{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:U5NO4WOXBEAAZAIUHEEXXDJJWA","short_pith_number":"pith:U5NO4WOX","schema_version":"1.0","canonical_sha256":"a75aee59d709000c811439097b8d29b00fbe262284661f83c55ec97040302bef","source":{"kind":"arxiv","id":"2405.18274","version":1},"attestation_state":"computed","paper":{"title":"Signal-Plus-Noise Decomposition of Nonlinear Spiked Random Matrix Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.SP","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Behrad Moniri, Hamed Hassani","submitted_at":"2024-05-28T15:24:35Z","abstract_excerpt":"In this paper, we study a nonlinear spiked random matrix model where a nonlinear function is applied element-wise to a noise matrix perturbed by a rank-one signal. We establish a signal-plus-noise decomposition for this model and identify precise phase transitions in the structure of the signal components at critical thresholds of signal strength. To demonstrate the applicability of this decomposition, we then utilize it to study new phenomena in the problems of signed signal recovery in nonlinear models and community detection in transformed stochastic block models. Finally, we validate our r"},"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":"2405.18274","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.ST","submitted_at":"2024-05-28T15:24:35Z","cross_cats_sorted":["cs.LG","eess.SP","stat.ML","stat.TH"],"title_canon_sha256":"02e0910bc85e350f5e03d78066071b5236b8204e5a50c7f4c0db5f888520dd84","abstract_canon_sha256":"723cf41706b1b366e9d365a203dbb7dfd71eb8bc0a911c08941f4f981a704c09"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:17.750157Z","signature_b64":"1DdpjPC2yYghk4H5aZzXR9AhCPTzVwzX1Pg+nWe9drloMYPORS+kLvWNs+Dj+QDeGEVlzQdJY0WZUFwTjR/HAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a75aee59d709000c811439097b8d29b00fbe262284661f83c55ec97040302bef","last_reissued_at":"2026-07-05T08:24:17.749702Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:17.749702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Signal-Plus-Noise Decomposition of Nonlinear Spiked Random Matrix Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.SP","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Behrad Moniri, Hamed Hassani","submitted_at":"2024-05-28T15:24:35Z","abstract_excerpt":"In this paper, we study a nonlinear spiked random matrix model where a nonlinear function is applied element-wise to a noise matrix perturbed by a rank-one signal. We establish a signal-plus-noise decomposition for this model and identify precise phase transitions in the structure of the signal components at critical thresholds of signal strength. To demonstrate the applicability of this decomposition, we then utilize it to study new phenomena in the problems of signed signal recovery in nonlinear models and community detection in transformed stochastic block models. Finally, we validate our r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18274","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/2405.18274/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":"2405.18274","created_at":"2026-07-05T08:24:17.749753+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.18274v1","created_at":"2026-07-05T08:24:17.749753+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18274","created_at":"2026-07-05T08:24:17.749753+00:00"},{"alias_kind":"pith_short_12","alias_value":"U5NO4WOXBEAA","created_at":"2026-07-05T08:24:17.749753+00:00"},{"alias_kind":"pith_short_16","alias_value":"U5NO4WOXBEAAZAIU","created_at":"2026-07-05T08:24:17.749753+00:00"},{"alias_kind":"pith_short_8","alias_value":"U5NO4WOX","created_at":"2026-07-05T08:24:17.749753+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":294,"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":294,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U5NO4WOXBEAAZAIUHEEXXDJJWA","json":"https://pith.science/pith/U5NO4WOXBEAAZAIUHEEXXDJJWA.json","graph_json":"https://pith.science/api/pith-number/U5NO4WOXBEAAZAIUHEEXXDJJWA/graph.json","events_json":"https://pith.science/api/pith-number/U5NO4WOXBEAAZAIUHEEXXDJJWA/events.json","paper":"https://pith.science/paper/U5NO4WOX"},"agent_actions":{"view_html":"https://pith.science/pith/U5NO4WOXBEAAZAIUHEEXXDJJWA","download_json":"https://pith.science/pith/U5NO4WOXBEAAZAIUHEEXXDJJWA.json","view_paper":"https://pith.science/paper/U5NO4WOX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.18274&json=true","fetch_graph":"https://pith.science/api/pith-number/U5NO4WOXBEAAZAIUHEEXXDJJWA/graph.json","fetch_events":"https://pith.science/api/pith-number/U5NO4WOXBEAAZAIUHEEXXDJJWA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U5NO4WOXBEAAZAIUHEEXXDJJWA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U5NO4WOXBEAAZAIUHEEXXDJJWA/action/storage_attestation","attest_author":"https://pith.science/pith/U5NO4WOXBEAAZAIUHEEXXDJJWA/action/author_attestation","sign_citation":"https://pith.science/pith/U5NO4WOXBEAAZAIUHEEXXDJJWA/action/citation_signature","submit_replication":"https://pith.science/pith/U5NO4WOXBEAAZAIUHEEXXDJJWA/action/replication_record"}},"created_at":"2026-07-05T08:24:17.749753+00:00","updated_at":"2026-07-05T08:24:17.749753+00:00"}