{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:P2NFNDDT7WUYN57R4Q4QBEYHJT","short_pith_number":"pith:P2NFNDDT","schema_version":"1.0","canonical_sha256":"7e9a568c73fda986f7f1e4390093074cc9284a5a50e26999fef154fe25e89d89","source":{"kind":"arxiv","id":"2310.15903","version":4},"attestation_state":"computed","paper":{"title":"Neural Collapse in Multi-label Learning with Pick-all-label Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Pengyu Li, Qing Qu, Xiao Li, Yutong Wang","submitted_at":"2023-10-24T15:07:16Z","abstract_excerpt":"We study deep neural networks for the multi-label classification (MLab) task through the lens of neural collapse (NC). Previous works have been restricted to the multi-class classification setting and discovered a prevalent NC phenomenon comprising of the following properties for the last-layer features: (i) the variability of features within every class collapses to zero, (ii) the set of feature means form an equi-angular tight frame (ETF), and (iii) the last layer classifiers collapse to the feature mean upon some scaling. We generalize the study to multi-label learning, and prove for the fi"},"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":"2310.15903","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-24T15:07:16Z","cross_cats_sorted":[],"title_canon_sha256":"ce34beb3c1ca065db713efe58543527c2d71dc6309e948ccba087c6cf5644f8a","abstract_canon_sha256":"bb1fb3e4b561d112c0627aba1e232af4c20b8b48baffaa612d131044c68baebd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:07.055073Z","signature_b64":"rw5nVvHo11HYasx26qsZIJg6ITOygrxrgwRRV533i0FIINhI1MrdUDP03W2QlNwle4qB0fhYS8B+jyITgDvDDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e9a568c73fda986f7f1e4390093074cc9284a5a50e26999fef154fe25e89d89","last_reissued_at":"2026-07-05T08:34:07.054580Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:07.054580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Collapse in Multi-label Learning with Pick-all-label Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Pengyu Li, Qing Qu, Xiao Li, Yutong Wang","submitted_at":"2023-10-24T15:07:16Z","abstract_excerpt":"We study deep neural networks for the multi-label classification (MLab) task through the lens of neural collapse (NC). Previous works have been restricted to the multi-class classification setting and discovered a prevalent NC phenomenon comprising of the following properties for the last-layer features: (i) the variability of features within every class collapses to zero, (ii) the set of feature means form an equi-angular tight frame (ETF), and (iii) the last layer classifiers collapse to the feature mean upon some scaling. We generalize the study to multi-label learning, and prove for the fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15903","kind":"arxiv","version":4},"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/2310.15903/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":"2310.15903","created_at":"2026-07-05T08:34:07.054639+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.15903v4","created_at":"2026-07-05T08:34:07.054639+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15903","created_at":"2026-07-05T08:34:07.054639+00:00"},{"alias_kind":"pith_short_12","alias_value":"P2NFNDDT7WUY","created_at":"2026-07-05T08:34:07.054639+00:00"},{"alias_kind":"pith_short_16","alias_value":"P2NFNDDT7WUYN57R","created_at":"2026-07-05T08:34:07.054639+00:00"},{"alias_kind":"pith_short_8","alias_value":"P2NFNDDT","created_at":"2026-07-05T08:34:07.054639+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"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":85,"is_internal_anchor":false},{"citing_arxiv_id":"2510.01105","citing_title":"Geometric Analysis of Neural Regression Collapse via Intrinsic Dimension","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P2NFNDDT7WUYN57R4Q4QBEYHJT","json":"https://pith.science/pith/P2NFNDDT7WUYN57R4Q4QBEYHJT.json","graph_json":"https://pith.science/api/pith-number/P2NFNDDT7WUYN57R4Q4QBEYHJT/graph.json","events_json":"https://pith.science/api/pith-number/P2NFNDDT7WUYN57R4Q4QBEYHJT/events.json","paper":"https://pith.science/paper/P2NFNDDT"},"agent_actions":{"view_html":"https://pith.science/pith/P2NFNDDT7WUYN57R4Q4QBEYHJT","download_json":"https://pith.science/pith/P2NFNDDT7WUYN57R4Q4QBEYHJT.json","view_paper":"https://pith.science/paper/P2NFNDDT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.15903&json=true","fetch_graph":"https://pith.science/api/pith-number/P2NFNDDT7WUYN57R4Q4QBEYHJT/graph.json","fetch_events":"https://pith.science/api/pith-number/P2NFNDDT7WUYN57R4Q4QBEYHJT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P2NFNDDT7WUYN57R4Q4QBEYHJT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P2NFNDDT7WUYN57R4Q4QBEYHJT/action/storage_attestation","attest_author":"https://pith.science/pith/P2NFNDDT7WUYN57R4Q4QBEYHJT/action/author_attestation","sign_citation":"https://pith.science/pith/P2NFNDDT7WUYN57R4Q4QBEYHJT/action/citation_signature","submit_replication":"https://pith.science/pith/P2NFNDDT7WUYN57R4Q4QBEYHJT/action/replication_record"}},"created_at":"2026-07-05T08:34:07.054639+00:00","updated_at":"2026-07-05T08:34:07.054639+00:00"}