{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LO6T63TTSRP6EB3NN5PGLBFU7U","short_pith_number":"pith:LO6T63TT","schema_version":"1.0","canonical_sha256":"5bbd3f6e73945fe2076d6f5e6584b4fd276badb4eeed885417aedaa0020000f5","source":{"kind":"arxiv","id":"2310.14055","version":1},"attestation_state":"computed","paper":{"title":"Spectral Phase Transitions in Non-Linear Wigner Spiked Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.PR","authors_text":"Alice Guionnet, Florent Krzakala, Justin Ko, Lenka Zdeborov\\'a, Pierre Mergny","submitted_at":"2023-10-21T16:23:59Z","abstract_excerpt":"We study the asymptotic behavior of the spectrum of a random matrix where a non-linearity is applied entry-wise to a Wigner matrix perturbed by a rank-one spike with independent and identically distributed entries. In this setting, we show that when the signal-to-noise ratio scale as $N^{\\frac{1}{2} (1-1/k_\\star)}$, where $k_\\star$ is the first non-zero generalized information coefficient of the function, the non-linear spike model effectively behaves as an equivalent spiked Wigner matrix, where the former spike before the non-linearity is now raised to a power $k_\\star$. This allows us to stu"},"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":"2310.14055","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.PR","submitted_at":"2023-10-21T16:23:59Z","cross_cats_sorted":[],"title_canon_sha256":"9c5510fd926d2e0bc228d7094b54d1ef1a77f139c7e62ecf76de3c51b8aad521","abstract_canon_sha256":"b4b2ef81a03cbd488db2dd45e83d07e3501e16f39e9771842a51a0a08e8c2925"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:39.098836Z","signature_b64":"syKqM6RtE0CfR2T5OWlHA3iTpjQDH3D09hgdIdMbvE86OXOGH/V85Th4QFaokPdcP7MIRgfpkr+pCxJc9886AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bbd3f6e73945fe2076d6f5e6584b4fd276badb4eeed885417aedaa0020000f5","last_reissued_at":"2026-07-05T07:03:39.098203Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:39.098203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spectral Phase Transitions in Non-Linear Wigner Spiked Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.PR","authors_text":"Alice Guionnet, Florent Krzakala, Justin Ko, Lenka Zdeborov\\'a, Pierre Mergny","submitted_at":"2023-10-21T16:23:59Z","abstract_excerpt":"We study the asymptotic behavior of the spectrum of a random matrix where a non-linearity is applied entry-wise to a Wigner matrix perturbed by a rank-one spike with independent and identically distributed entries. In this setting, we show that when the signal-to-noise ratio scale as $N^{\\frac{1}{2} (1-1/k_\\star)}$, where $k_\\star$ is the first non-zero generalized information coefficient of the function, the non-linear spike model effectively behaves as an equivalent spiked Wigner matrix, where the former spike before the non-linearity is now raised to a power $k_\\star$. This allows us to stu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14055","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/2310.14055/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":"2310.14055","created_at":"2026-07-05T07:03:39.098302+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.14055v1","created_at":"2026-07-05T07:03:39.098302+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14055","created_at":"2026-07-05T07:03:39.098302+00:00"},{"alias_kind":"pith_short_12","alias_value":"LO6T63TTSRP6","created_at":"2026-07-05T07:03:39.098302+00:00"},{"alias_kind":"pith_short_16","alias_value":"LO6T63TTSRP6EB3N","created_at":"2026-07-05T07:03:39.098302+00:00"},{"alias_kind":"pith_short_8","alias_value":"LO6T63TT","created_at":"2026-07-05T07:03:39.098302+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17767","citing_title":"Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent","ref_index":295,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17767","citing_title":"Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent","ref_index":295,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LO6T63TTSRP6EB3NN5PGLBFU7U","json":"https://pith.science/pith/LO6T63TTSRP6EB3NN5PGLBFU7U.json","graph_json":"https://pith.science/api/pith-number/LO6T63TTSRP6EB3NN5PGLBFU7U/graph.json","events_json":"https://pith.science/api/pith-number/LO6T63TTSRP6EB3NN5PGLBFU7U/events.json","paper":"https://pith.science/paper/LO6T63TT"},"agent_actions":{"view_html":"https://pith.science/pith/LO6T63TTSRP6EB3NN5PGLBFU7U","download_json":"https://pith.science/pith/LO6T63TTSRP6EB3NN5PGLBFU7U.json","view_paper":"https://pith.science/paper/LO6T63TT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.14055&json=true","fetch_graph":"https://pith.science/api/pith-number/LO6T63TTSRP6EB3NN5PGLBFU7U/graph.json","fetch_events":"https://pith.science/api/pith-number/LO6T63TTSRP6EB3NN5PGLBFU7U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LO6T63TTSRP6EB3NN5PGLBFU7U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LO6T63TTSRP6EB3NN5PGLBFU7U/action/storage_attestation","attest_author":"https://pith.science/pith/LO6T63TTSRP6EB3NN5PGLBFU7U/action/author_attestation","sign_citation":"https://pith.science/pith/LO6T63TTSRP6EB3NN5PGLBFU7U/action/citation_signature","submit_replication":"https://pith.science/pith/LO6T63TTSRP6EB3NN5PGLBFU7U/action/replication_record"}},"created_at":"2026-07-05T07:03:39.098302+00:00","updated_at":"2026-07-05T07:03:39.098302+00:00"}