{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TBETBECXYEU662LUW54CYY3T5K","short_pith_number":"pith:TBETBECX","schema_version":"1.0","canonical_sha256":"9849309057c129ef6974b7782c6373ea8f522ffcb24ad3f3f57a254c81c51465","source":{"kind":"arxiv","id":"2310.18280","version":1},"attestation_state":"computed","paper":{"title":"Universality for the global spectrum of random inner-product kernel matrices in the polynomial regime","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.PR","authors_text":"Benjamin McKenna, Horng-Tzer Yau, Sofiia Dubova, Yue M. Lu","submitted_at":"2023-10-27T17:15:55Z","abstract_excerpt":"We consider certain large random matrices, called random inner-product kernel matrices, which are essentially given by a nonlinear function $f$ applied entrywise to a sample-covariance matrix, $f(X^TX)$, where $X \\in \\mathbb{R}^{d \\times N}$ is random and normalized in such a way that $f$ typically has order-one arguments. We work in the polynomial regime, where $N \\asymp d^\\ell$ for some $\\ell > 0$, not just the linear regime where $\\ell = 1$. Earlier work by various authors showed that, when the columns of $X$ are either uniform on the sphere or standard Gaussian vectors, and when $\\ell$ is "},"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":"2310.18280","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.PR","submitted_at":"2023-10-27T17:15:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"686e43c160d1e614463bdd04933cf8a32077b6a29bf8c671fd4368d6bbcd6dab","abstract_canon_sha256":"df4567bdddbd78a36c67ed055f413bd08e11e8eb1d21d644ffb8918e31ecc4db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:59.817873Z","signature_b64":"8dEAmYxzUxoE6NCA5SpR/QbzYQsj7I0yfvCvMCW3wCWaDa99p4oXxZ3ciUm+YpTzx9DhOS/ESv9qOTQoiI37Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9849309057c129ef6974b7782c6373ea8f522ffcb24ad3f3f57a254c81c51465","last_reissued_at":"2026-07-05T07:05:59.817369Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:59.817369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Universality for the global spectrum of random inner-product kernel matrices in the polynomial regime","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.PR","authors_text":"Benjamin McKenna, Horng-Tzer Yau, Sofiia Dubova, Yue M. Lu","submitted_at":"2023-10-27T17:15:55Z","abstract_excerpt":"We consider certain large random matrices, called random inner-product kernel matrices, which are essentially given by a nonlinear function $f$ applied entrywise to a sample-covariance matrix, $f(X^TX)$, where $X \\in \\mathbb{R}^{d \\times N}$ is random and normalized in such a way that $f$ typically has order-one arguments. We work in the polynomial regime, where $N \\asymp d^\\ell$ for some $\\ell > 0$, not just the linear regime where $\\ell = 1$. Earlier work by various authors showed that, when the columns of $X$ are either uniform on the sphere or standard Gaussian vectors, and when $\\ell$ is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18280","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/2310.18280/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":"2310.18280","created_at":"2026-07-05T07:05:59.817429+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.18280v1","created_at":"2026-07-05T07:05:59.817429+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18280","created_at":"2026-07-05T07:05:59.817429+00:00"},{"alias_kind":"pith_short_12","alias_value":"TBETBECXYEU6","created_at":"2026-07-05T07:05:59.817429+00:00"},{"alias_kind":"pith_short_16","alias_value":"TBETBECXYEU662LU","created_at":"2026-07-05T07:05:59.817429+00:00"},{"alias_kind":"pith_short_8","alias_value":"TBETBECX","created_at":"2026-07-05T07:05:59.817429+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2405.00592","citing_title":"Scaling and renormalization in high-dimensional regression","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14567","citing_title":"Scaling Laws from Sequential Feature Recovery: A Solvable Hierarchical Model","ref_index":91,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TBETBECXYEU662LUW54CYY3T5K","json":"https://pith.science/pith/TBETBECXYEU662LUW54CYY3T5K.json","graph_json":"https://pith.science/api/pith-number/TBETBECXYEU662LUW54CYY3T5K/graph.json","events_json":"https://pith.science/api/pith-number/TBETBECXYEU662LUW54CYY3T5K/events.json","paper":"https://pith.science/paper/TBETBECX"},"agent_actions":{"view_html":"https://pith.science/pith/TBETBECXYEU662LUW54CYY3T5K","download_json":"https://pith.science/pith/TBETBECXYEU662LUW54CYY3T5K.json","view_paper":"https://pith.science/paper/TBETBECX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.18280&json=true","fetch_graph":"https://pith.science/api/pith-number/TBETBECXYEU662LUW54CYY3T5K/graph.json","fetch_events":"https://pith.science/api/pith-number/TBETBECXYEU662LUW54CYY3T5K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TBETBECXYEU662LUW54CYY3T5K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TBETBECXYEU662LUW54CYY3T5K/action/storage_attestation","attest_author":"https://pith.science/pith/TBETBECXYEU662LUW54CYY3T5K/action/author_attestation","sign_citation":"https://pith.science/pith/TBETBECXYEU662LUW54CYY3T5K/action/citation_signature","submit_replication":"https://pith.science/pith/TBETBECXYEU662LUW54CYY3T5K/action/replication_record"}},"created_at":"2026-07-05T07:05:59.817429+00:00","updated_at":"2026-07-05T07:05:59.817429+00:00"}