{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:B4TEBXBTQYE4T3NKG64OFMWGA5","short_pith_number":"pith:B4TEBXBT","schema_version":"1.0","canonical_sha256":"0f2640dc338609c9edaa37b8e2b2c60757b5f5428a0aa55c96ad9975c603fe79","source":{"kind":"arxiv","id":"1809.08346","version":2},"attestation_state":"computed","paper":{"title":"A Meta-Learning Approach for Custom Model Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amir Erfan Eshratifar, David Eigen, Massoud Pedram, Mohammad Saeed Abrishami","submitted_at":"2018-09-21T23:47:34Z","abstract_excerpt":"Transfer-learning and meta-learning are two effective methods to apply knowledge learned from large data sources to new tasks. In few-class, few-shot target task settings (i.e. when there are only a few classes and training examples available in the target task), meta-learning approaches that optimize for future task learning have outperformed the typical transfer approach of initializing model weights from a pre-trained starting point. But as we experimentally show, meta-learning algorithms that work well in the few-class setting do not generalize well in many-shot and many-class cases. In th"},"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":"1809.08346","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-21T23:47:34Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"9eb53c13e96161786470d6181162f0c526b04133604bf07a76276c8a55df857e","abstract_canon_sha256":"7a5956608c702e66aca7b3741a15420d0f0ff92f9b11a9eeacd2d65189ef0924"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:31.583807Z","signature_b64":"6Rj9JtOqoRWdvmjtfkTVLuU/deghtDqitYj7EV9UITzfwgJhWdOx62mF1uqPml8wwL27GKyVYua+scCJsB05Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f2640dc338609c9edaa37b8e2b2c60757b5f5428a0aa55c96ad9975c603fe79","last_reissued_at":"2026-05-17T23:54:31.583185Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:31.583185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Meta-Learning Approach for Custom Model Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amir Erfan Eshratifar, David Eigen, Massoud Pedram, Mohammad Saeed Abrishami","submitted_at":"2018-09-21T23:47:34Z","abstract_excerpt":"Transfer-learning and meta-learning are two effective methods to apply knowledge learned from large data sources to new tasks. In few-class, few-shot target task settings (i.e. when there are only a few classes and training examples available in the target task), meta-learning approaches that optimize for future task learning have outperformed the typical transfer approach of initializing model weights from a pre-trained starting point. But as we experimentally show, meta-learning algorithms that work well in the few-class setting do not generalize well in many-shot and many-class cases. In th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.08346","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":""},"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":"1809.08346","created_at":"2026-05-17T23:54:31.583276+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.08346v2","created_at":"2026-05-17T23:54:31.583276+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.08346","created_at":"2026-05-17T23:54:31.583276+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4TEBXBTQYE4","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4TEBXBTQYE4T3NK","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4TEBXBT","created_at":"2026-05-18T12:32:13.499390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B4TEBXBTQYE4T3NKG64OFMWGA5","json":"https://pith.science/pith/B4TEBXBTQYE4T3NKG64OFMWGA5.json","graph_json":"https://pith.science/api/pith-number/B4TEBXBTQYE4T3NKG64OFMWGA5/graph.json","events_json":"https://pith.science/api/pith-number/B4TEBXBTQYE4T3NKG64OFMWGA5/events.json","paper":"https://pith.science/paper/B4TEBXBT"},"agent_actions":{"view_html":"https://pith.science/pith/B4TEBXBTQYE4T3NKG64OFMWGA5","download_json":"https://pith.science/pith/B4TEBXBTQYE4T3NKG64OFMWGA5.json","view_paper":"https://pith.science/paper/B4TEBXBT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.08346&json=true","fetch_graph":"https://pith.science/api/pith-number/B4TEBXBTQYE4T3NKG64OFMWGA5/graph.json","fetch_events":"https://pith.science/api/pith-number/B4TEBXBTQYE4T3NKG64OFMWGA5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4TEBXBTQYE4T3NKG64OFMWGA5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4TEBXBTQYE4T3NKG64OFMWGA5/action/storage_attestation","attest_author":"https://pith.science/pith/B4TEBXBTQYE4T3NKG64OFMWGA5/action/author_attestation","sign_citation":"https://pith.science/pith/B4TEBXBTQYE4T3NKG64OFMWGA5/action/citation_signature","submit_replication":"https://pith.science/pith/B4TEBXBTQYE4T3NKG64OFMWGA5/action/replication_record"}},"created_at":"2026-05-17T23:54:31.583276+00:00","updated_at":"2026-05-17T23:54:31.583276+00:00"}