{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RTKPEVQPMCUNW4FVZIIVBGAPW6","short_pith_number":"pith:RTKPEVQP","schema_version":"1.0","canonical_sha256":"8cd4f2560f60a8db70b5ca1150980fb7b3d87bf31a9813dbd5e659c03f1a3536","source":{"kind":"arxiv","id":"1805.08136","version":3},"attestation_state":"computed","paper":{"title":"Meta-learning with differentiable closed-form solvers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Jo\\~ao F. Henriques, Luca Bertinetto, Philip H.S. Torr","submitted_at":"2018-05-21T15:44:51Z","abstract_excerpt":"Adapting deep networks to new concepts from a few examples is challenging, due to the high computational requirements of standard fine-tuning procedures. Most work on few-shot learning has thus focused on simple learning techniques for adaptation, such as nearest neighbours or gradient descent. Nonetheless, the machine learning literature contains a wealth of methods that learn non-deep models very efficiently. In this paper, we propose to use these fast convergent methods as the main adaptation mechanism for few-shot learning. The main idea is to teach a deep network to use standard machine l"},"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":"1805.08136","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-21T15:44:51Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"e268703e7c0c0ec6dfb9fa4b7e6384683b4574786bc3d0e0bf98760412cb7885","abstract_canon_sha256":"52e38e2f0ddd688b9074114904a4eea0322d9b03ae2ea488646e1242a565c7ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:41.801915Z","signature_b64":"CBX4SvW8Uc4hy/08txUgF8IavQdlM7XJis+QgnmvYrppDhmAY4nufU201VFuFDW2+nehvK9Q/rEF8QGccVzNBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cd4f2560f60a8db70b5ca1150980fb7b3d87bf31a9813dbd5e659c03f1a3536","last_reissued_at":"2026-05-17T23:39:41.801236Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:41.801236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-learning with differentiable closed-form solvers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Jo\\~ao F. Henriques, Luca Bertinetto, Philip H.S. Torr","submitted_at":"2018-05-21T15:44:51Z","abstract_excerpt":"Adapting deep networks to new concepts from a few examples is challenging, due to the high computational requirements of standard fine-tuning procedures. Most work on few-shot learning has thus focused on simple learning techniques for adaptation, such as nearest neighbours or gradient descent. Nonetheless, the machine learning literature contains a wealth of methods that learn non-deep models very efficiently. In this paper, we propose to use these fast convergent methods as the main adaptation mechanism for few-shot learning. The main idea is to teach a deep network to use standard machine l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08136","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1805.08136","created_at":"2026-05-17T23:39:41.801365+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.08136v3","created_at":"2026-05-17T23:39:41.801365+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08136","created_at":"2026-05-17T23:39:41.801365+00:00"},{"alias_kind":"pith_short_12","alias_value":"RTKPEVQPMCUN","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"RTKPEVQPMCUNW4FV","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"RTKPEVQP","created_at":"2026-05-18T12:32:50.500415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2605.23033","citing_title":"Uncovering the Latent Potential of Deep Intermediate Representations","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2311.14756","citing_title":"Task-Distributionally Robust Data-Free Meta-Learning","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2510.18326","citing_title":"Enhancing Few-Shot Classification of Benchmark and Disaster Imagery with ABHFA-Net","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2511.17902","citing_title":"Statistically-Guided Meta-Learning for Cross-Deployment Activity Recognition in Distributed Fiber-Optic Sensing","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13672","citing_title":"SpurAudio: A Benchmark for Studying Shortcut Learning in Few-Shot Audio Classification","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10288","citing_title":"BROS: Bias-Corrected Randomized Subspaces for Memory-Efficient Single-Loop Bilevel Optimization","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10288","citing_title":"BROS: Bias-Corrected Randomized Subspaces for Memory-Efficient Single-Loop Bilevel Optimization","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2204.14198","citing_title":"Flamingo: a Visual Language Model for Few-Shot Learning","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RTKPEVQPMCUNW4FVZIIVBGAPW6","json":"https://pith.science/pith/RTKPEVQPMCUNW4FVZIIVBGAPW6.json","graph_json":"https://pith.science/api/pith-number/RTKPEVQPMCUNW4FVZIIVBGAPW6/graph.json","events_json":"https://pith.science/api/pith-number/RTKPEVQPMCUNW4FVZIIVBGAPW6/events.json","paper":"https://pith.science/paper/RTKPEVQP"},"agent_actions":{"view_html":"https://pith.science/pith/RTKPEVQPMCUNW4FVZIIVBGAPW6","download_json":"https://pith.science/pith/RTKPEVQPMCUNW4FVZIIVBGAPW6.json","view_paper":"https://pith.science/paper/RTKPEVQP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.08136&json=true","fetch_graph":"https://pith.science/api/pith-number/RTKPEVQPMCUNW4FVZIIVBGAPW6/graph.json","fetch_events":"https://pith.science/api/pith-number/RTKPEVQPMCUNW4FVZIIVBGAPW6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RTKPEVQPMCUNW4FVZIIVBGAPW6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RTKPEVQPMCUNW4FVZIIVBGAPW6/action/storage_attestation","attest_author":"https://pith.science/pith/RTKPEVQPMCUNW4FVZIIVBGAPW6/action/author_attestation","sign_citation":"https://pith.science/pith/RTKPEVQPMCUNW4FVZIIVBGAPW6/action/citation_signature","submit_replication":"https://pith.science/pith/RTKPEVQPMCUNW4FVZIIVBGAPW6/action/replication_record"}},"created_at":"2026-05-17T23:39:41.801365+00:00","updated_at":"2026-05-17T23:39:41.801365+00:00"}