{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JI4A3QCIOP6NGHVYPMZ6HGGEOZ","short_pith_number":"pith:JI4A3QCI","schema_version":"1.0","canonical_sha256":"4a380dc04873fcd31eb87b33e398c4767a5ded6546f2b0532cd531b27d9d9b6e","source":{"kind":"arxiv","id":"2308.13431","version":1},"attestation_state":"computed","paper":{"title":"Six Lectures on Linearized 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":"Andrea Montanari, Theodor Misiakiewicz","submitted_at":"2023-08-25T15:23:06Z","abstract_excerpt":"In these six lectures, we examine what can be learnt about the behavior of multi-layer neural networks from the analysis of linear models. We first recall the correspondence between neural networks and linear models via the so-called lazy regime. We then review four models for linearized neural networks: linear regression with concentrated features, kernel ridge regression, random feature model and neural tangent model. Finally, we highlight the limitations of the linear theory and discuss how other approaches can overcome them."},"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":"2308.13431","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-08-25T15:23:06Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"34cf0e5c73aa0cf23c4810a0453d2d4506795253fbd5df22bb21d66fb92a05c6","abstract_canon_sha256":"b63e5732460d1222c8df282575fcdb4d8a83c5624979fbbdc9efbe93bd255314"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:44:43.850913Z","signature_b64":"3ges5efEgHdGAioMzV3CsKmSxW6zUJWpZ1m/pYRWXFM/AA0XyPhoms+kUns9rv9vLgj3v9DIJmNoJgZztXJGAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a380dc04873fcd31eb87b33e398c4767a5ded6546f2b0532cd531b27d9d9b6e","last_reissued_at":"2026-07-05T06:44:43.850438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:44:43.850438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Six Lectures on Linearized 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":"Andrea Montanari, Theodor Misiakiewicz","submitted_at":"2023-08-25T15:23:06Z","abstract_excerpt":"In these six lectures, we examine what can be learnt about the behavior of multi-layer neural networks from the analysis of linear models. We first recall the correspondence between neural networks and linear models via the so-called lazy regime. We then review four models for linearized neural networks: linear regression with concentrated features, kernel ridge regression, random feature model and neural tangent model. Finally, we highlight the limitations of the linear theory and discuss how other approaches can overcome them."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13431","kind":"arxiv","version":1},"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/2308.13431/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":"2308.13431","created_at":"2026-07-05T06:44:43.850493+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.13431v1","created_at":"2026-07-05T06:44:43.850493+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13431","created_at":"2026-07-05T06:44:43.850493+00:00"},{"alias_kind":"pith_short_12","alias_value":"JI4A3QCIOP6N","created_at":"2026-07-05T06:44:43.850493+00:00"},{"alias_kind":"pith_short_16","alias_value":"JI4A3QCIOP6NGHVY","created_at":"2026-07-05T06:44:43.850493+00:00"},{"alias_kind":"pith_short_8","alias_value":"JI4A3QCI","created_at":"2026-07-05T06:44:43.850493+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18598","citing_title":"Pointwise Generalization in Deep Neural Networks","ref_index":148,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07286","citing_title":"Sparse Random-Feature Neural Networks with Krylov-Based SVD for Singularly Perturbed ODE","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JI4A3QCIOP6NGHVYPMZ6HGGEOZ","json":"https://pith.science/pith/JI4A3QCIOP6NGHVYPMZ6HGGEOZ.json","graph_json":"https://pith.science/api/pith-number/JI4A3QCIOP6NGHVYPMZ6HGGEOZ/graph.json","events_json":"https://pith.science/api/pith-number/JI4A3QCIOP6NGHVYPMZ6HGGEOZ/events.json","paper":"https://pith.science/paper/JI4A3QCI"},"agent_actions":{"view_html":"https://pith.science/pith/JI4A3QCIOP6NGHVYPMZ6HGGEOZ","download_json":"https://pith.science/pith/JI4A3QCIOP6NGHVYPMZ6HGGEOZ.json","view_paper":"https://pith.science/paper/JI4A3QCI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.13431&json=true","fetch_graph":"https://pith.science/api/pith-number/JI4A3QCIOP6NGHVYPMZ6HGGEOZ/graph.json","fetch_events":"https://pith.science/api/pith-number/JI4A3QCIOP6NGHVYPMZ6HGGEOZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JI4A3QCIOP6NGHVYPMZ6HGGEOZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JI4A3QCIOP6NGHVYPMZ6HGGEOZ/action/storage_attestation","attest_author":"https://pith.science/pith/JI4A3QCIOP6NGHVYPMZ6HGGEOZ/action/author_attestation","sign_citation":"https://pith.science/pith/JI4A3QCIOP6NGHVYPMZ6HGGEOZ/action/citation_signature","submit_replication":"https://pith.science/pith/JI4A3QCIOP6NGHVYPMZ6HGGEOZ/action/replication_record"}},"created_at":"2026-07-05T06:44:43.850493+00:00","updated_at":"2026-07-05T06:44:43.850493+00:00"}