{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:N7ICX3WFQCPCV2WLBGZKIASO5S","short_pith_number":"pith:N7ICX3WF","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"},"canonical_sha256":"6fd02beec5809e2aeacb09b2a4024eec9885c365dd69f9c742f769a186cfee64","source":{"kind":"arxiv","id":"2212.12206","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.12206","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"arxiv_version","alias_value":"2212.12206v4","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.12206","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"pith_short_12","alias_value":"N7ICX3WFQCPC","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"pith_short_16","alias_value":"N7ICX3WFQCPCV2WL","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"pith_short_8","alias_value":"N7ICX3WF","created_at":"2026-07-05T08:45:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:N7ICX3WFQCPCV2WLBGZKIASO5S","target":"record","payload":{"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"},"canonical_sha256":"6fd02beec5809e2aeacb09b2a4024eec9885c365dd69f9c742f769a186cfee64","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"},"source_kind":"arxiv","source_id":"2212.12206","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:45:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IW4WAmjnQtq0v7dCtTh4BuuVMc45g/DsHtHBoLFGbPtoadiPQzUKTSw0KfgkNof2rOFnllRZF40sqwlyzGNdBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:50:44.087191Z"},"content_sha256":"3fbb720872eab585527240768c8449dada1a7876ec5b0e3130cceb47bede038f","schema_version":"1.0","event_id":"sha256:3fbb720872eab585527240768c8449dada1a7876ec5b0e3130cceb47bede038f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:N7ICX3WFQCPCV2WLBGZKIASO5S","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:45:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"biwstD441eAl8oCCkn1kQ1P6WcyDEa+vxzzvYtfgRYAzW4+KVmatucz2ddke+XS062MDvSiRC0amReK5td2gAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:50:44.087701Z"},"content_sha256":"63b98c4b96bb26605253546d373cefc7111a121f503dfb89859d97e65257869a","schema_version":"1.0","event_id":"sha256:63b98c4b96bb26605253546d373cefc7111a121f503dfb89859d97e65257869a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N7ICX3WFQCPCV2WLBGZKIASO5S/bundle.json","state_url":"https://pith.science/pith/N7ICX3WFQCPCV2WLBGZKIASO5S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N7ICX3WFQCPCV2WLBGZKIASO5S/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T04:50:44Z","links":{"resolver":"https://pith.science/pith/N7ICX3WFQCPCV2WLBGZKIASO5S","bundle":"https://pith.science/pith/N7ICX3WFQCPCV2WLBGZKIASO5S/bundle.json","state":"https://pith.science/pith/N7ICX3WFQCPCV2WLBGZKIASO5S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N7ICX3WFQCPCV2WLBGZKIASO5S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:N7ICX3WFQCPCV2WLBGZKIASO5S","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8b6bbaca39a882a93e78708172a6045296c46ee081f7d3e7d846bd26d506a966","cross_cats_sorted":["cs.AI","cs.CV","eess.IV","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-23T08:48:34Z","title_canon_sha256":"9732da9a3e4297da886c0602a5c331fd4395c6e2328a7e84d7b518195c207811"},"schema_version":"1.0","source":{"id":"2212.12206","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.12206","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"arxiv_version","alias_value":"2212.12206v4","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.12206","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"pith_short_12","alias_value":"N7ICX3WFQCPC","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"pith_short_16","alias_value":"N7ICX3WFQCPCV2WL","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"pith_short_8","alias_value":"N7ICX3WF","created_at":"2026-07-05T08:45:45Z"}],"graph_snapshots":[{"event_id":"sha256:63b98c4b96bb26605253546d373cefc7111a121f503dfb89859d97e65257869a","target":"graph","created_at":"2026-07-05T08:45:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2212.12206/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Carlos Fernandez-Granda, Jinxin Zhou, Qing Qu, Sheng Liu, Xiao Li, Xinyu Lu, Zhihui Zhu","cross_cats":["cs.AI","cs.CV","eess.IV","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-23T08:48:34Z","title":"Understanding and Improving Transfer Learning of Deep Models via Neural Collapse"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.12206","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3fbb720872eab585527240768c8449dada1a7876ec5b0e3130cceb47bede038f","target":"record","created_at":"2026-07-05T08:45:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8b6bbaca39a882a93e78708172a6045296c46ee081f7d3e7d846bd26d506a966","cross_cats_sorted":["cs.AI","cs.CV","eess.IV","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-23T08:48:34Z","title_canon_sha256":"9732da9a3e4297da886c0602a5c331fd4395c6e2328a7e84d7b518195c207811"},"schema_version":"1.0","source":{"id":"2212.12206","kind":"arxiv","version":4}},"canonical_sha256":"6fd02beec5809e2aeacb09b2a4024eec9885c365dd69f9c742f769a186cfee64","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6fd02beec5809e2aeacb09b2a4024eec9885c365dd69f9c742f769a186cfee64","first_computed_at":"2026-07-05T08:45:45.409535Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:45.409535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F+3I2y6aiP3jEhl4d3WY5LJfcZl0/M//20s6MVhlkMgyeu8xONzjOIQ7XHr9QwCaWu0dtm3tzLFFOcXoN49HBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:45.409955Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.12206","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3fbb720872eab585527240768c8449dada1a7876ec5b0e3130cceb47bede038f","sha256:63b98c4b96bb26605253546d373cefc7111a121f503dfb89859d97e65257869a"],"state_sha256":"90bc6e9ca8ed73726429cc54743d038a453cb8e277372358ec2c57e7354ebec3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TYuOkFmMjGpo1My9igv9Jp5oB6DHIQu3gqHz/+tZz5n4+mfOb5zeC/dmQJZT+b8DUYe4OsKv3NWuXcyX3ywLBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:50:44.091844Z","bundle_sha256":"6127e0c2264660440fdda0286a49430170941a536735f44aac891eab5ca8b38b"}}