc5e6a27187b771f8428d25df34b3cc2f11e74123a4e4","last_reissued_at":"2026-07-05T10:38:29.172786Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:29.172786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Hongsheng Li, Peng Gao, Renrui Zhang, Rongyao Fang, Shijie Geng, Teli Ma, Yongfeng Zhang, Yu Qiao","submitted_at":"2021-10-09T11:39:30Z","abstract_excerpt":"Large-scale contrastive vision-language pre-training has shown significant progress in visual representation learning. Unlike traditional visual systems trained by a fixed set of discrete labels, a new paradigm was introduced in \\cite{radford2021learning} to directly learn to align images with raw texts in an open-vocabulary setting. On downstream tasks, a carefully chosen text prompt is employed to make zero-shot predictions.~To avoid non-trivial prompt engineering, context optimization \\cite{zhou2021coop} has been proposed to learn continuous vectors as task-specific prompts with few-shot tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04544","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/2110.04544/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":"2110.04544","created_at":"2026-07-05T10:38:29.172845+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.04544v2","created_at":"2026-07-05T10:38:29.172845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04544","created_at":"2026-07-05T10:38:29.172845+00:00"},{"alias_kind":"pith_short_12","alias_value":"YJDZQQQJKQS4","created_at":"2026-07-05T10:38:29.172845+00:00"},{"alias_kind":"pith_short_16","alias_value":"YJDZQQQJKQS44UG5","created_at":"2026-07-05T10:38:29.172845+00:00"},{"alias_kind":"pith_short_8","alias_value":"YJDZQQQJ","created_at":"2026-07-05T10:38:29.172845+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2407.17491","citing_title":"Robust Adaptation of Foundation Models with Black-Box Visual Prompting","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2302.05543","citing_title":"Adding Conditional Control to Text-to-Image Diffusion Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2601.09746","citing_title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2312.17090","citing_title":"Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels","ref_index":195,"is_internal_anchor":false},{"citing_arxiv_id":"2603.03577","citing_title":"From Local Matches to Global Masks: Template-Guided Instance Detection and Segmentation in Open-World Scenes","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2304.15010","citing_title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2303.16199","citing_title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","ref_index":202,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11939","citing_title":"Cluster-Aware Neural Collapse Prompt Tuning for Long-Tailed Generalization of Vision-Language Models","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06477","citing_title":"GeoStack: A Framework for Quasi-Abelian Knowledge Composition in VLMs","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2208.01618","citing_title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2303.05499","citing_title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YJDZQQQJKQS44UG5YXTKE4MHW5","json":"https://pith.science/pith/YJDZQQQJKQS44UG5YXTKE4MHW5.json","graph_json":"https://pith.science/api/pith-number/YJDZQQQJKQS44UG5YXTKE4MHW5/graph.json","events_json":"https://pith.science/api/pith-number/YJDZQQQJKQS44UG5YXTKE4MHW5/events.json","paper":"https://pith.science/paper/YJDZQQQJ"},"agent_actions":{"view_html":"https://pith.science/pith/YJDZQQQJKQS44UG5YXTKE4MHW5","download_json":"https://pith.science/pith/YJDZQQQJKQS44UG5YXTKE4MHW5.json","view_paper":"https://pith.science/paper/YJDZQQQJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.04544&json=true","fetch_graph":"https://pith.science/api/pith-number/YJDZQQQJKQS44UG5YXTKE4MHW5/graph.json","fetch_events":"https://pith.science/api/pith-number/YJDZQQQJKQS44UG5YXTKE4MHW5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YJDZQQQJKQS44UG5YXTKE4MHW5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YJDZQQQJKQS44UG5YXTKE4MHW5/action/storage_attestation","attest_author":"https://pith.science/pith/YJDZQQQJKQS44UG5YXTKE4MHW5/action/author_attestation","sign_citation":"https://pith.science/pith/YJDZQQQJKQS44UG5YXTKE4MHW5/action/citation_signature","submit_replication":"https://pith.science/pith/YJDZQQQJKQS44UG5YXTKE4MHW5/action/replication_record"}},"created_at":"2026-07-05T10:38:29.172845+00:00","updated_at":"2026-07-05T10:38:29.172845+00:00"}