{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Y7BU4BUU3RTCMEZOP75RY4QM3R","short_pith_number":"pith:Y7BU4BUU","schema_version":"1.0","canonical_sha256":"c7c34e0694dc6626132e7ffb1c720cdc6d5e3ca7243aed143cec6f097f3a988e","source":{"kind":"arxiv","id":"2306.09295","version":1},"attestation_state":"computed","paper":{"title":"Neural Fine-Tuning Search for Few-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Da Li, {\\L}ukasz Dudziak, Panagiotis Eustratiadis, Timothy Hospedales","submitted_at":"2023-06-15T17:20:35Z","abstract_excerpt":"In few-shot recognition, a classifier that has been trained on one set of classes is required to rapidly adapt and generalize to a disjoint, novel set of classes. To that end, recent studies have shown the efficacy of fine-tuning with carefully crafted adaptation architectures. However this raises the question of: How can one design the optimal adaptation strategy? In this paper, we study this question through the lens of neural architecture search (NAS). Given a pre-trained neural network, our algorithm discovers the optimal arrangement of adapters, which layers to keep frozen and which to fi"},"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":"2306.09295","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-15T17:20:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"015123ca553f44f08622c6d4a212fae35e143aed5f77e12b0fba3b31b647715b","abstract_canon_sha256":"2e925650b501b7c35a7d600c68c8750d43bcea1716a47077cac28f832394f730"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:10.714881Z","signature_b64":"Vdu74k93lQDfehE/7VFcbwzco5qVqx8b6PlAgGu6pVboXiicHeSFRD/zzNEhJD5jkOYqTNsW1q/+ImGI7KxcAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7c34e0694dc6626132e7ffb1c720cdc6d5e3ca7243aed143cec6f097f3a988e","last_reissued_at":"2026-07-05T06:21:10.714387Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:10.714387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Fine-Tuning Search for Few-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Da Li, {\\L}ukasz Dudziak, Panagiotis Eustratiadis, Timothy Hospedales","submitted_at":"2023-06-15T17:20:35Z","abstract_excerpt":"In few-shot recognition, a classifier that has been trained on one set of classes is required to rapidly adapt and generalize to a disjoint, novel set of classes. To that end, recent studies have shown the efficacy of fine-tuning with carefully crafted adaptation architectures. However this raises the question of: How can one design the optimal adaptation strategy? In this paper, we study this question through the lens of neural architecture search (NAS). Given a pre-trained neural network, our algorithm discovers the optimal arrangement of adapters, which layers to keep frozen and which to fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09295","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/2306.09295/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":"2306.09295","created_at":"2026-07-05T06:21:10.714453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.09295v1","created_at":"2026-07-05T06:21:10.714453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09295","created_at":"2026-07-05T06:21:10.714453+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y7BU4BUU3RTC","created_at":"2026-07-05T06:21:10.714453+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y7BU4BUU3RTCMEZO","created_at":"2026-07-05T06:21:10.714453+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y7BU4BUU","created_at":"2026-07-05T06:21:10.714453+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.17079","citing_title":"Few-Shot Learning in Video and 3D Object Detection: A Survey","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y7BU4BUU3RTCMEZOP75RY4QM3R","json":"https://pith.science/pith/Y7BU4BUU3RTCMEZOP75RY4QM3R.json","graph_json":"https://pith.science/api/pith-number/Y7BU4BUU3RTCMEZOP75RY4QM3R/graph.json","events_json":"https://pith.science/api/pith-number/Y7BU4BUU3RTCMEZOP75RY4QM3R/events.json","paper":"https://pith.science/paper/Y7BU4BUU"},"agent_actions":{"view_html":"https://pith.science/pith/Y7BU4BUU3RTCMEZOP75RY4QM3R","download_json":"https://pith.science/pith/Y7BU4BUU3RTCMEZOP75RY4QM3R.json","view_paper":"https://pith.science/paper/Y7BU4BUU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.09295&json=true","fetch_graph":"https://pith.science/api/pith-number/Y7BU4BUU3RTCMEZOP75RY4QM3R/graph.json","fetch_events":"https://pith.science/api/pith-number/Y7BU4BUU3RTCMEZOP75RY4QM3R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y7BU4BUU3RTCMEZOP75RY4QM3R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y7BU4BUU3RTCMEZOP75RY4QM3R/action/storage_attestation","attest_author":"https://pith.science/pith/Y7BU4BUU3RTCMEZOP75RY4QM3R/action/author_attestation","sign_citation":"https://pith.science/pith/Y7BU4BUU3RTCMEZOP75RY4QM3R/action/citation_signature","submit_replication":"https://pith.science/pith/Y7BU4BUU3RTCMEZOP75RY4QM3R/action/replication_record"}},"created_at":"2026-07-05T06:21:10.714453+00:00","updated_at":"2026-07-05T06:21:10.714453+00:00"}