{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3D5EHAHOIN5NAA3VFYXYQBYMMS","short_pith_number":"pith:3D5EHAHO","schema_version":"1.0","canonical_sha256":"d8fa4380ee437ad003752e2f88070c6483f9570189537e08d64c55a91cba8ce8","source":{"kind":"arxiv","id":"2206.06526","version":2},"attestation_state":"computed","paper":{"title":"Overparametrized linear dimensionality reductions: From projection pursuit to two-layer neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andrea Montanari, Kangjie Zhou","submitted_at":"2022-06-14T00:07:33Z","abstract_excerpt":"Given a cloud of $n$ data points in $\\mathbb{R}^d$, consider all projections onto $m$-dimensional subspaces of $\\mathbb{R}^d$ and, for each such projection, the empirical distribution of the projected points. What does this collection of probability distributions look like when $n,d$ grow large?\n  We consider this question under the null model in which the points are i.i.d. standard Gaussian vectors, focusing on the asymptotic regime in which $n,d\\to\\infty$, with $n/d\\to\\alpha\\in (0,\\infty)$, while $m$ is fixed. Denoting by $\\mathscr{F}_{m, \\alpha}$ the set of probability distributions in $\\ma"},"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":"2206.06526","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-06-14T00:07:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9f9afeeb6b8489a745cb21b1d94da99657084a373f7e7189d92981e18c8e2653","abstract_canon_sha256":"6a046379d80db3e4e62457c76d5bb1522b47ed25faf9dcb8de5074104dc74765"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:11.927489Z","signature_b64":"iKRKPDqJ9uoMKMjds9RmjfxJWqXgKvhyGgy2asqC6KFbZnfSTPJyY1X1122yR451eZz5oUSJC5oUSPCnvs+JAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8fa4380ee437ad003752e2f88070c6483f9570189537e08d64c55a91cba8ce8","last_reissued_at":"2026-07-05T10:58:11.926951Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:11.926951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Overparametrized linear dimensionality reductions: From projection pursuit to two-layer neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andrea Montanari, Kangjie Zhou","submitted_at":"2022-06-14T00:07:33Z","abstract_excerpt":"Given a cloud of $n$ data points in $\\mathbb{R}^d$, consider all projections onto $m$-dimensional subspaces of $\\mathbb{R}^d$ and, for each such projection, the empirical distribution of the projected points. What does this collection of probability distributions look like when $n,d$ grow large?\n  We consider this question under the null model in which the points are i.i.d. standard Gaussian vectors, focusing on the asymptotic regime in which $n,d\\to\\infty$, with $n/d\\to\\alpha\\in (0,\\infty)$, while $m$ is fixed. Denoting by $\\mathscr{F}_{m, \\alpha}$ the set of probability distributions in $\\ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.06526","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/2206.06526/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":"2206.06526","created_at":"2026-07-05T10:58:11.927014+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.06526v2","created_at":"2026-07-05T10:58:11.927014+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.06526","created_at":"2026-07-05T10:58:11.927014+00:00"},{"alias_kind":"pith_short_12","alias_value":"3D5EHAHOIN5N","created_at":"2026-07-05T10:58:11.927014+00:00"},{"alias_kind":"pith_short_16","alias_value":"3D5EHAHOIN5NAA3V","created_at":"2026-07-05T10:58:11.927014+00:00"},{"alias_kind":"pith_short_8","alias_value":"3D5EHAHO","created_at":"2026-07-05T10:58:11.927014+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28573","citing_title":"Replica Symmetry Breaking and Algorithmic Thresholds in Empirical Risk Minimization under Multi-Index Model","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3D5EHAHOIN5NAA3VFYXYQBYMMS","json":"https://pith.science/pith/3D5EHAHOIN5NAA3VFYXYQBYMMS.json","graph_json":"https://pith.science/api/pith-number/3D5EHAHOIN5NAA3VFYXYQBYMMS/graph.json","events_json":"https://pith.science/api/pith-number/3D5EHAHOIN5NAA3VFYXYQBYMMS/events.json","paper":"https://pith.science/paper/3D5EHAHO"},"agent_actions":{"view_html":"https://pith.science/pith/3D5EHAHOIN5NAA3VFYXYQBYMMS","download_json":"https://pith.science/pith/3D5EHAHOIN5NAA3VFYXYQBYMMS.json","view_paper":"https://pith.science/paper/3D5EHAHO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.06526&json=true","fetch_graph":"https://pith.science/api/pith-number/3D5EHAHOIN5NAA3VFYXYQBYMMS/graph.json","fetch_events":"https://pith.science/api/pith-number/3D5EHAHOIN5NAA3VFYXYQBYMMS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3D5EHAHOIN5NAA3VFYXYQBYMMS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3D5EHAHOIN5NAA3VFYXYQBYMMS/action/storage_attestation","attest_author":"https://pith.science/pith/3D5EHAHOIN5NAA3VFYXYQBYMMS/action/author_attestation","sign_citation":"https://pith.science/pith/3D5EHAHOIN5NAA3VFYXYQBYMMS/action/citation_signature","submit_replication":"https://pith.science/pith/3D5EHAHOIN5NAA3VFYXYQBYMMS/action/replication_record"}},"created_at":"2026-07-05T10:58:11.927014+00:00","updated_at":"2026-07-05T10:58:11.927014+00:00"}