{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:CPHYO6OTCMIWVVI26S6EPJRAAC","short_pith_number":"pith:CPHYO6OT","schema_version":"1.0","canonical_sha256":"13cf8779d313116ad51af4bc47a62000a5ac2acb2eec56ded8548589c6769fda","source":{"kind":"arxiv","id":"1810.08591","version":4},"attestation_state":"computed","paper":{"title":"A Modern Take on the Bias-Variance Tradeoff in Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aristide Baratin, Brady Neal, Ioannis Mitliagkas, Matthew Scicluna, Sarthak Mittal, Simon Lacoste-Julien, Vinayak Tantia","submitted_at":"2018-10-19T17:19:38Z","abstract_excerpt":"The bias-variance tradeoff tells us that as model complexity increases, bias falls and variances increases, leading to a U-shaped test error curve. However, recent empirical results with over-parameterized neural networks are marked by a striking absence of the classic U-shaped test error curve: test error keeps decreasing in wider networks. This suggests that there might not be a bias-variance tradeoff in neural networks with respect to network width, unlike was originally claimed by, e.g., Geman et al. (1992). Motivated by the shaky evidence used to support this claim in neural networks, we "},"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":"1810.08591","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-19T17:19:38Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fb5ddcb2ce0723bcdbb68265a2b826db0709d5ebc5325bd3df70dfc8be1d62a7","abstract_canon_sha256":"ddefa999aaf5f98e7dac69074da55f8d18416a52ac665405365b91383ea5a2b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:21.747681Z","signature_b64":"4dxleSyulo16H3MOQezvP0zSz6fSHqqt4U76BfT/JVpvsvJ2m3VE3JEZzub5khYITc5P5lLY+re0dQTaRix4BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13cf8779d313116ad51af4bc47a62000a5ac2acb2eec56ded8548589c6769fda","last_reissued_at":"2026-07-05T06:14:21.747192Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:21.747192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Modern Take on the Bias-Variance Tradeoff in Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aristide Baratin, Brady Neal, Ioannis Mitliagkas, Matthew Scicluna, Sarthak Mittal, Simon Lacoste-Julien, Vinayak Tantia","submitted_at":"2018-10-19T17:19:38Z","abstract_excerpt":"The bias-variance tradeoff tells us that as model complexity increases, bias falls and variances increases, leading to a U-shaped test error curve. However, recent empirical results with over-parameterized neural networks are marked by a striking absence of the classic U-shaped test error curve: test error keeps decreasing in wider networks. This suggests that there might not be a bias-variance tradeoff in neural networks with respect to network width, unlike was originally claimed by, e.g., Geman et al. (1992). Motivated by the shaky evidence used to support this claim in neural networks, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.08591","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/1810.08591/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":"1810.08591","created_at":"2026-07-05T06:14:21.747250+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.08591v4","created_at":"2026-07-05T06:14:21.747250+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.08591","created_at":"2026-07-05T06:14:21.747250+00:00"},{"alias_kind":"pith_short_12","alias_value":"CPHYO6OTCMIW","created_at":"2026-07-05T06:14:21.747250+00:00"},{"alias_kind":"pith_short_16","alias_value":"CPHYO6OTCMIWVVI2","created_at":"2026-07-05T06:14:21.747250+00:00"},{"alias_kind":"pith_short_8","alias_value":"CPHYO6OT","created_at":"2026-07-05T06:14:21.747250+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08377","citing_title":"Eigenvalue Calibration for Semantic Embeddings of Large Language Models","ref_index":245,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21494","citing_title":"Double descent for least-squares interpolation on contaminated data: A simulation study","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2512.04153","citing_title":"Data-Driven Predictions for Dark Photon and Millicharged Particle Production","ref_index":99,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21411","citing_title":"A Green-Integral-Constrained Neural Solver with Stochastic Physics-Informed Regularization","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CPHYO6OTCMIWVVI26S6EPJRAAC","json":"https://pith.science/pith/CPHYO6OTCMIWVVI26S6EPJRAAC.json","graph_json":"https://pith.science/api/pith-number/CPHYO6OTCMIWVVI26S6EPJRAAC/graph.json","events_json":"https://pith.science/api/pith-number/CPHYO6OTCMIWVVI26S6EPJRAAC/events.json","paper":"https://pith.science/paper/CPHYO6OT"},"agent_actions":{"view_html":"https://pith.science/pith/CPHYO6OTCMIWVVI26S6EPJRAAC","download_json":"https://pith.science/pith/CPHYO6OTCMIWVVI26S6EPJRAAC.json","view_paper":"https://pith.science/paper/CPHYO6OT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.08591&json=true","fetch_graph":"https://pith.science/api/pith-number/CPHYO6OTCMIWVVI26S6EPJRAAC/graph.json","fetch_events":"https://pith.science/api/pith-number/CPHYO6OTCMIWVVI26S6EPJRAAC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CPHYO6OTCMIWVVI26S6EPJRAAC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CPHYO6OTCMIWVVI26S6EPJRAAC/action/storage_attestation","attest_author":"https://pith.science/pith/CPHYO6OTCMIWVVI26S6EPJRAAC/action/author_attestation","sign_citation":"https://pith.science/pith/CPHYO6OTCMIWVVI26S6EPJRAAC/action/citation_signature","submit_replication":"https://pith.science/pith/CPHYO6OTCMIWVVI26S6EPJRAAC/action/replication_record"}},"created_at":"2026-07-05T06:14:21.747250+00:00","updated_at":"2026-07-05T06:14:21.747250+00:00"}