{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:Z7E5VFB6227OIEZ2BOUI2OBISE","short_pith_number":"pith:Z7E5VFB6","schema_version":"1.0","canonical_sha256":"cfc9da943ed6bee4133a0ba88d382891071cf4ad470cbb34924853c7389f26dd","source":{"kind":"arxiv","id":"1812.11118","version":2},"attestation_state":"computed","paper":{"title":"Reconciling modern machine learning practice and the bias-variance trade-off","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Daniel Hsu, Mikhail Belkin, Siyuan Ma, Soumik Mandal","submitted_at":"2018-12-28T17:15:38Z","abstract_excerpt":"Breakthroughs in machine learning are rapidly changing science and society, yet our fundamental understanding of this technology has lagged far behind. Indeed, one of the central tenets of the field, the bias-variance trade-off, appears to be at odds with the observed behavior of methods used in the modern machine learning practice. The bias-variance trade-off implies that a model should balance under-fitting and over-fitting: rich enough to express underlying structure in data, simple enough to avoid fitting spurious patterns. However, in the modern practice, very rich models such as neural n"},"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":"1812.11118","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-12-28T17:15:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c3ec47ad73bb2d997637938407e39e10b3d068485422744d04da1fedfa1caed8","abstract_canon_sha256":"63ff84eb6591772a93a7794fa2260275c4a873697934f83a8d7052f8df032056"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:29:22.018546Z","signature_b64":"bb7Is6YGPdqh9jZstQ2vnefWIsXpuVLHmnLCyvCemrbAntP2hbDoZFBboLPx49T3gNJiiBkq+MP590To47SjDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfc9da943ed6bee4133a0ba88d382891071cf4ad470cbb34924853c7389f26dd","last_reissued_at":"2026-07-05T04:29:22.018128Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:29:22.018128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reconciling modern machine learning practice and the bias-variance trade-off","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Daniel Hsu, Mikhail Belkin, Siyuan Ma, Soumik Mandal","submitted_at":"2018-12-28T17:15:38Z","abstract_excerpt":"Breakthroughs in machine learning are rapidly changing science and society, yet our fundamental understanding of this technology has lagged far behind. Indeed, one of the central tenets of the field, the bias-variance trade-off, appears to be at odds with the observed behavior of methods used in the modern machine learning practice. The bias-variance trade-off implies that a model should balance under-fitting and over-fitting: rich enough to express underlying structure in data, simple enough to avoid fitting spurious patterns. However, in the modern practice, very rich models such as neural n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.11118","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/1812.11118/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":"1812.11118","created_at":"2026-07-05T04:29:22.018183+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.11118v2","created_at":"2026-07-05T04:29:22.018183+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.11118","created_at":"2026-07-05T04:29:22.018183+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z7E5VFB6227O","created_at":"2026-07-05T04:29:22.018183+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z7E5VFB6227OIEZ2","created_at":"2026-07-05T04:29:22.018183+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z7E5VFB6","created_at":"2026-07-05T04:29:22.018183+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23591","citing_title":"Asymmetric Scaling Laws from Sparse Features","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2212.08989","citing_title":"Deep learning applied to computational mechanics: A comprehensive review, state of the art, and the classics","ref_index":138,"is_internal_anchor":false},{"citing_arxiv_id":"2102.01293","citing_title":"Scaling Laws for Transfer","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2205.10487","citing_title":"Scaling Laws and Interpretability of Learning from Repeated Data","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06394","citing_title":"Lecture Notes on Statistical Physics and Neural Networks","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2201.02177","citing_title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2112.00861","citing_title":"A General Language Assistant as a Laboratory for Alignment","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2207.05221","citing_title":"Language Models (Mostly) Know What They Know","ref_index":161,"is_internal_anchor":false},{"citing_arxiv_id":"2001.08361","citing_title":"Scaling Laws for Neural Language Models","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z7E5VFB6227OIEZ2BOUI2OBISE","json":"https://pith.science/pith/Z7E5VFB6227OIEZ2BOUI2OBISE.json","graph_json":"https://pith.science/api/pith-number/Z7E5VFB6227OIEZ2BOUI2OBISE/graph.json","events_json":"https://pith.science/api/pith-number/Z7E5VFB6227OIEZ2BOUI2OBISE/events.json","paper":"https://pith.science/paper/Z7E5VFB6"},"agent_actions":{"view_html":"https://pith.science/pith/Z7E5VFB6227OIEZ2BOUI2OBISE","download_json":"https://pith.science/pith/Z7E5VFB6227OIEZ2BOUI2OBISE.json","view_paper":"https://pith.science/paper/Z7E5VFB6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.11118&json=true","fetch_graph":"https://pith.science/api/pith-number/Z7E5VFB6227OIEZ2BOUI2OBISE/graph.json","fetch_events":"https://pith.science/api/pith-number/Z7E5VFB6227OIEZ2BOUI2OBISE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z7E5VFB6227OIEZ2BOUI2OBISE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z7E5VFB6227OIEZ2BOUI2OBISE/action/storage_attestation","attest_author":"https://pith.science/pith/Z7E5VFB6227OIEZ2BOUI2OBISE/action/author_attestation","sign_citation":"https://pith.science/pith/Z7E5VFB6227OIEZ2BOUI2OBISE/action/citation_signature","submit_replication":"https://pith.science/pith/Z7E5VFB6227OIEZ2BOUI2OBISE/action/replication_record"}},"created_at":"2026-07-05T04:29:22.018183+00:00","updated_at":"2026-07-05T04:29:22.018183+00:00"}