{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XAOR2CG4FY3GRDG73UR5SB722N","short_pith_number":"pith:XAOR2CG4","schema_version":"1.0","canonical_sha256":"b81d1d08dc2e36688cdfdd23d907fad368ad5959061e3b0c14d0531e134ab1ed","source":{"kind":"arxiv","id":"2002.11328","version":3},"attestation_state":"computed","paper":{"title":"Rethinking Bias-Variance Trade-off for Generalization of Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chong You, Jacob Steinhardt, Yaodong Yu, Yi Ma, Zitong Yang","submitted_at":"2020-02-26T07:21:54Z","abstract_excerpt":"The classical bias-variance trade-off predicts that bias decreases and variance increase with model complexity, leading to a U-shaped risk curve. Recent work calls this into question for neural networks and other over-parameterized models, for which it is often observed that larger models generalize better. We provide a simple explanation for this by measuring the bias and variance of neural networks: while the bias is monotonically decreasing as in the classical theory, the variance is unimodal or bell-shaped: it increases then decreases with the width of the network. We vary the network arch"},"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":"2002.11328","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-26T07:21:54Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e59663841e76a0a62606bc94ef022df9554dc41d07ce7c420cdb9deea4b2552d","abstract_canon_sha256":"94cf676b6ce0f1a68514ff7847c59e3ff97f1fb59a9e2cc6dfc5de3d0ea315e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:57:50.317445Z","signature_b64":"+oY/PkLbu96zYyMSDxWTE/YDBrU6jcYhCI8igP0jkaGl0BXEOjVmm+8TVo5dj0wj93Z0lVN6VdnQmmoPFFtwCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b81d1d08dc2e36688cdfdd23d907fad368ad5959061e3b0c14d0531e134ab1ed","last_reissued_at":"2026-07-05T01:57:50.317023Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:57:50.317023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Bias-Variance Trade-off for Generalization of Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chong You, Jacob Steinhardt, Yaodong Yu, Yi Ma, Zitong Yang","submitted_at":"2020-02-26T07:21:54Z","abstract_excerpt":"The classical bias-variance trade-off predicts that bias decreases and variance increase with model complexity, leading to a U-shaped risk curve. Recent work calls this into question for neural networks and other over-parameterized models, for which it is often observed that larger models generalize better. We provide a simple explanation for this by measuring the bias and variance of neural networks: while the bias is monotonically decreasing as in the classical theory, the variance is unimodal or bell-shaped: it increases then decreases with the width of the network. We vary the network arch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.11328","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/2002.11328/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":"2002.11328","created_at":"2026-07-05T01:57:50.317084+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.11328v3","created_at":"2026-07-05T01:57:50.317084+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.11328","created_at":"2026-07-05T01:57:50.317084+00:00"},{"alias_kind":"pith_short_12","alias_value":"XAOR2CG4FY3G","created_at":"2026-07-05T01:57:50.317084+00:00"},{"alias_kind":"pith_short_16","alias_value":"XAOR2CG4FY3GRDG7","created_at":"2026-07-05T01:57:50.317084+00:00"},{"alias_kind":"pith_short_8","alias_value":"XAOR2CG4","created_at":"2026-07-05T01:57:50.317084+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/XAOR2CG4FY3GRDG73UR5SB722N","json":"https://pith.science/pith/XAOR2CG4FY3GRDG73UR5SB722N.json","graph_json":"https://pith.science/api/pith-number/XAOR2CG4FY3GRDG73UR5SB722N/graph.json","events_json":"https://pith.science/api/pith-number/XAOR2CG4FY3GRDG73UR5SB722N/events.json","paper":"https://pith.science/paper/XAOR2CG4"},"agent_actions":{"view_html":"https://pith.science/pith/XAOR2CG4FY3GRDG73UR5SB722N","download_json":"https://pith.science/pith/XAOR2CG4FY3GRDG73UR5SB722N.json","view_paper":"https://pith.science/paper/XAOR2CG4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.11328&json=true","fetch_graph":"https://pith.science/api/pith-number/XAOR2CG4FY3GRDG73UR5SB722N/graph.json","fetch_events":"https://pith.science/api/pith-number/XAOR2CG4FY3GRDG73UR5SB722N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XAOR2CG4FY3GRDG73UR5SB722N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XAOR2CG4FY3GRDG73UR5SB722N/action/storage_attestation","attest_author":"https://pith.science/pith/XAOR2CG4FY3GRDG73UR5SB722N/action/author_attestation","sign_citation":"https://pith.science/pith/XAOR2CG4FY3GRDG73UR5SB722N/action/citation_signature","submit_replication":"https://pith.science/pith/XAOR2CG4FY3GRDG73UR5SB722N/action/replication_record"}},"created_at":"2026-07-05T01:57:50.317084+00:00","updated_at":"2026-07-05T01:57:50.317084+00:00"}