{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:EPMBLXCXYJEEN63GFOA7IHO3PN","short_pith_number":"pith:EPMBLXCX","schema_version":"1.0","canonical_sha256":"23d815dc57c24846fb662b81f41ddb7b4e22d30452a91377ea9c8a5589a54f1d","source":{"kind":"arxiv","id":"2001.06188","version":2},"attestation_state":"computed","paper":{"title":"On Random Matrices Arising in Deep Neural Networks. Gaussian Case","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.MP","stat.ML"],"primary_cat":"math-ph","authors_text":"Leonid Pastur","submitted_at":"2020-01-17T08:30:57Z","abstract_excerpt":"The paper deals with distribution of singular values of product of random matrices arising in the analysis of deep neural networks. The matrices resemble the product analogs of the sample covariance matrices, however, an important difference is that the population covariance matrices, which are assumed to be non-random in the standard setting of statistics and random matrix theory, are now random, moreover, are certain functions of random data matrices. The problem has been considered in recent work [21] by using the techniques of free probability theory. Since, however, free probability theor"},"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":"2001.06188","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math-ph","submitted_at":"2020-01-17T08:30:57Z","cross_cats_sorted":["math.MP","stat.ML"],"title_canon_sha256":"fab945285f299b58556bb0c11184d39b983a15cf81a2709f1876b44bbf4380fd","abstract_canon_sha256":"6f90d88483401ddbe6a165604c3be3ea763266f6f676823214796b821a05db53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:53:07.799976Z","signature_b64":"b4EQx0H/t/VIzF+78CXGjRjwm5kqX67wYhXbgDynCplTXxQIyiQlEaWBt2TdIqhXFGu6I8k2PwGHxRqYP3XWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23d815dc57c24846fb662b81f41ddb7b4e22d30452a91377ea9c8a5589a54f1d","last_reissued_at":"2026-07-05T01:53:07.799579Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:53:07.799579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Random Matrices Arising in Deep Neural Networks. Gaussian Case","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.MP","stat.ML"],"primary_cat":"math-ph","authors_text":"Leonid Pastur","submitted_at":"2020-01-17T08:30:57Z","abstract_excerpt":"The paper deals with distribution of singular values of product of random matrices arising in the analysis of deep neural networks. The matrices resemble the product analogs of the sample covariance matrices, however, an important difference is that the population covariance matrices, which are assumed to be non-random in the standard setting of statistics and random matrix theory, are now random, moreover, are certain functions of random data matrices. The problem has been considered in recent work [21] by using the techniques of free probability theory. Since, however, free probability theor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.06188","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/2001.06188/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":"2001.06188","created_at":"2026-07-05T01:53:07.799637+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.06188v2","created_at":"2026-07-05T01:53:07.799637+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.06188","created_at":"2026-07-05T01:53:07.799637+00:00"},{"alias_kind":"pith_short_12","alias_value":"EPMBLXCXYJEE","created_at":"2026-07-05T01:53:07.799637+00:00"},{"alias_kind":"pith_short_16","alias_value":"EPMBLXCXYJEEN63G","created_at":"2026-07-05T01:53:07.799637+00:00"},{"alias_kind":"pith_short_8","alias_value":"EPMBLXCX","created_at":"2026-07-05T01:53:07.799637+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02608","citing_title":"Pruning Deep Neural Networks via the Marchenko--Pastur Distribution","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EPMBLXCXYJEEN63GFOA7IHO3PN","json":"https://pith.science/pith/EPMBLXCXYJEEN63GFOA7IHO3PN.json","graph_json":"https://pith.science/api/pith-number/EPMBLXCXYJEEN63GFOA7IHO3PN/graph.json","events_json":"https://pith.science/api/pith-number/EPMBLXCXYJEEN63GFOA7IHO3PN/events.json","paper":"https://pith.science/paper/EPMBLXCX"},"agent_actions":{"view_html":"https://pith.science/pith/EPMBLXCXYJEEN63GFOA7IHO3PN","download_json":"https://pith.science/pith/EPMBLXCXYJEEN63GFOA7IHO3PN.json","view_paper":"https://pith.science/paper/EPMBLXCX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.06188&json=true","fetch_graph":"https://pith.science/api/pith-number/EPMBLXCXYJEEN63GFOA7IHO3PN/graph.json","fetch_events":"https://pith.science/api/pith-number/EPMBLXCXYJEEN63GFOA7IHO3PN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EPMBLXCXYJEEN63GFOA7IHO3PN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EPMBLXCXYJEEN63GFOA7IHO3PN/action/storage_attestation","attest_author":"https://pith.science/pith/EPMBLXCXYJEEN63GFOA7IHO3PN/action/author_attestation","sign_citation":"https://pith.science/pith/EPMBLXCXYJEEN63GFOA7IHO3PN/action/citation_signature","submit_replication":"https://pith.science/pith/EPMBLXCXYJEEN63GFOA7IHO3PN/action/replication_record"}},"created_at":"2026-07-05T01:53:07.799637+00:00","updated_at":"2026-07-05T01:53:07.799637+00:00"}