{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EQ5GSC7X2PYIYUMXALC7XS2JRI","short_pith_number":"pith:EQ5GSC7X","schema_version":"1.0","canonical_sha256":"243a690bf7d3f08c519702c5fbcb498a09cdf7f28cf3f4ee1d72be6312440e68","source":{"kind":"arxiv","id":"2509.24882","version":2},"attestation_state":"computed","paper":{"title":"Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bruno Loureiro, Emanuele Troiani, Florent Krzakala, Julius Girardin, Lenka Zdeborov\\'a, Leonardo Defilippis, Vittorio Erba, Yizhou Xu","submitted_at":"2025-09-29T14:58:13Z","abstract_excerpt":"Neural scaling laws underlie many of the recent advances in deep learning, yet their theoretical understanding remains largely confined to linear models. In this work, we present a systematic analysis of scaling laws for quadratic and diagonal neural networks in the feature learning regime. Leveraging connections with matrix compressed sensing and LASSO, we derive a detailed phase diagram for the scaling exponents of the excess risk as a function of sample complexity and weight decay. This analysis uncovers crossovers between distinct scaling regimes and plateau behaviors, mirroring phenomena "},"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":"2509.24882","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-29T14:58:13Z","cross_cats_sorted":["cond-mat.dis-nn","cs.AI","stat.ML"],"title_canon_sha256":"7c702dfb3b114423677ab889394327ecc73c6c4cf062de7640d36b9d26ba6635","abstract_canon_sha256":"609e1ee9efe3cdaed0220f12e153e0fc0da0374630233f1a1f47ddc254c9aa85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:16.577607Z","signature_b64":"QA1NK7LXSE6SURcQ8xjlqk3M8T44rLwvzqkAKGJckM+UnQx+FD73QxE4bvw36sRUcY120wMbNeFFZ3CqpJnJDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"243a690bf7d3f08c519702c5fbcb498a09cdf7f28cf3f4ee1d72be6312440e68","last_reissued_at":"2026-06-05T01:15:16.576800Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:16.576800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bruno Loureiro, Emanuele Troiani, Florent Krzakala, Julius Girardin, Lenka Zdeborov\\'a, Leonardo Defilippis, Vittorio Erba, Yizhou Xu","submitted_at":"2025-09-29T14:58:13Z","abstract_excerpt":"Neural scaling laws underlie many of the recent advances in deep learning, yet their theoretical understanding remains largely confined to linear models. In this work, we present a systematic analysis of scaling laws for quadratic and diagonal neural networks in the feature learning regime. Leveraging connections with matrix compressed sensing and LASSO, we derive a detailed phase diagram for the scaling exponents of the excess risk as a function of sample complexity and weight decay. This analysis uncovers crossovers between distinct scaling regimes and plateau behaviors, mirroring phenomena "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.24882","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/2509.24882/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":"2509.24882","created_at":"2026-06-05T01:15:16.576905+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.24882v2","created_at":"2026-06-05T01:15:16.576905+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.24882","created_at":"2026-06-05T01:15:16.576905+00:00"},{"alias_kind":"pith_short_12","alias_value":"EQ5GSC7X2PYI","created_at":"2026-06-05T01:15:16.576905+00:00"},{"alias_kind":"pith_short_16","alias_value":"EQ5GSC7X2PYIYUMX","created_at":"2026-06-05T01:15:16.576905+00:00"},{"alias_kind":"pith_short_8","alias_value":"EQ5GSC7X","created_at":"2026-06-05T01:15:16.576905+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"2603.10067","citing_title":"HTMuon: Improving Muon via Heavy-Tailed Spectral Correction","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23591","citing_title":"Asymmetric Scaling Laws from Sparse Features","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07870","citing_title":"Spectral Dynamics in Deep Networks: Feature Learning, Outlier Escape, and Learning Rate Transfer","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16913","citing_title":"A Fourier perspective on the learning dynamics of neural networks: from sample complexities to mechanistic insights","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10395","citing_title":"Sharp feature-learning transitions and Bayes-optimal neural scaling laws in extensive-width networks","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21691","citing_title":"There Will Be a Scientific Theory of Deep Learning","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EQ5GSC7X2PYIYUMXALC7XS2JRI","json":"https://pith.science/pith/EQ5GSC7X2PYIYUMXALC7XS2JRI.json","graph_json":"https://pith.science/api/pith-number/EQ5GSC7X2PYIYUMXALC7XS2JRI/graph.json","events_json":"https://pith.science/api/pith-number/EQ5GSC7X2PYIYUMXALC7XS2JRI/events.json","paper":"https://pith.science/paper/EQ5GSC7X"},"agent_actions":{"view_html":"https://pith.science/pith/EQ5GSC7X2PYIYUMXALC7XS2JRI","download_json":"https://pith.science/pith/EQ5GSC7X2PYIYUMXALC7XS2JRI.json","view_paper":"https://pith.science/paper/EQ5GSC7X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.24882&json=true","fetch_graph":"https://pith.science/api/pith-number/EQ5GSC7X2PYIYUMXALC7XS2JRI/graph.json","fetch_events":"https://pith.science/api/pith-number/EQ5GSC7X2PYIYUMXALC7XS2JRI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EQ5GSC7X2PYIYUMXALC7XS2JRI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EQ5GSC7X2PYIYUMXALC7XS2JRI/action/storage_attestation","attest_author":"https://pith.science/pith/EQ5GSC7X2PYIYUMXALC7XS2JRI/action/author_attestation","sign_citation":"https://pith.science/pith/EQ5GSC7X2PYIYUMXALC7XS2JRI/action/citation_signature","submit_replication":"https://pith.science/pith/EQ5GSC7X2PYIYUMXALC7XS2JRI/action/replication_record"}},"created_at":"2026-06-05T01:15:16.576905+00:00","updated_at":"2026-06-05T01:15:16.576905+00:00"}