{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LMJN5DKC6TC23G3YLPJIAMO27B","short_pith_number":"pith:LMJN5DKC","schema_version":"1.0","canonical_sha256":"5b12de8d42f4c5ad9b785bd28031daf84b8c6e61b9f33ed4740b92d34cdb1ee6","source":{"kind":"arxiv","id":"2402.10474","version":2},"attestation_state":"computed","paper":{"title":"One-Bit Quantization and Sparsification for Multiclass Linear Classification with Strong Regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Babak Hassibi, Danil Akhtiamov, Reza Ghane","submitted_at":"2024-02-16T06:39:40Z","abstract_excerpt":"We study the use of linear regression for multiclass classification in the over-parametrized regime where some of the training data is mislabeled. In such scenarios it is necessary to add an explicit regularization term, $\\lambda f(w)$, for some convex function $f(\\cdot)$, to avoid overfitting the mislabeled data. In our analysis, we assume that the data is sampled from a Gaussian Mixture Model with equal class sizes, and that a proportion $c$ of the training labels is corrupted for each class. Under these assumptions, we prove that the best classification performance is achieved when $f(\\cdot"},"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":"2402.10474","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-16T06:39:40Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4063949d2a474ad7d798191fe68dcc8428a291aa46089fc6e03e7b26bffc6b93","abstract_canon_sha256":"7e4f8b4e97141e6fd14ce9f0a13c9192b98ca2472f1e37b794c73b722e515d46"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:51.823952Z","signature_b64":"I1624q0Qx5G/nz8w/96NCf/JfIvqBQNS/EHkopW6qndx3Rf2WNBJzbgFLKJVajMoa11PsQKbRrxQVTwPtV13DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b12de8d42f4c5ad9b785bd28031daf84b8c6e61b9f33ed4740b92d34cdb1ee6","last_reissued_at":"2026-07-05T09:18:51.823423Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:51.823423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One-Bit Quantization and Sparsification for Multiclass Linear Classification with Strong Regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Babak Hassibi, Danil Akhtiamov, Reza Ghane","submitted_at":"2024-02-16T06:39:40Z","abstract_excerpt":"We study the use of linear regression for multiclass classification in the over-parametrized regime where some of the training data is mislabeled. In such scenarios it is necessary to add an explicit regularization term, $\\lambda f(w)$, for some convex function $f(\\cdot)$, to avoid overfitting the mislabeled data. In our analysis, we assume that the data is sampled from a Gaussian Mixture Model with equal class sizes, and that a proportion $c$ of the training labels is corrupted for each class. Under these assumptions, we prove that the best classification performance is achieved when $f(\\cdot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10474","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/2402.10474/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":"2402.10474","created_at":"2026-07-05T09:18:51.823484+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.10474v2","created_at":"2026-07-05T09:18:51.823484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10474","created_at":"2026-07-05T09:18:51.823484+00:00"},{"alias_kind":"pith_short_12","alias_value":"LMJN5DKC6TC2","created_at":"2026-07-05T09:18:51.823484+00:00"},{"alias_kind":"pith_short_16","alias_value":"LMJN5DKC6TC23G3Y","created_at":"2026-07-05T09:18:51.823484+00:00"},{"alias_kind":"pith_short_8","alias_value":"LMJN5DKC","created_at":"2026-07-05T09:18:51.823484+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/LMJN5DKC6TC23G3YLPJIAMO27B","json":"https://pith.science/pith/LMJN5DKC6TC23G3YLPJIAMO27B.json","graph_json":"https://pith.science/api/pith-number/LMJN5DKC6TC23G3YLPJIAMO27B/graph.json","events_json":"https://pith.science/api/pith-number/LMJN5DKC6TC23G3YLPJIAMO27B/events.json","paper":"https://pith.science/paper/LMJN5DKC"},"agent_actions":{"view_html":"https://pith.science/pith/LMJN5DKC6TC23G3YLPJIAMO27B","download_json":"https://pith.science/pith/LMJN5DKC6TC23G3YLPJIAMO27B.json","view_paper":"https://pith.science/paper/LMJN5DKC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.10474&json=true","fetch_graph":"https://pith.science/api/pith-number/LMJN5DKC6TC23G3YLPJIAMO27B/graph.json","fetch_events":"https://pith.science/api/pith-number/LMJN5DKC6TC23G3YLPJIAMO27B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LMJN5DKC6TC23G3YLPJIAMO27B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LMJN5DKC6TC23G3YLPJIAMO27B/action/storage_attestation","attest_author":"https://pith.science/pith/LMJN5DKC6TC23G3YLPJIAMO27B/action/author_attestation","sign_citation":"https://pith.science/pith/LMJN5DKC6TC23G3YLPJIAMO27B/action/citation_signature","submit_replication":"https://pith.science/pith/LMJN5DKC6TC23G3YLPJIAMO27B/action/replication_record"}},"created_at":"2026-07-05T09:18:51.823484+00:00","updated_at":"2026-07-05T09:18:51.823484+00:00"}