{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BJ2DMB22N5ISVFXJ3HG2AUCFSS","short_pith_number":"pith:BJ2DMB22","schema_version":"1.0","canonical_sha256":"0a7436075a6f512a96e9d9cda0504594ba2a76ee534c21aaefa42377d1796064","source":{"kind":"arxiv","id":"2406.02105","version":3},"attestation_state":"computed","paper":{"title":"Can Kernel Methods Explain How the Data Affects Neural Collapse?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Tom Tirer, Vignesh Kothapalli","submitted_at":"2024-06-04T08:33:56Z","abstract_excerpt":"A vast amount of literature has recently focused on the \"Neural Collapse\" (NC) phenomenon, which emerges when training neural network (NN) classifiers beyond the zero training error point. The core component of NC is the decrease in the within-class variability of the network's deepest features, dubbed as NC1. The theoretical works that study NC are typically based on simplified unconstrained features models (UFMs) that mask any effect of the data on the extent of collapse. To address this limitation of UFMs, this paper explores the possibility of analyzing NC1 using kernels associated with sh"},"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":"2406.02105","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-04T08:33:56Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT","stat.ML"],"title_canon_sha256":"a7f1af642c40e22649d16f8bc42ff827fa69d04d2477e2b4eb9bfddab52bf465","abstract_canon_sha256":"c78b23cf4099b3116a90743f7e7b15f194f2cda412db8eaaed92f432cb8c292b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:45.478829Z","signature_b64":"IQDRdIQ0h2mwouLaTARtDWWzS/ZoC3SVt7jLtbYMtyT6ukZ73VEA+S/dmUXxo6nPR6Otyzu5w6ZuEv4iSynbDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a7436075a6f512a96e9d9cda0504594ba2a76ee534c21aaefa42377d1796064","last_reissued_at":"2026-07-05T10:53:45.478329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:45.478329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Kernel Methods Explain How the Data Affects Neural Collapse?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Tom Tirer, Vignesh Kothapalli","submitted_at":"2024-06-04T08:33:56Z","abstract_excerpt":"A vast amount of literature has recently focused on the \"Neural Collapse\" (NC) phenomenon, which emerges when training neural network (NN) classifiers beyond the zero training error point. The core component of NC is the decrease in the within-class variability of the network's deepest features, dubbed as NC1. The theoretical works that study NC are typically based on simplified unconstrained features models (UFMs) that mask any effect of the data on the extent of collapse. To address this limitation of UFMs, this paper explores the possibility of analyzing NC1 using kernels associated with sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02105","kind":"arxiv","version":3},"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/2406.02105/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":"2406.02105","created_at":"2026-07-05T10:53:45.478390+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02105v3","created_at":"2026-07-05T10:53:45.478390+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02105","created_at":"2026-07-05T10:53:45.478390+00:00"},{"alias_kind":"pith_short_12","alias_value":"BJ2DMB22N5IS","created_at":"2026-07-05T10:53:45.478390+00:00"},{"alias_kind":"pith_short_16","alias_value":"BJ2DMB22N5ISVFXJ","created_at":"2026-07-05T10:53:45.478390+00:00"},{"alias_kind":"pith_short_8","alias_value":"BJ2DMB22","created_at":"2026-07-05T10:53:45.478390+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/BJ2DMB22N5ISVFXJ3HG2AUCFSS","json":"https://pith.science/pith/BJ2DMB22N5ISVFXJ3HG2AUCFSS.json","graph_json":"https://pith.science/api/pith-number/BJ2DMB22N5ISVFXJ3HG2AUCFSS/graph.json","events_json":"https://pith.science/api/pith-number/BJ2DMB22N5ISVFXJ3HG2AUCFSS/events.json","paper":"https://pith.science/paper/BJ2DMB22"},"agent_actions":{"view_html":"https://pith.science/pith/BJ2DMB22N5ISVFXJ3HG2AUCFSS","download_json":"https://pith.science/pith/BJ2DMB22N5ISVFXJ3HG2AUCFSS.json","view_paper":"https://pith.science/paper/BJ2DMB22","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02105&json=true","fetch_graph":"https://pith.science/api/pith-number/BJ2DMB22N5ISVFXJ3HG2AUCFSS/graph.json","fetch_events":"https://pith.science/api/pith-number/BJ2DMB22N5ISVFXJ3HG2AUCFSS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BJ2DMB22N5ISVFXJ3HG2AUCFSS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BJ2DMB22N5ISVFXJ3HG2AUCFSS/action/storage_attestation","attest_author":"https://pith.science/pith/BJ2DMB22N5ISVFXJ3HG2AUCFSS/action/author_attestation","sign_citation":"https://pith.science/pith/BJ2DMB22N5ISVFXJ3HG2AUCFSS/action/citation_signature","submit_replication":"https://pith.science/pith/BJ2DMB22N5ISVFXJ3HG2AUCFSS/action/replication_record"}},"created_at":"2026-07-05T10:53:45.478390+00:00","updated_at":"2026-07-05T10:53:45.478390+00:00"}