{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:U6Z3MQ4F5TBEXSCICICURTBDLR","short_pith_number":"pith:U6Z3MQ4F","schema_version":"1.0","canonical_sha256":"a7b3b64385ecc24bc848120548cc235c4492555eb7079a46b93834ff247e19a8","source":{"kind":"arxiv","id":"2507.23017","version":1},"attestation_state":"computed","paper":{"title":"A Smoothing Newton Method for Rank-one Matrix Recovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Gabriel Abreu, Tyler Maunu","submitted_at":"2025-07-30T18:25:42Z","abstract_excerpt":"We consider the phase retrieval problem, which involves recovering a rank-one positive semidefinite matrix from rank-one measurements. A recently proposed algorithm based on Bures-Wasserstein gradient descent (BWGD) exhibits superlinear convergence, but it is unstable, and existing theory can only prove local linear convergence for higher rank matrix recovery. We resolve this gap by revealing that BWGD implements Newton's method with a nonsmooth and nonconvex objective. We develop a smoothing framework that regularizes the objective, enabling a stable method with rigorous superlinear convergen"},"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":"2507.23017","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-07-30T18:25:42Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"426518203caa75849d25ec7bf5eff0f9d8db9b602e7e2143506649561912f343","abstract_canon_sha256":"a8b3ac80b6206d073bbbbce7d366ca6d110f4c66ab50cc3f8390d21e25e88569"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:03.825501Z","signature_b64":"T8kreu6qd60r9YjT3t38Xv2+HtS3co1cbF0TMhl0IAwzipgN7bGOnw8SMYpBMYD4B+nfLaw7mEUWcbvP/dZwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7b3b64385ecc24bc848120548cc235c4492555eb7079a46b93834ff247e19a8","last_reissued_at":"2026-07-05T11:46:03.824965Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:03.824965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Smoothing Newton Method for Rank-one Matrix Recovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Gabriel Abreu, Tyler Maunu","submitted_at":"2025-07-30T18:25:42Z","abstract_excerpt":"We consider the phase retrieval problem, which involves recovering a rank-one positive semidefinite matrix from rank-one measurements. A recently proposed algorithm based on Bures-Wasserstein gradient descent (BWGD) exhibits superlinear convergence, but it is unstable, and existing theory can only prove local linear convergence for higher rank matrix recovery. We resolve this gap by revealing that BWGD implements Newton's method with a nonsmooth and nonconvex objective. We develop a smoothing framework that regularizes the objective, enabling a stable method with rigorous superlinear convergen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23017","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/2507.23017/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":"2507.23017","created_at":"2026-07-05T11:46:03.825031+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.23017v1","created_at":"2026-07-05T11:46:03.825031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23017","created_at":"2026-07-05T11:46:03.825031+00:00"},{"alias_kind":"pith_short_12","alias_value":"U6Z3MQ4F5TBE","created_at":"2026-07-05T11:46:03.825031+00:00"},{"alias_kind":"pith_short_16","alias_value":"U6Z3MQ4F5TBEXSCI","created_at":"2026-07-05T11:46:03.825031+00:00"},{"alias_kind":"pith_short_8","alias_value":"U6Z3MQ4F","created_at":"2026-07-05T11:46:03.825031+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U6Z3MQ4F5TBEXSCICICURTBDLR","json":"https://pith.science/pith/U6Z3MQ4F5TBEXSCICICURTBDLR.json","graph_json":"https://pith.science/api/pith-number/U6Z3MQ4F5TBEXSCICICURTBDLR/graph.json","events_json":"https://pith.science/api/pith-number/U6Z3MQ4F5TBEXSCICICURTBDLR/events.json","paper":"https://pith.science/paper/U6Z3MQ4F"},"agent_actions":{"view_html":"https://pith.science/pith/U6Z3MQ4F5TBEXSCICICURTBDLR","download_json":"https://pith.science/pith/U6Z3MQ4F5TBEXSCICICURTBDLR.json","view_paper":"https://pith.science/paper/U6Z3MQ4F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.23017&json=true","fetch_graph":"https://pith.science/api/pith-number/U6Z3MQ4F5TBEXSCICICURTBDLR/graph.json","fetch_events":"https://pith.science/api/pith-number/U6Z3MQ4F5TBEXSCICICURTBDLR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U6Z3MQ4F5TBEXSCICICURTBDLR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U6Z3MQ4F5TBEXSCICICURTBDLR/action/storage_attestation","attest_author":"https://pith.science/pith/U6Z3MQ4F5TBEXSCICICURTBDLR/action/author_attestation","sign_citation":"https://pith.science/pith/U6Z3MQ4F5TBEXSCICICURTBDLR/action/citation_signature","submit_replication":"https://pith.science/pith/U6Z3MQ4F5TBEXSCICICURTBDLR/action/replication_record"}},"created_at":"2026-07-05T11:46:03.825031+00:00","updated_at":"2026-07-05T11:46:03.825031+00:00"}