{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DOSRWWKCSY6EHINFK72FWDTM6L","short_pith_number":"pith:DOSRWWKC","schema_version":"1.0","canonical_sha256":"1ba51b5942963c43a1a557f45b0e6cf2f4917c27aa82b210351a4f092f3ec679","source":{"kind":"arxiv","id":"1910.00216","version":2},"attestation_state":"computed","paper":{"title":"Revisiting Fine-tuning for Few-shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Akihiro Nakamura, Tatsuya Harada","submitted_at":"2019-10-01T06:21:50Z","abstract_excerpt":"Few-shot learning is the process of learning novel classes using only a few examples and it remains a challenging task in machine learning. Many sophisticated few-shot learning algorithms have been proposed based on the notion that networks can easily overfit to novel examples if they are simply fine-tuned using only a few examples. In this study, we show that in the commonly used low-resolution mini-ImageNet dataset, the fine-tuning method achieves higher accuracy than common few-shot learning algorithms in the 1-shot task and nearly the same accuracy as that of the state-of-the-art algorithm"},"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":"1910.00216","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-01T06:21:50Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"c7052c3f451846a349f3b164d4378020abd303edcd1886d8224a0a3a9c27c72a","abstract_canon_sha256":"7870fb558d06b808014f7f63712b0dd72d305c679addb5e8852dd17e746ab587"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:09:27.235999Z","signature_b64":"3lrvGNHn8oxy+gt4ydYOomGI7MI7zhxEgLdMVdN0NB9321AdoLlR0LXmA6Xma1IXc5ueXA+Q4U9dxYaDnRtmAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ba51b5942963c43a1a557f45b0e6cf2f4917c27aa82b210351a4f092f3ec679","last_reissued_at":"2026-07-05T00:09:27.235554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:09:27.235554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Fine-tuning for Few-shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Akihiro Nakamura, Tatsuya Harada","submitted_at":"2019-10-01T06:21:50Z","abstract_excerpt":"Few-shot learning is the process of learning novel classes using only a few examples and it remains a challenging task in machine learning. Many sophisticated few-shot learning algorithms have been proposed based on the notion that networks can easily overfit to novel examples if they are simply fine-tuned using only a few examples. In this study, we show that in the commonly used low-resolution mini-ImageNet dataset, the fine-tuning method achieves higher accuracy than common few-shot learning algorithms in the 1-shot task and nearly the same accuracy as that of the state-of-the-art algorithm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.00216","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/1910.00216/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":"1910.00216","created_at":"2026-07-05T00:09:27.235611+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.00216v2","created_at":"2026-07-05T00:09:27.235611+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.00216","created_at":"2026-07-05T00:09:27.235611+00:00"},{"alias_kind":"pith_short_12","alias_value":"DOSRWWKCSY6E","created_at":"2026-07-05T00:09:27.235611+00:00"},{"alias_kind":"pith_short_16","alias_value":"DOSRWWKCSY6EHINF","created_at":"2026-07-05T00:09:27.235611+00:00"},{"alias_kind":"pith_short_8","alias_value":"DOSRWWKC","created_at":"2026-07-05T00:09:27.235611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.20511","citing_title":"Beyond Class Tokens: LLM-guided Dominant Property Mining for Few-shot Classification","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DOSRWWKCSY6EHINFK72FWDTM6L","json":"https://pith.science/pith/DOSRWWKCSY6EHINFK72FWDTM6L.json","graph_json":"https://pith.science/api/pith-number/DOSRWWKCSY6EHINFK72FWDTM6L/graph.json","events_json":"https://pith.science/api/pith-number/DOSRWWKCSY6EHINFK72FWDTM6L/events.json","paper":"https://pith.science/paper/DOSRWWKC"},"agent_actions":{"view_html":"https://pith.science/pith/DOSRWWKCSY6EHINFK72FWDTM6L","download_json":"https://pith.science/pith/DOSRWWKCSY6EHINFK72FWDTM6L.json","view_paper":"https://pith.science/paper/DOSRWWKC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.00216&json=true","fetch_graph":"https://pith.science/api/pith-number/DOSRWWKCSY6EHINFK72FWDTM6L/graph.json","fetch_events":"https://pith.science/api/pith-number/DOSRWWKCSY6EHINFK72FWDTM6L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DOSRWWKCSY6EHINFK72FWDTM6L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DOSRWWKCSY6EHINFK72FWDTM6L/action/storage_attestation","attest_author":"https://pith.science/pith/DOSRWWKCSY6EHINFK72FWDTM6L/action/author_attestation","sign_citation":"https://pith.science/pith/DOSRWWKCSY6EHINFK72FWDTM6L/action/citation_signature","submit_replication":"https://pith.science/pith/DOSRWWKCSY6EHINFK72FWDTM6L/action/replication_record"}},"created_at":"2026-07-05T00:09:27.235611+00:00","updated_at":"2026-07-05T00:09:27.235611+00:00"}