{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GUJPU7CTKQ3VLU76WDSNTCN3LQ","short_pith_number":"pith:GUJPU7CT","schema_version":"1.0","canonical_sha256":"3512fa7c53543755d3feb0e4d989bb5c17c638dfb4ae8d3015b7287af61074f1","source":{"kind":"arxiv","id":"2011.11619","version":1},"attestation_state":"computed","paper":{"title":"Neural collapse with unconstrained features","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dustin G. Mixon, Hans Parshall, Jianzong Pi","submitted_at":"2020-11-23T18:49:36Z","abstract_excerpt":"Neural collapse is an emergent phenomenon in deep learning that was recently discovered by Papyan, Han and Donoho. We propose a simple \"unconstrained features model\" in which neural collapse also emerges empirically. By studying this model, we provide some explanation for the emergence of neural collapse in terms of the landscape of empirical risk."},"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":"2011.11619","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-11-23T18:49:36Z","cross_cats_sorted":[],"title_canon_sha256":"357d47e947fb36b568b52ab7ae8a954a9e00cf3c0c03b2a3e947d462b5bc68c9","abstract_canon_sha256":"39b39df8da02046a04b63f85a37d80fe993cfd99b407a375460e2f59d651238f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:53:44.229036Z","signature_b64":"muQetIKmiDe9+To3xlH6azswiT5iyuB1D9P/P8V9t458jh3tGw81tjj8j2ulX3MBRFKfShoW7TQjnLsvJlwkBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3512fa7c53543755d3feb0e4d989bb5c17c638dfb4ae8d3015b7287af61074f1","last_reissued_at":"2026-07-05T01:53:44.228659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:53:44.228659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural collapse with unconstrained features","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dustin G. Mixon, Hans Parshall, Jianzong Pi","submitted_at":"2020-11-23T18:49:36Z","abstract_excerpt":"Neural collapse is an emergent phenomenon in deep learning that was recently discovered by Papyan, Han and Donoho. We propose a simple \"unconstrained features model\" in which neural collapse also emerges empirically. By studying this model, we provide some explanation for the emergence of neural collapse in terms of the landscape of empirical risk."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.11619","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/2011.11619/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":"2011.11619","created_at":"2026-07-05T01:53:44.228715+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.11619v1","created_at":"2026-07-05T01:53:44.228715+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.11619","created_at":"2026-07-05T01:53:44.228715+00:00"},{"alias_kind":"pith_short_12","alias_value":"GUJPU7CTKQ3V","created_at":"2026-07-05T01:53:44.228715+00:00"},{"alias_kind":"pith_short_16","alias_value":"GUJPU7CTKQ3VLU76","created_at":"2026-07-05T01:53:44.228715+00:00"},{"alias_kind":"pith_short_8","alias_value":"GUJPU7CT","created_at":"2026-07-05T01:53:44.228715+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29679","citing_title":"Learning as Observable Matrix Dynamics: Diffusive Relaxations versus Phase Transitions","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20302","citing_title":"Neural Collapse by Design: Learning Class Prototypes on the Hypersphere","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20302","citing_title":"Neural Collapse by Design: Learning Class Prototypes on the Hypersphere","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2510.01105","citing_title":"Geometric Analysis of Neural Regression Collapse via Intrinsic Dimension","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GUJPU7CTKQ3VLU76WDSNTCN3LQ","json":"https://pith.science/pith/GUJPU7CTKQ3VLU76WDSNTCN3LQ.json","graph_json":"https://pith.science/api/pith-number/GUJPU7CTKQ3VLU76WDSNTCN3LQ/graph.json","events_json":"https://pith.science/api/pith-number/GUJPU7CTKQ3VLU76WDSNTCN3LQ/events.json","paper":"https://pith.science/paper/GUJPU7CT"},"agent_actions":{"view_html":"https://pith.science/pith/GUJPU7CTKQ3VLU76WDSNTCN3LQ","download_json":"https://pith.science/pith/GUJPU7CTKQ3VLU76WDSNTCN3LQ.json","view_paper":"https://pith.science/paper/GUJPU7CT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.11619&json=true","fetch_graph":"https://pith.science/api/pith-number/GUJPU7CTKQ3VLU76WDSNTCN3LQ/graph.json","fetch_events":"https://pith.science/api/pith-number/GUJPU7CTKQ3VLU76WDSNTCN3LQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GUJPU7CTKQ3VLU76WDSNTCN3LQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GUJPU7CTKQ3VLU76WDSNTCN3LQ/action/storage_attestation","attest_author":"https://pith.science/pith/GUJPU7CTKQ3VLU76WDSNTCN3LQ/action/author_attestation","sign_citation":"https://pith.science/pith/GUJPU7CTKQ3VLU76WDSNTCN3LQ/action/citation_signature","submit_replication":"https://pith.science/pith/GUJPU7CTKQ3VLU76WDSNTCN3LQ/action/replication_record"}},"created_at":"2026-07-05T01:53:44.228715+00:00","updated_at":"2026-07-05T01:53:44.228715+00:00"}