{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XHU4UFC2H3WAPVYVPD4V3QU2RT","short_pith_number":"pith:XHU4UFC2","schema_version":"1.0","canonical_sha256":"b9e9ca145a3eec07d71578f95dc29a8cf20ea4dbeaeccc0affb348dc8c9a815a","source":{"kind":"arxiv","id":"2201.05101","version":1},"attestation_state":"computed","paper":{"title":"Statistically Optimal First Order Algorithms: A Proof via Orthogonalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.CO","authors_text":"Andrea Montanari, Yuchen Wu","submitted_at":"2022-01-13T17:45:56Z","abstract_excerpt":"We consider a class of statistical estimation problems in which we are given a random data matrix ${\\boldsymbol X}\\in {\\mathbb R}^{n\\times d}$ (and possibly some labels ${\\boldsymbol y}\\in{\\mathbb R}^n$) and would like to estimate a coefficient vector ${\\boldsymbol \\theta}\\in{\\mathbb R}^d$ (or possibly a constant number of such vectors). Special cases include low-rank matrix estimation and regularized estimation in generalized linear models (e.g., sparse regression). First order methods proceed by iteratively multiplying current estimates by ${\\boldsymbol X}$ or its transpose. Examples include"},"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":"2201.05101","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2022-01-13T17:45:56Z","cross_cats_sorted":[],"title_canon_sha256":"2a771dbcfcd41839b1a8f682e3de6d3bd575693c464c3f8369848352c7c676f8","abstract_canon_sha256":"9a18dcabd1b7115bdac55ca88fb85280569af37204629c54979e93408e0273b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:48:15.959359Z","signature_b64":"qDBNbCZrGhbtYtMc1DdpLelDEIuPUWwSg8pljOZeQnWvdLlP7ggTitnSjtg0+BDASMuwpfW9d41Q9GySotxWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9e9ca145a3eec07d71578f95dc29a8cf20ea4dbeaeccc0affb348dc8c9a815a","last_reissued_at":"2026-07-05T03:48:15.958881Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:48:15.958881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Statistically Optimal First Order Algorithms: A Proof via Orthogonalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.CO","authors_text":"Andrea Montanari, Yuchen Wu","submitted_at":"2022-01-13T17:45:56Z","abstract_excerpt":"We consider a class of statistical estimation problems in which we are given a random data matrix ${\\boldsymbol X}\\in {\\mathbb R}^{n\\times d}$ (and possibly some labels ${\\boldsymbol y}\\in{\\mathbb R}^n$) and would like to estimate a coefficient vector ${\\boldsymbol \\theta}\\in{\\mathbb R}^d$ (or possibly a constant number of such vectors). Special cases include low-rank matrix estimation and regularized estimation in generalized linear models (e.g., sparse regression). First order methods proceed by iteratively multiplying current estimates by ${\\boldsymbol X}$ or its transpose. Examples include"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.05101","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/2201.05101/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":"2201.05101","created_at":"2026-07-05T03:48:15.958934+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.05101v1","created_at":"2026-07-05T03:48:15.958934+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.05101","created_at":"2026-07-05T03:48:15.958934+00:00"},{"alias_kind":"pith_short_12","alias_value":"XHU4UFC2H3WA","created_at":"2026-07-05T03:48:15.958934+00:00"},{"alias_kind":"pith_short_16","alias_value":"XHU4UFC2H3WAPVYV","created_at":"2026-07-05T03:48:15.958934+00:00"},{"alias_kind":"pith_short_8","alias_value":"XHU4UFC2","created_at":"2026-07-05T03:48:15.958934+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":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XHU4UFC2H3WAPVYVPD4V3QU2RT","json":"https://pith.science/pith/XHU4UFC2H3WAPVYVPD4V3QU2RT.json","graph_json":"https://pith.science/api/pith-number/XHU4UFC2H3WAPVYVPD4V3QU2RT/graph.json","events_json":"https://pith.science/api/pith-number/XHU4UFC2H3WAPVYVPD4V3QU2RT/events.json","paper":"https://pith.science/paper/XHU4UFC2"},"agent_actions":{"view_html":"https://pith.science/pith/XHU4UFC2H3WAPVYVPD4V3QU2RT","download_json":"https://pith.science/pith/XHU4UFC2H3WAPVYVPD4V3QU2RT.json","view_paper":"https://pith.science/paper/XHU4UFC2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.05101&json=true","fetch_graph":"https://pith.science/api/pith-number/XHU4UFC2H3WAPVYVPD4V3QU2RT/graph.json","fetch_events":"https://pith.science/api/pith-number/XHU4UFC2H3WAPVYVPD4V3QU2RT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XHU4UFC2H3WAPVYVPD4V3QU2RT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XHU4UFC2H3WAPVYVPD4V3QU2RT/action/storage_attestation","attest_author":"https://pith.science/pith/XHU4UFC2H3WAPVYVPD4V3QU2RT/action/author_attestation","sign_citation":"https://pith.science/pith/XHU4UFC2H3WAPVYVPD4V3QU2RT/action/citation_signature","submit_replication":"https://pith.science/pith/XHU4UFC2H3WAPVYVPD4V3QU2RT/action/replication_record"}},"created_at":"2026-07-05T03:48:15.958934+00:00","updated_at":"2026-07-05T03:48:15.958934+00:00"}