{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IEWBLMASNJIBO3MIOHCLNJJVMS","short_pith_number":"pith:IEWBLMAS","schema_version":"1.0","canonical_sha256":"412c15b0126a50176d8871c4b6a53564a7b47482f26ab478a56360e36cee4bf9","source":{"kind":"arxiv","id":"2202.08384","version":1},"attestation_state":"computed","paper":{"title":"Limitations of Neural Collapse for Understanding Generalization in Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Like Hui, Mikhail Belkin, Preetum Nakkiran","submitted_at":"2022-02-17T00:20:12Z","abstract_excerpt":"The recent work of Papyan, Han, & Donoho (2020) presented an intriguing \"Neural Collapse\" phenomenon, showing a structural property of interpolating classifiers in the late stage of training. This opened a rich area of exploration studying this phenomenon. Our motivation is to study the upper limits of this research program: How far will understanding Neural Collapse take us in understanding deep learning? First, we investigate its role in generalization. We refine the Neural Collapse conjecture into two separate conjectures: collapse on the train set (an optimization property) and collapse on"},"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":"2202.08384","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-17T00:20:12Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"296bcd978af71d1967049e19052c4cf1afb705e36f7c22f5d6e8fadb21dd8cf9","abstract_canon_sha256":"df4ff36329bb4677500aabccca870d0e33c30b9c106b9d0e85c91d652d65fa8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:57:45.237581Z","signature_b64":"pQALEIxpvVsQ4w/iZoD/E+u236ViBvY6/W904BMjVyut9URCj+ebBwPyNSj6r6AkY9jE2yJPMWzL9TZJsXLXAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"412c15b0126a50176d8871c4b6a53564a7b47482f26ab478a56360e36cee4bf9","last_reissued_at":"2026-07-05T03:57:45.237054Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:57:45.237054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Limitations of Neural Collapse for Understanding Generalization in Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Like Hui, Mikhail Belkin, Preetum Nakkiran","submitted_at":"2022-02-17T00:20:12Z","abstract_excerpt":"The recent work of Papyan, Han, & Donoho (2020) presented an intriguing \"Neural Collapse\" phenomenon, showing a structural property of interpolating classifiers in the late stage of training. This opened a rich area of exploration studying this phenomenon. Our motivation is to study the upper limits of this research program: How far will understanding Neural Collapse take us in understanding deep learning? First, we investigate its role in generalization. We refine the Neural Collapse conjecture into two separate conjectures: collapse on the train set (an optimization property) and collapse on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.08384","kind":"arxiv","version":1},"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/2202.08384/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":"2202.08384","created_at":"2026-07-05T03:57:45.237129+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.08384v1","created_at":"2026-07-05T03:57:45.237129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.08384","created_at":"2026-07-05T03:57:45.237129+00:00"},{"alias_kind":"pith_short_12","alias_value":"IEWBLMASNJIB","created_at":"2026-07-05T03:57:45.237129+00:00"},{"alias_kind":"pith_short_16","alias_value":"IEWBLMASNJIBO3MI","created_at":"2026-07-05T03:57:45.237129+00:00"},{"alias_kind":"pith_short_8","alias_value":"IEWBLMAS","created_at":"2026-07-05T03:57:45.237129+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":123,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20302","citing_title":"Neural Collapse by Design: Learning Class Prototypes on the Hypersphere","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20302","citing_title":"Neural Collapse by Design: Learning Class Prototypes on the Hypersphere","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2510.01105","citing_title":"Geometric Analysis of Neural Regression Collapse via Intrinsic Dimension","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IEWBLMASNJIBO3MIOHCLNJJVMS","json":"https://pith.science/pith/IEWBLMASNJIBO3MIOHCLNJJVMS.json","graph_json":"https://pith.science/api/pith-number/IEWBLMASNJIBO3MIOHCLNJJVMS/graph.json","events_json":"https://pith.science/api/pith-number/IEWBLMASNJIBO3MIOHCLNJJVMS/events.json","paper":"https://pith.science/paper/IEWBLMAS"},"agent_actions":{"view_html":"https://pith.science/pith/IEWBLMASNJIBO3MIOHCLNJJVMS","download_json":"https://pith.science/pith/IEWBLMASNJIBO3MIOHCLNJJVMS.json","view_paper":"https://pith.science/paper/IEWBLMAS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.08384&json=true","fetch_graph":"https://pith.science/api/pith-number/IEWBLMASNJIBO3MIOHCLNJJVMS/graph.json","fetch_events":"https://pith.science/api/pith-number/IEWBLMASNJIBO3MIOHCLNJJVMS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IEWBLMASNJIBO3MIOHCLNJJVMS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IEWBLMASNJIBO3MIOHCLNJJVMS/action/storage_attestation","attest_author":"https://pith.science/pith/IEWBLMASNJIBO3MIOHCLNJJVMS/action/author_attestation","sign_citation":"https://pith.science/pith/IEWBLMASNJIBO3MIOHCLNJJVMS/action/citation_signature","submit_replication":"https://pith.science/pith/IEWBLMASNJIBO3MIOHCLNJJVMS/action/replication_record"}},"created_at":"2026-07-05T03:57:45.237129+00:00","updated_at":"2026-07-05T03:57:45.237129+00:00"}