{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6Z5FQK3BQYFDXBONM3LECAQNVV","short_pith_number":"pith:6Z5FQK3B","schema_version":"1.0","canonical_sha256":"f67a582b61860a3b85cd66d641020dad65526a93c73b0e26e3870e98c9baca6a","source":{"kind":"arxiv","id":"2410.13991","version":1},"attestation_state":"computed","paper":{"title":"Generalization for Least Squares Regression With Simple Spiked Covariances","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Jiping Li, Rishi Sonthalia","submitted_at":"2024-10-17T19:46:51Z","abstract_excerpt":"Random matrix theory has proven to be a valuable tool in analyzing the generalization of linear models. However, the generalization properties of even two-layer neural networks trained by gradient descent remain poorly understood. To understand the generalization performance of such networks, it is crucial to characterize the spectrum of the feature matrix at the hidden layer. Recent work has made progress in this direction by describing the spectrum after a single gradient step, revealing a spiked covariance structure. Yet, the generalization error for linear models with spiked covariances ha"},"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":"2410.13991","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"math.ST","submitted_at":"2024-10-17T19:46:51Z","cross_cats_sorted":["cs.LG","stat.ML","stat.TH"],"title_canon_sha256":"5f251257b79ff24c1d6e1ebcf069b312066835f917902c78cd198ad4f6a134f7","abstract_canon_sha256":"ec0a0d723ba78d8b9b5e5186aa7ed510b2c5f7e8f669f9be2faf283539255f39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:25.536175Z","signature_b64":"Uv1+HGU5ES8pH153XUNpyOaDe9/qTK4hfsOyeD5DTRClyTOLvjlG31ITM92IlqOezqEqVgyj4WcNXVOtHgEaBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f67a582b61860a3b85cd66d641020dad65526a93c73b0e26e3870e98c9baca6a","last_reissued_at":"2026-07-05T09:22:25.535669Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:25.535669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalization for Least Squares Regression With Simple Spiked Covariances","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Jiping Li, Rishi Sonthalia","submitted_at":"2024-10-17T19:46:51Z","abstract_excerpt":"Random matrix theory has proven to be a valuable tool in analyzing the generalization of linear models. However, the generalization properties of even two-layer neural networks trained by gradient descent remain poorly understood. To understand the generalization performance of such networks, it is crucial to characterize the spectrum of the feature matrix at the hidden layer. Recent work has made progress in this direction by describing the spectrum after a single gradient step, revealing a spiked covariance structure. Yet, the generalization error for linear models with spiked covariances ha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13991","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/2410.13991/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":"2410.13991","created_at":"2026-07-05T09:22:25.535744+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13991v1","created_at":"2026-07-05T09:22:25.535744+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13991","created_at":"2026-07-05T09:22:25.535744+00:00"},{"alias_kind":"pith_short_12","alias_value":"6Z5FQK3BQYFD","created_at":"2026-07-05T09:22:25.535744+00:00"},{"alias_kind":"pith_short_16","alias_value":"6Z5FQK3BQYFDXBON","created_at":"2026-07-05T09:22:25.535744+00:00"},{"alias_kind":"pith_short_8","alias_value":"6Z5FQK3B","created_at":"2026-07-05T09:22:25.535744+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.18346","citing_title":"On the Mechanisms of Weak-to-Strong Generalization: A Theoretical Perspective","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6Z5FQK3BQYFDXBONM3LECAQNVV","json":"https://pith.science/pith/6Z5FQK3BQYFDXBONM3LECAQNVV.json","graph_json":"https://pith.science/api/pith-number/6Z5FQK3BQYFDXBONM3LECAQNVV/graph.json","events_json":"https://pith.science/api/pith-number/6Z5FQK3BQYFDXBONM3LECAQNVV/events.json","paper":"https://pith.science/paper/6Z5FQK3B"},"agent_actions":{"view_html":"https://pith.science/pith/6Z5FQK3BQYFDXBONM3LECAQNVV","download_json":"https://pith.science/pith/6Z5FQK3BQYFDXBONM3LECAQNVV.json","view_paper":"https://pith.science/paper/6Z5FQK3B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13991&json=true","fetch_graph":"https://pith.science/api/pith-number/6Z5FQK3BQYFDXBONM3LECAQNVV/graph.json","fetch_events":"https://pith.science/api/pith-number/6Z5FQK3BQYFDXBONM3LECAQNVV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6Z5FQK3BQYFDXBONM3LECAQNVV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6Z5FQK3BQYFDXBONM3LECAQNVV/action/storage_attestation","attest_author":"https://pith.science/pith/6Z5FQK3BQYFDXBONM3LECAQNVV/action/author_attestation","sign_citation":"https://pith.science/pith/6Z5FQK3BQYFDXBONM3LECAQNVV/action/citation_signature","submit_replication":"https://pith.science/pith/6Z5FQK3BQYFDXBONM3LECAQNVV/action/replication_record"}},"created_at":"2026-07-05T09:22:25.535744+00:00","updated_at":"2026-07-05T09:22:25.535744+00:00"}