{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KLG3S5JYDSZWYR6CO7GA6TMC3G","short_pith_number":"pith:KLG3S5JY","schema_version":"1.0","canonical_sha256":"52cdb975381cb36c47c277cc0f4d82d99820316877f53e48e107ce21c62f887e","source":{"kind":"arxiv","id":"2411.17278","version":1},"attestation_state":"computed","paper":{"title":"The Exploration of Neural Collapse under Imbalanced Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Haixia Liu","submitted_at":"2024-11-26T09:59:34Z","abstract_excerpt":"Neural collapse, a newly identified characteristic, describes a property of solutions during model training. In this paper, we explore neural collapse in the context of imbalanced data. We consider the $L$-extended unconstrained feature model with a bias term and provide a theoretical analysis of global minimizer.\n  Our findings include: (1) Features within the same class converge to their class mean, similar to both the balanced case and the imbalanced case without bias. (2) The geometric structure is mainly on the left orthonormal transformation of the product of $L$ linear classifiers and t"},"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":"2411.17278","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-26T09:59:34Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"1f36e3fbe9f8eec8c71900c13e62d7f6d24b23ac57d8e45be5d27da7a43e23b3","abstract_canon_sha256":"8d34e76a2454ea203df6f441c56fbfe4b3874ebd1f63b3a8cb43107948579422"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:29.976528Z","signature_b64":"yP6pOXMpL5IIEniNR44AG/NkWJ5GdMWSByiC5r9jqd32Uq0vlwRj1B8u/qFuIZi8Ut9kMpMcviWDDiXqHFM6BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52cdb975381cb36c47c277cc0f4d82d99820316877f53e48e107ce21c62f887e","last_reissued_at":"2026-07-05T09:40:29.976161Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:29.976161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Exploration of Neural Collapse under Imbalanced Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Haixia Liu","submitted_at":"2024-11-26T09:59:34Z","abstract_excerpt":"Neural collapse, a newly identified characteristic, describes a property of solutions during model training. In this paper, we explore neural collapse in the context of imbalanced data. We consider the $L$-extended unconstrained feature model with a bias term and provide a theoretical analysis of global minimizer.\n  Our findings include: (1) Features within the same class converge to their class mean, similar to both the balanced case and the imbalanced case without bias. (2) The geometric structure is mainly on the left orthonormal transformation of the product of $L$ linear classifiers and t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17278","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/2411.17278/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":"2411.17278","created_at":"2026-07-05T09:40:29.976218+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.17278v1","created_at":"2026-07-05T09:40:29.976218+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17278","created_at":"2026-07-05T09:40:29.976218+00:00"},{"alias_kind":"pith_short_12","alias_value":"KLG3S5JYDSZW","created_at":"2026-07-05T09:40:29.976218+00:00"},{"alias_kind":"pith_short_16","alias_value":"KLG3S5JYDSZWYR6C","created_at":"2026-07-05T09:40:29.976218+00:00"},{"alias_kind":"pith_short_8","alias_value":"KLG3S5JY","created_at":"2026-07-05T09:40:29.976218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00344","citing_title":"The role of class encoding in neural collapse","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KLG3S5JYDSZWYR6CO7GA6TMC3G","json":"https://pith.science/pith/KLG3S5JYDSZWYR6CO7GA6TMC3G.json","graph_json":"https://pith.science/api/pith-number/KLG3S5JYDSZWYR6CO7GA6TMC3G/graph.json","events_json":"https://pith.science/api/pith-number/KLG3S5JYDSZWYR6CO7GA6TMC3G/events.json","paper":"https://pith.science/paper/KLG3S5JY"},"agent_actions":{"view_html":"https://pith.science/pith/KLG3S5JYDSZWYR6CO7GA6TMC3G","download_json":"https://pith.science/pith/KLG3S5JYDSZWYR6CO7GA6TMC3G.json","view_paper":"https://pith.science/paper/KLG3S5JY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.17278&json=true","fetch_graph":"https://pith.science/api/pith-number/KLG3S5JYDSZWYR6CO7GA6TMC3G/graph.json","fetch_events":"https://pith.science/api/pith-number/KLG3S5JYDSZWYR6CO7GA6TMC3G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KLG3S5JYDSZWYR6CO7GA6TMC3G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KLG3S5JYDSZWYR6CO7GA6TMC3G/action/storage_attestation","attest_author":"https://pith.science/pith/KLG3S5JYDSZWYR6CO7GA6TMC3G/action/author_attestation","sign_citation":"https://pith.science/pith/KLG3S5JYDSZWYR6CO7GA6TMC3G/action/citation_signature","submit_replication":"https://pith.science/pith/KLG3S5JYDSZWYR6CO7GA6TMC3G/action/replication_record"}},"created_at":"2026-07-05T09:40:29.976218+00:00","updated_at":"2026-07-05T09:40:29.976218+00:00"}