{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LKPHZG4DJFF4KW6ID3J7LQNZQ4","short_pith_number":"pith:LKPHZG4D","schema_version":"1.0","canonical_sha256":"5a9e7c9b83494bc55bc81ed3f5c1b9872abd7f1514808ee2287cb4ecc5a45587","source":{"kind":"arxiv","id":"2305.16427","version":2},"attestation_state":"computed","paper":{"title":"Neural (Tangent Kernel) Collapse","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dana Weitzner, Gitta Kutyniok, Hung-Hsu Chou, Mariia Seleznova, Raja Giryes","submitted_at":"2023-05-25T18:56:34Z","abstract_excerpt":"This work bridges two important concepts: the Neural Tangent Kernel (NTK), which captures the evolution of deep neural networks (DNNs) during training, and the Neural Collapse (NC) phenomenon, which refers to the emergence of symmetry and structure in the last-layer features of well-trained classification DNNs. We adopt the natural assumption that the empirical NTK develops a block structure aligned with the class labels, i.e., samples within the same class have stronger correlations than samples from different classes. Under this assumption, we derive the dynamics of DNNs trained with mean sq"},"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":"2305.16427","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-25T18:56:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c559c73e5ce004313a9dc826af3f894bc4976f16fafb9b48988b3751c5a91863","abstract_canon_sha256":"873d5a89acdfafab75ad0ed994bb1570deb9e8ed28ff37e7ee5facc181a16031"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:29.241359Z","signature_b64":"30TrsJf1ZMTyfS7PhnYkcS12DX7sdY5ri1zixweBbebLdjrkAVuhlroc5slYniDc6yFST3LpQAtkv0YwrHufAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a9e7c9b83494bc55bc81ed3f5c1b9872abd7f1514808ee2287cb4ecc5a45587","last_reissued_at":"2026-07-05T07:09:29.240837Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:29.240837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural (Tangent Kernel) Collapse","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dana Weitzner, Gitta Kutyniok, Hung-Hsu Chou, Mariia Seleznova, Raja Giryes","submitted_at":"2023-05-25T18:56:34Z","abstract_excerpt":"This work bridges two important concepts: the Neural Tangent Kernel (NTK), which captures the evolution of deep neural networks (DNNs) during training, and the Neural Collapse (NC) phenomenon, which refers to the emergence of symmetry and structure in the last-layer features of well-trained classification DNNs. We adopt the natural assumption that the empirical NTK develops a block structure aligned with the class labels, i.e., samples within the same class have stronger correlations than samples from different classes. Under this assumption, we derive the dynamics of DNNs trained with mean sq"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16427","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/2305.16427/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":"2305.16427","created_at":"2026-07-05T07:09:29.240902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.16427v2","created_at":"2026-07-05T07:09:29.240902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16427","created_at":"2026-07-05T07:09:29.240902+00:00"},{"alias_kind":"pith_short_12","alias_value":"LKPHZG4DJFF4","created_at":"2026-07-05T07:09:29.240902+00:00"},{"alias_kind":"pith_short_16","alias_value":"LKPHZG4DJFF4KW6I","created_at":"2026-07-05T07:09:29.240902+00:00"},{"alias_kind":"pith_short_8","alias_value":"LKPHZG4D","created_at":"2026-07-05T07:09:29.240902+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/LKPHZG4DJFF4KW6ID3J7LQNZQ4","json":"https://pith.science/pith/LKPHZG4DJFF4KW6ID3J7LQNZQ4.json","graph_json":"https://pith.science/api/pith-number/LKPHZG4DJFF4KW6ID3J7LQNZQ4/graph.json","events_json":"https://pith.science/api/pith-number/LKPHZG4DJFF4KW6ID3J7LQNZQ4/events.json","paper":"https://pith.science/paper/LKPHZG4D"},"agent_actions":{"view_html":"https://pith.science/pith/LKPHZG4DJFF4KW6ID3J7LQNZQ4","download_json":"https://pith.science/pith/LKPHZG4DJFF4KW6ID3J7LQNZQ4.json","view_paper":"https://pith.science/paper/LKPHZG4D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.16427&json=true","fetch_graph":"https://pith.science/api/pith-number/LKPHZG4DJFF4KW6ID3J7LQNZQ4/graph.json","fetch_events":"https://pith.science/api/pith-number/LKPHZG4DJFF4KW6ID3J7LQNZQ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LKPHZG4DJFF4KW6ID3J7LQNZQ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LKPHZG4DJFF4KW6ID3J7LQNZQ4/action/storage_attestation","attest_author":"https://pith.science/pith/LKPHZG4DJFF4KW6ID3J7LQNZQ4/action/author_attestation","sign_citation":"https://pith.science/pith/LKPHZG4DJFF4KW6ID3J7LQNZQ4/action/citation_signature","submit_replication":"https://pith.science/pith/LKPHZG4DJFF4KW6ID3J7LQNZQ4/action/replication_record"}},"created_at":"2026-07-05T07:09:29.240902+00:00","updated_at":"2026-07-05T07:09:29.240902+00:00"}