{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CBNLBFBXXXSCI3OD7MPO7IZWPK","short_pith_number":"pith:CBNLBFBX","schema_version":"1.0","canonical_sha256":"105ab09437bde4246dc3fb1eefa3367abc8f1381e2c494a6fd255fddef201852","source":{"kind":"arxiv","id":"2303.02151","version":1},"attestation_state":"computed","paper":{"title":"Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bohao Li, Hanqiu Deng, Hongsheng Li, Peng Gao, Renrui Zhang, Siyuan Huang, Xiangfei Hu, Yu Qiao","submitted_at":"2023-03-03T18:58:16Z","abstract_excerpt":"Visual recognition in low-data regimes requires deep neural networks to learn generalized representations from limited training samples. Recently, CLIP-based methods have shown promising few-shot performance benefited from the contrastive language-image pre-training. We then question, if the more diverse pre-training knowledge can be cascaded to further assist few-shot representation learning. In this paper, we propose CaFo, a Cascade of Foundation models that incorporates diverse prior knowledge of various pre-training paradigms for better few-shot learning. Our CaFo incorporates CLIP's langu"},"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":"2303.02151","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-03T18:58:16Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f3c752c689703c46502ea7794e23f3f014ced5a4e4ad3e90ac5d620a15a1998b","abstract_canon_sha256":"4dc7bd560c4562ec484a487e67cdf9cc74ec483a614a16370f2c59fde336de73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:53.085500Z","signature_b64":"nKr6cTrp0g6xqZNnL8ft58N97IFqKHYzVf8nLrQiZksHApLWer1G++aXz6R7m3R3vNjg+EHliLnqdCiqLCvVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"105ab09437bde4246dc3fb1eefa3367abc8f1381e2c494a6fd255fddef201852","last_reissued_at":"2026-07-05T05:47:53.084991Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:53.084991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bohao Li, Hanqiu Deng, Hongsheng Li, Peng Gao, Renrui Zhang, Siyuan Huang, Xiangfei Hu, Yu Qiao","submitted_at":"2023-03-03T18:58:16Z","abstract_excerpt":"Visual recognition in low-data regimes requires deep neural networks to learn generalized representations from limited training samples. Recently, CLIP-based methods have shown promising few-shot performance benefited from the contrastive language-image pre-training. We then question, if the more diverse pre-training knowledge can be cascaded to further assist few-shot representation learning. In this paper, we propose CaFo, a Cascade of Foundation models that incorporates diverse prior knowledge of various pre-training paradigms for better few-shot learning. Our CaFo incorporates CLIP's langu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.02151","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/2303.02151/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":"2303.02151","created_at":"2026-07-05T05:47:53.085056+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.02151v1","created_at":"2026-07-05T05:47:53.085056+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.02151","created_at":"2026-07-05T05:47:53.085056+00:00"},{"alias_kind":"pith_short_12","alias_value":"CBNLBFBXXXSC","created_at":"2026-07-05T05:47:53.085056+00:00"},{"alias_kind":"pith_short_16","alias_value":"CBNLBFBXXXSCI3OD","created_at":"2026-07-05T05:47:53.085056+00:00"},{"alias_kind":"pith_short_8","alias_value":"CBNLBFBX","created_at":"2026-07-05T05:47:53.085056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2303.16199","citing_title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","ref_index":210,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CBNLBFBXXXSCI3OD7MPO7IZWPK","json":"https://pith.science/pith/CBNLBFBXXXSCI3OD7MPO7IZWPK.json","graph_json":"https://pith.science/api/pith-number/CBNLBFBXXXSCI3OD7MPO7IZWPK/graph.json","events_json":"https://pith.science/api/pith-number/CBNLBFBXXXSCI3OD7MPO7IZWPK/events.json","paper":"https://pith.science/paper/CBNLBFBX"},"agent_actions":{"view_html":"https://pith.science/pith/CBNLBFBXXXSCI3OD7MPO7IZWPK","download_json":"https://pith.science/pith/CBNLBFBXXXSCI3OD7MPO7IZWPK.json","view_paper":"https://pith.science/paper/CBNLBFBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.02151&json=true","fetch_graph":"https://pith.science/api/pith-number/CBNLBFBXXXSCI3OD7MPO7IZWPK/graph.json","fetch_events":"https://pith.science/api/pith-number/CBNLBFBXXXSCI3OD7MPO7IZWPK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CBNLBFBXXXSCI3OD7MPO7IZWPK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CBNLBFBXXXSCI3OD7MPO7IZWPK/action/storage_attestation","attest_author":"https://pith.science/pith/CBNLBFBXXXSCI3OD7MPO7IZWPK/action/author_attestation","sign_citation":"https://pith.science/pith/CBNLBFBXXXSCI3OD7MPO7IZWPK/action/citation_signature","submit_replication":"https://pith.science/pith/CBNLBFBXXXSCI3OD7MPO7IZWPK/action/replication_record"}},"created_at":"2026-07-05T05:47:53.085056+00:00","updated_at":"2026-07-05T05:47:53.085056+00:00"}