{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:W66GRJMJPKOXM5UYXC6D22IQLD","short_pith_number":"pith:W66GRJMJ","schema_version":"1.0","canonical_sha256":"b7bc68a5897a9d767698b8bc3d691058c5e7dd87a76901eb9ac4fe495c9c30e6","source":{"kind":"arxiv","id":"2404.09778","version":2},"attestation_state":"computed","paper":{"title":"The Devil is in the Few Shots: Iterative Visual Knowledge Completion for Few-shot Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoxing Chen, Hao Zhou, Jianbing Zhang, Qifeng Zhou, Xinyu Dai, Yaohui Li","submitted_at":"2024-04-15T13:30:34Z","abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) has shown powerful zero-shot learning performance. Few-shot learning aims to further enhance the transfer capability of CLIP by giving few images in each class, aka 'few shots'. Most existing methods either implicitly learn from the few shots by incorporating learnable prompts or adapters, or explicitly embed them in a cache model for inference. However, the narrow distribution of few shots often contains incomplete class information, leading to biased visual knowledge with high risk of misclassification. To tackle this problem, recent methods pro"},"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":"2404.09778","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T13:30:34Z","cross_cats_sorted":[],"title_canon_sha256":"5277858d7b37a944d7d60c37f82d2418253ff2bd2a16487f9710a2246da69c41","abstract_canon_sha256":"a1d6a774f3437ff496742002cb8729e466ade11527563defa3e1bd3e4f0e6f59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:50.073504Z","signature_b64":"zoVZbm0epMj0Ajd8WKkHLFXIoJARYKNfJrXgw90nIp3RrUNEYubg+KCT5nNmWsKcUFH5kWZhAE9vh/JuR8KQBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7bc68a5897a9d767698b8bc3d691058c5e7dd87a76901eb9ac4fe495c9c30e6","last_reissued_at":"2026-07-05T08:09:50.072995Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:50.072995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Devil is in the Few Shots: Iterative Visual Knowledge Completion for Few-shot Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoxing Chen, Hao Zhou, Jianbing Zhang, Qifeng Zhou, Xinyu Dai, Yaohui Li","submitted_at":"2024-04-15T13:30:34Z","abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) has shown powerful zero-shot learning performance. Few-shot learning aims to further enhance the transfer capability of CLIP by giving few images in each class, aka 'few shots'. Most existing methods either implicitly learn from the few shots by incorporating learnable prompts or adapters, or explicitly embed them in a cache model for inference. However, the narrow distribution of few shots often contains incomplete class information, leading to biased visual knowledge with high risk of misclassification. To tackle this problem, recent methods pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09778","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/2404.09778/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":"2404.09778","created_at":"2026-07-05T08:09:50.073057+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.09778v2","created_at":"2026-07-05T08:09:50.073057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09778","created_at":"2026-07-05T08:09:50.073057+00:00"},{"alias_kind":"pith_short_12","alias_value":"W66GRJMJPKOX","created_at":"2026-07-05T08:09:50.073057+00:00"},{"alias_kind":"pith_short_16","alias_value":"W66GRJMJPKOXM5UY","created_at":"2026-07-05T08:09:50.073057+00:00"},{"alias_kind":"pith_short_8","alias_value":"W66GRJMJ","created_at":"2026-07-05T08:09:50.073057+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.15099","citing_title":"Context-Aware Multimodal Pretraining","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W66GRJMJPKOXM5UYXC6D22IQLD","json":"https://pith.science/pith/W66GRJMJPKOXM5UYXC6D22IQLD.json","graph_json":"https://pith.science/api/pith-number/W66GRJMJPKOXM5UYXC6D22IQLD/graph.json","events_json":"https://pith.science/api/pith-number/W66GRJMJPKOXM5UYXC6D22IQLD/events.json","paper":"https://pith.science/paper/W66GRJMJ"},"agent_actions":{"view_html":"https://pith.science/pith/W66GRJMJPKOXM5UYXC6D22IQLD","download_json":"https://pith.science/pith/W66GRJMJPKOXM5UYXC6D22IQLD.json","view_paper":"https://pith.science/paper/W66GRJMJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.09778&json=true","fetch_graph":"https://pith.science/api/pith-number/W66GRJMJPKOXM5UYXC6D22IQLD/graph.json","fetch_events":"https://pith.science/api/pith-number/W66GRJMJPKOXM5UYXC6D22IQLD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W66GRJMJPKOXM5UYXC6D22IQLD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W66GRJMJPKOXM5UYXC6D22IQLD/action/storage_attestation","attest_author":"https://pith.science/pith/W66GRJMJPKOXM5UYXC6D22IQLD/action/author_attestation","sign_citation":"https://pith.science/pith/W66GRJMJPKOXM5UYXC6D22IQLD/action/citation_signature","submit_replication":"https://pith.science/pith/W66GRJMJPKOXM5UYXC6D22IQLD/action/replication_record"}},"created_at":"2026-07-05T08:09:50.073057+00:00","updated_at":"2026-07-05T08:09:50.073057+00:00"}