{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H7KOD6A44TTFI2IOBZDEAMDN3N","short_pith_number":"pith:H7KOD6A4","schema_version":"1.0","canonical_sha256":"3fd4e1f81ce4e654690e0e4640306ddb6711641d8845c624ea55d39ca21a8a1b","source":{"kind":"arxiv","id":"2410.21194","version":1},"attestation_state":"computed","paper":{"title":"SoS Certifiability of Subgaussian Distributions and its Algorithmic Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.DS","authors_text":"Ankit Pensia, Ilias Diakonikolas, Samuel B. Hopkins, Stefan Tiegel","submitted_at":"2024-10-28T16:36:58Z","abstract_excerpt":"We prove that there is a universal constant $C>0$ so that for every $d \\in \\mathbb N$, every centered subgaussian distribution $\\mathcal D$ on $\\mathbb R^d$, and every even $p \\in \\mathbb N$, the $d$-variate polynomial $(Cp)^{p/2} \\cdot \\|v\\|_{2}^p - \\mathbb E_{X \\sim \\mathcal D} \\langle v,X\\rangle^p$ is a sum of square polynomials. This establishes that every subgaussian distribution is \\emph{SoS-certifiably subgaussian} -- a condition that yields efficient learning algorithms for a wide variety of high-dimensional statistical tasks. As a direct corollary, we obtain computationally efficient "},"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":"2410.21194","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2024-10-28T16:36:58Z","cross_cats_sorted":["cs.LG","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"1799649abdcd66e5b3461b229c82ff79161a032ccf0d138e4bd4417777bb2964","abstract_canon_sha256":"a22d0347e67f30bd9bc17880e7259c3346d6f64c26c3de63ea99d1b8d1adf78f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:16.760788Z","signature_b64":"Ez28GPauAAvdapllhZwQ+M8GNfWQpI5cRmmWZhLX+he3hgp+lSwX8eVfkhDlt3I8kWp7FXRc3i6f8vGzLrlrBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fd4e1f81ce4e654690e0e4640306ddb6711641d8845c624ea55d39ca21a8a1b","last_reissued_at":"2026-07-05T09:27:16.760344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:16.760344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SoS Certifiability of Subgaussian Distributions and its Algorithmic Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.DS","authors_text":"Ankit Pensia, Ilias Diakonikolas, Samuel B. Hopkins, Stefan Tiegel","submitted_at":"2024-10-28T16:36:58Z","abstract_excerpt":"We prove that there is a universal constant $C>0$ so that for every $d \\in \\mathbb N$, every centered subgaussian distribution $\\mathcal D$ on $\\mathbb R^d$, and every even $p \\in \\mathbb N$, the $d$-variate polynomial $(Cp)^{p/2} \\cdot \\|v\\|_{2}^p - \\mathbb E_{X \\sim \\mathcal D} \\langle v,X\\rangle^p$ is a sum of square polynomials. This establishes that every subgaussian distribution is \\emph{SoS-certifiably subgaussian} -- a condition that yields efficient learning algorithms for a wide variety of high-dimensional statistical tasks. As a direct corollary, we obtain computationally efficient "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21194","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/2410.21194/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":"2410.21194","created_at":"2026-07-05T09:27:16.760406+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.21194v1","created_at":"2026-07-05T09:27:16.760406+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21194","created_at":"2026-07-05T09:27:16.760406+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7KOD6A44TTF","created_at":"2026-07-05T09:27:16.760406+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7KOD6A44TTFI2IO","created_at":"2026-07-05T09:27:16.760406+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7KOD6A4","created_at":"2026-07-05T09:27:16.760406+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06564","citing_title":"Nearly Optimal Robust Covariance and Scatter Matrix Estimation Beyond Gaussians","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H7KOD6A44TTFI2IOBZDEAMDN3N","json":"https://pith.science/pith/H7KOD6A44TTFI2IOBZDEAMDN3N.json","graph_json":"https://pith.science/api/pith-number/H7KOD6A44TTFI2IOBZDEAMDN3N/graph.json","events_json":"https://pith.science/api/pith-number/H7KOD6A44TTFI2IOBZDEAMDN3N/events.json","paper":"https://pith.science/paper/H7KOD6A4"},"agent_actions":{"view_html":"https://pith.science/pith/H7KOD6A44TTFI2IOBZDEAMDN3N","download_json":"https://pith.science/pith/H7KOD6A44TTFI2IOBZDEAMDN3N.json","view_paper":"https://pith.science/paper/H7KOD6A4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.21194&json=true","fetch_graph":"https://pith.science/api/pith-number/H7KOD6A44TTFI2IOBZDEAMDN3N/graph.json","fetch_events":"https://pith.science/api/pith-number/H7KOD6A44TTFI2IOBZDEAMDN3N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7KOD6A44TTFI2IOBZDEAMDN3N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7KOD6A44TTFI2IOBZDEAMDN3N/action/storage_attestation","attest_author":"https://pith.science/pith/H7KOD6A44TTFI2IOBZDEAMDN3N/action/author_attestation","sign_citation":"https://pith.science/pith/H7KOD6A44TTFI2IOBZDEAMDN3N/action/citation_signature","submit_replication":"https://pith.science/pith/H7KOD6A44TTFI2IOBZDEAMDN3N/action/replication_record"}},"created_at":"2026-07-05T09:27:16.760406+00:00","updated_at":"2026-07-05T09:27:16.760406+00:00"}