{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EX5275ZFOSP3GFXWWSALVD3VUQ","short_pith_number":"pith:EX5275ZF","schema_version":"1.0","canonical_sha256":"25fbaff725749fb316f6b480ba8f75a4272a061bdfe6d2c3b9d67e9fb551b9c1","source":{"kind":"arxiv","id":"2309.09725","version":2},"attestation_state":"computed","paper":{"title":"Neural Collapse for Unconstrained Feature Model under Cross-entropy Loss with Imbalanced Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Shuyang Ling, Wanli Hong","submitted_at":"2023-09-18T12:45:08Z","abstract_excerpt":"Recent years have witnessed the huge success of deep neural networks (DNNs) in various tasks of computer vision and text processing. Interestingly, these DNNs with massive number of parameters share similar structural properties on their feature representation and last-layer classifier at terminal phase of training (TPT). Specifically, if the training data are balanced (each class shares the same number of samples), it is observed that the feature vectors of samples from the same class converge to their corresponding in-class mean features and their pairwise angles are the same. This fascinati"},"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":"2309.09725","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-09-18T12:45:08Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"4a12b7e36e935405c9eff5167d318236a85064add34c9e74da1324a3106e15b2","abstract_canon_sha256":"199188bda5c6be0bf7a036279a2833d3fdc6f75cbd63f92f963fcdadf7fbff9d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:50.611648Z","signature_b64":"n1SmKtJMSsaRnk7Iu/gqAUZYsRoJi/+bDVcyAPKM46t2mZHuPhACeT/lTvencOeFBCOkRhNyVEmOne1Zj9HJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25fbaff725749fb316f6b480ba8f75a4272a061bdfe6d2c3b9d67e9fb551b9c1","last_reissued_at":"2026-07-05T07:04:50.611137Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:50.611137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Collapse for Unconstrained Feature Model under Cross-entropy Loss with Imbalanced Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Shuyang Ling, Wanli Hong","submitted_at":"2023-09-18T12:45:08Z","abstract_excerpt":"Recent years have witnessed the huge success of deep neural networks (DNNs) in various tasks of computer vision and text processing. Interestingly, these DNNs with massive number of parameters share similar structural properties on their feature representation and last-layer classifier at terminal phase of training (TPT). Specifically, if the training data are balanced (each class shares the same number of samples), it is observed that the feature vectors of samples from the same class converge to their corresponding in-class mean features and their pairwise angles are the same. This fascinati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09725","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/2309.09725/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":"2309.09725","created_at":"2026-07-05T07:04:50.611200+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.09725v2","created_at":"2026-07-05T07:04:50.611200+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09725","created_at":"2026-07-05T07:04:50.611200+00:00"},{"alias_kind":"pith_short_12","alias_value":"EX5275ZFOSP3","created_at":"2026-07-05T07:04:50.611200+00:00"},{"alias_kind":"pith_short_16","alias_value":"EX5275ZFOSP3GFXW","created_at":"2026-07-05T07:04:50.611200+00:00"},{"alias_kind":"pith_short_8","alias_value":"EX5275ZF","created_at":"2026-07-05T07:04:50.611200+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23087","citing_title":"The Implicit Bias of Depth: From Neural Collapse to Softmax Codes","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2510.01105","citing_title":"Geometric Analysis of Neural Regression Collapse via Intrinsic Dimension","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10047","citing_title":"Rethinking Loss Reweighting for Imbalance Learning as an Inverse Problem: A Neural Collapse Point of View","ref_index":4,"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":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EX5275ZFOSP3GFXWWSALVD3VUQ","json":"https://pith.science/pith/EX5275ZFOSP3GFXWWSALVD3VUQ.json","graph_json":"https://pith.science/api/pith-number/EX5275ZFOSP3GFXWWSALVD3VUQ/graph.json","events_json":"https://pith.science/api/pith-number/EX5275ZFOSP3GFXWWSALVD3VUQ/events.json","paper":"https://pith.science/paper/EX5275ZF"},"agent_actions":{"view_html":"https://pith.science/pith/EX5275ZFOSP3GFXWWSALVD3VUQ","download_json":"https://pith.science/pith/EX5275ZFOSP3GFXWWSALVD3VUQ.json","view_paper":"https://pith.science/paper/EX5275ZF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.09725&json=true","fetch_graph":"https://pith.science/api/pith-number/EX5275ZFOSP3GFXWWSALVD3VUQ/graph.json","fetch_events":"https://pith.science/api/pith-number/EX5275ZFOSP3GFXWWSALVD3VUQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EX5275ZFOSP3GFXWWSALVD3VUQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EX5275ZFOSP3GFXWWSALVD3VUQ/action/storage_attestation","attest_author":"https://pith.science/pith/EX5275ZFOSP3GFXWWSALVD3VUQ/action/author_attestation","sign_citation":"https://pith.science/pith/EX5275ZFOSP3GFXWWSALVD3VUQ/action/citation_signature","submit_replication":"https://pith.science/pith/EX5275ZFOSP3GFXWWSALVD3VUQ/action/replication_record"}},"created_at":"2026-07-05T07:04:50.611200+00:00","updated_at":"2026-07-05T07:04:50.611200+00:00"}