{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:N7ICX3WFQCPCV2WLBGZKIASO5S","short_pith_number":"pith:N7ICX3WF","schema_version":"1.0","canonical_sha256":"6fd02beec5809e2aeacb09b2a4024eec9885c365dd69f9c742f769a186cfee64","source":{"kind":"arxiv","id":"2212.12206","version":4},"attestation_state":"computed","paper":{"title":"Understanding and Improving Transfer Learning of Deep Models via Neural Collapse","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","eess.IV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Carlos Fernandez-Granda, Jinxin Zhou, Qing Qu, Sheng Liu, Xiao Li, Xinyu Lu, Zhihui Zhu","submitted_at":"2022-12-23T08:48:34Z","abstract_excerpt":"With the ever-increasing complexity of large-scale pre-trained models coupled with a shortage of labeled data for downstream training, transfer learning has become the primary approach in many fields, including natural language processing, computer vision, and multi-modal learning. Despite recent progress, the fine-tuning process for large-scale pre-trained models in vision still mostly relies on trial and error. This work investigates the relationship between neural collapse (NC) and transfer learning for classification problems. NC is an intriguing while prevalent phenomenon that has been re"},"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":"2212.12206","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-23T08:48:34Z","cross_cats_sorted":["cs.AI","cs.CV","eess.IV","stat.ML"],"title_canon_sha256":"9732da9a3e4297da886c0602a5c331fd4395c6e2328a7e84d7b518195c207811","abstract_canon_sha256":"8b6bbaca39a882a93e78708172a6045296c46ee081f7d3e7d846bd26d506a966"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:45.409955Z","signature_b64":"F+3I2y6aiP3jEhl4d3WY5LJfcZl0/M//20s6MVhlkMgyeu8xONzjOIQ7XHr9QwCaWu0dtm3tzLFFOcXoN49HBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fd02beec5809e2aeacb09b2a4024eec9885c365dd69f9c742f769a186cfee64","last_reissued_at":"2026-07-05T08:45:45.409535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:45.409535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding and Improving Transfer Learning of Deep Models via Neural Collapse","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","eess.IV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Carlos Fernandez-Granda, Jinxin Zhou, Qing Qu, Sheng Liu, Xiao Li, Xinyu Lu, Zhihui Zhu","submitted_at":"2022-12-23T08:48:34Z","abstract_excerpt":"With the ever-increasing complexity of large-scale pre-trained models coupled with a shortage of labeled data for downstream training, transfer learning has become the primary approach in many fields, including natural language processing, computer vision, and multi-modal learning. Despite recent progress, the fine-tuning process for large-scale pre-trained models in vision still mostly relies on trial and error. This work investigates the relationship between neural collapse (NC) and transfer learning for classification problems. NC is an intriguing while prevalent phenomenon that has been re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.12206","kind":"arxiv","version":4},"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/2212.12206/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":"2212.12206","created_at":"2026-07-05T08:45:45.409590+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.12206v4","created_at":"2026-07-05T08:45:45.409590+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.12206","created_at":"2026-07-05T08:45:45.409590+00:00"},{"alias_kind":"pith_short_12","alias_value":"N7ICX3WFQCPC","created_at":"2026-07-05T08:45:45.409590+00:00"},{"alias_kind":"pith_short_16","alias_value":"N7ICX3WFQCPCV2WL","created_at":"2026-07-05T08:45:45.409590+00:00"},{"alias_kind":"pith_short_8","alias_value":"N7ICX3WF","created_at":"2026-07-05T08:45:45.409590+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02106","citing_title":"When Tabular Foundation Models Transfer Across Modalities: A Systematic Evaluation Across 95 Datasets, 7 Modalities, and Two Regimes","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23087","citing_title":"The Implicit Bias of Depth: From Neural Collapse to Softmax Codes","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2510.01105","citing_title":"Geometric Analysis of Neural Regression Collapse via Intrinsic Dimension","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12843","citing_title":"Bayesian Model Merging","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11291","citing_title":"Optimal Representations for Generalized Contrastive Learning with Imbalanced Datasets","ref_index":118,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01897","citing_title":"How Label Imbalance Shapes Geometry: A General Spectral Analysis of Multi-Label Neural Collapse","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N7ICX3WFQCPCV2WLBGZKIASO5S","json":"https://pith.science/pith/N7ICX3WFQCPCV2WLBGZKIASO5S.json","graph_json":"https://pith.science/api/pith-number/N7ICX3WFQCPCV2WLBGZKIASO5S/graph.json","events_json":"https://pith.science/api/pith-number/N7ICX3WFQCPCV2WLBGZKIASO5S/events.json","paper":"https://pith.science/paper/N7ICX3WF"},"agent_actions":{"view_html":"https://pith.science/pith/N7ICX3WFQCPCV2WLBGZKIASO5S","download_json":"https://pith.science/pith/N7ICX3WFQCPCV2WLBGZKIASO5S.json","view_paper":"https://pith.science/paper/N7ICX3WF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.12206&json=true","fetch_graph":"https://pith.science/api/pith-number/N7ICX3WFQCPCV2WLBGZKIASO5S/graph.json","fetch_events":"https://pith.science/api/pith-number/N7ICX3WFQCPCV2WLBGZKIASO5S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N7ICX3WFQCPCV2WLBGZKIASO5S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N7ICX3WFQCPCV2WLBGZKIASO5S/action/storage_attestation","attest_author":"https://pith.science/pith/N7ICX3WFQCPCV2WLBGZKIASO5S/action/author_attestation","sign_citation":"https://pith.science/pith/N7ICX3WFQCPCV2WLBGZKIASO5S/action/citation_signature","submit_replication":"https://pith.science/pith/N7ICX3WFQCPCV2WLBGZKIASO5S/action/replication_record"}},"created_at":"2026-07-05T08:45:45.409590+00:00","updated_at":"2026-07-05T08:45:45.409590+00:00"}