{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CF7VNRSNQ6ERWSWB2DIUNBPZVI","short_pith_number":"pith:CF7VNRSN","schema_version":"1.0","canonical_sha256":"117f56c64d87891b4ac1d0d14685f9aa0657d80c4132ec24297d8b6055d8b77d","source":{"kind":"arxiv","id":"2402.10164","version":2},"attestation_state":"computed","paper":{"title":"Random features and polynomial rules","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cond-mat.dis-nn","authors_text":"Fabi\\'an Aguirre-L\\'opez, Mauro Pastore, Silvio Franz","submitted_at":"2024-02-15T18:09:41Z","abstract_excerpt":"Random features models play a distinguished role in the theory of deep learning, describing the behavior of neural networks close to their infinite-width limit. In this work, we present a thorough analysis of the generalization performance of random features models for generic supervised learning problems with Gaussian data. Our approach, built with tools from the statistical mechanics of disordered systems, maps the random features model to an equivalent polynomial model, and allows us to plot average generalization curves as functions of the two main control parameters of the problem: the nu"},"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":"2402.10164","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2024-02-15T18:09:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"590a36b4df8b050afd557ed59d200977856cfd940fa97c10828ea583d23801ce","abstract_canon_sha256":"9489afda52921d23b14868ca3f54a1a26786be86167c6a557a22b32773e1aac1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:39.322136Z","signature_b64":"6CaSmQ4A41B8FvtKIGS/AvsGxr1TjnvtRmlUuNWcEdqDLVAphW8mqyQr/pnjuyAyByY7YWwq0/Be9VzQv3EFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"117f56c64d87891b4ac1d0d14685f9aa0657d80c4132ec24297d8b6055d8b77d","last_reissued_at":"2026-07-05T10:07:39.321657Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:39.321657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Random features and polynomial rules","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cond-mat.dis-nn","authors_text":"Fabi\\'an Aguirre-L\\'opez, Mauro Pastore, Silvio Franz","submitted_at":"2024-02-15T18:09:41Z","abstract_excerpt":"Random features models play a distinguished role in the theory of deep learning, describing the behavior of neural networks close to their infinite-width limit. In this work, we present a thorough analysis of the generalization performance of random features models for generic supervised learning problems with Gaussian data. Our approach, built with tools from the statistical mechanics of disordered systems, maps the random features model to an equivalent polynomial model, and allows us to plot average generalization curves as functions of the two main control parameters of the problem: the nu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10164","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/2402.10164/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":"2402.10164","created_at":"2026-07-05T10:07:39.321708+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.10164v2","created_at":"2026-07-05T10:07:39.321708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10164","created_at":"2026-07-05T10:07:39.321708+00:00"},{"alias_kind":"pith_short_12","alias_value":"CF7VNRSNQ6ER","created_at":"2026-07-05T10:07:39.321708+00:00"},{"alias_kind":"pith_short_16","alias_value":"CF7VNRSNQ6ERWSWB","created_at":"2026-07-05T10:07:39.321708+00:00"},{"alias_kind":"pith_short_8","alias_value":"CF7VNRSN","created_at":"2026-07-05T10:07:39.321708+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.15911","citing_title":"Kernel shape renormalization explains output-output correlations in finite Bayesian one-hidden-layer networks","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CF7VNRSNQ6ERWSWB2DIUNBPZVI","json":"https://pith.science/pith/CF7VNRSNQ6ERWSWB2DIUNBPZVI.json","graph_json":"https://pith.science/api/pith-number/CF7VNRSNQ6ERWSWB2DIUNBPZVI/graph.json","events_json":"https://pith.science/api/pith-number/CF7VNRSNQ6ERWSWB2DIUNBPZVI/events.json","paper":"https://pith.science/paper/CF7VNRSN"},"agent_actions":{"view_html":"https://pith.science/pith/CF7VNRSNQ6ERWSWB2DIUNBPZVI","download_json":"https://pith.science/pith/CF7VNRSNQ6ERWSWB2DIUNBPZVI.json","view_paper":"https://pith.science/paper/CF7VNRSN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.10164&json=true","fetch_graph":"https://pith.science/api/pith-number/CF7VNRSNQ6ERWSWB2DIUNBPZVI/graph.json","fetch_events":"https://pith.science/api/pith-number/CF7VNRSNQ6ERWSWB2DIUNBPZVI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CF7VNRSNQ6ERWSWB2DIUNBPZVI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CF7VNRSNQ6ERWSWB2DIUNBPZVI/action/storage_attestation","attest_author":"https://pith.science/pith/CF7VNRSNQ6ERWSWB2DIUNBPZVI/action/author_attestation","sign_citation":"https://pith.science/pith/CF7VNRSNQ6ERWSWB2DIUNBPZVI/action/citation_signature","submit_replication":"https://pith.science/pith/CF7VNRSNQ6ERWSWB2DIUNBPZVI/action/replication_record"}},"created_at":"2026-07-05T10:07:39.321708+00:00","updated_at":"2026-07-05T10:07:39.321708+00:00"}