{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6MR3AHCDZQWLLEOGLDQITT6G36","short_pith_number":"pith:6MR3AHCD","schema_version":"1.0","canonical_sha256":"f323b01c43cc2cb591c658e089cfc6dfaf409237bce6f52f88dc38b34856a88e","source":{"kind":"arxiv","id":"1912.06987","version":2},"attestation_state":"computed","paper":{"title":"The Generalization Error of the Minimum-norm Solutions for Over-parameterized Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Chao Ma, Lei Wu, Weinan E","submitted_at":"2019-12-15T06:05:14Z","abstract_excerpt":"We study the generalization properties of minimum-norm solutions for three over-parametrized machine learning models including the random feature model, the two-layer neural network model and the residual network model. We proved that for all three models, the generalization error for the minimum-norm solution is comparable to the Monte Carlo rate, up to some logarithmic terms, as long as the models are sufficiently over-parametrized."},"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":"1912.06987","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-12-15T06:05:14Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"3f22e00b2ca7e719f0bbcdce90c990d4f8fb764c09452b5e3c9962f3a333a809","abstract_canon_sha256":"a33fe3256194cbeb6e14bb35408a3a18cea110f5109baafbe2b79ce37a5b1c25"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:10:23.710475Z","signature_b64":"1F324TtYQsfQMrQYlBL21BFN+ESAzRcM0YrHTf/zZLx9KV+9fs17672U/5VMYBmlJpPgM/PfpvG1a7PYslhHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f323b01c43cc2cb591c658e089cfc6dfaf409237bce6f52f88dc38b34856a88e","last_reissued_at":"2026-07-05T02:10:23.710001Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:10:23.710001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Generalization Error of the Minimum-norm Solutions for Over-parameterized Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Chao Ma, Lei Wu, Weinan E","submitted_at":"2019-12-15T06:05:14Z","abstract_excerpt":"We study the generalization properties of minimum-norm solutions for three over-parametrized machine learning models including the random feature model, the two-layer neural network model and the residual network model. We proved that for all three models, the generalization error for the minimum-norm solution is comparable to the Monte Carlo rate, up to some logarithmic terms, as long as the models are sufficiently over-parametrized."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.06987","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/1912.06987/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":"1912.06987","created_at":"2026-07-05T02:10:23.710064+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.06987v2","created_at":"2026-07-05T02:10:23.710064+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.06987","created_at":"2026-07-05T02:10:23.710064+00:00"},{"alias_kind":"pith_short_12","alias_value":"6MR3AHCDZQWL","created_at":"2026-07-05T02:10:23.710064+00:00"},{"alias_kind":"pith_short_16","alias_value":"6MR3AHCDZQWLLEOG","created_at":"2026-07-05T02:10:23.710064+00:00"},{"alias_kind":"pith_short_8","alias_value":"6MR3AHCD","created_at":"2026-07-05T02:10:23.710064+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.14757","citing_title":"Solving Inverse Parametrized Problems via Finite Elements and Extreme Learning Networks","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6MR3AHCDZQWLLEOGLDQITT6G36","json":"https://pith.science/pith/6MR3AHCDZQWLLEOGLDQITT6G36.json","graph_json":"https://pith.science/api/pith-number/6MR3AHCDZQWLLEOGLDQITT6G36/graph.json","events_json":"https://pith.science/api/pith-number/6MR3AHCDZQWLLEOGLDQITT6G36/events.json","paper":"https://pith.science/paper/6MR3AHCD"},"agent_actions":{"view_html":"https://pith.science/pith/6MR3AHCDZQWLLEOGLDQITT6G36","download_json":"https://pith.science/pith/6MR3AHCDZQWLLEOGLDQITT6G36.json","view_paper":"https://pith.science/paper/6MR3AHCD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.06987&json=true","fetch_graph":"https://pith.science/api/pith-number/6MR3AHCDZQWLLEOGLDQITT6G36/graph.json","fetch_events":"https://pith.science/api/pith-number/6MR3AHCDZQWLLEOGLDQITT6G36/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6MR3AHCDZQWLLEOGLDQITT6G36/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6MR3AHCDZQWLLEOGLDQITT6G36/action/storage_attestation","attest_author":"https://pith.science/pith/6MR3AHCDZQWLLEOGLDQITT6G36/action/author_attestation","sign_citation":"https://pith.science/pith/6MR3AHCDZQWLLEOGLDQITT6G36/action/citation_signature","submit_replication":"https://pith.science/pith/6MR3AHCDZQWLLEOGLDQITT6G36/action/replication_record"}},"created_at":"2026-07-05T02:10:23.710064+00:00","updated_at":"2026-07-05T02:10:23.710064+00:00"}