{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HLE4LOWYVTPU2WJ5GBMMMYYSZA","short_pith_number":"pith:HLE4LOWY","schema_version":"1.0","canonical_sha256":"3ac9c5bad8acdf4d593d3058c66312c813c0a2e0ad50c9333347ed0b8320ce98","source":{"kind":"arxiv","id":"2507.22170","version":1},"attestation_state":"computed","paper":{"title":"Stacked SVD or SVD stacked? A Random Matrix Theory perspective on data integration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.ME","stat.TH"],"primary_cat":"stat.ML","authors_text":"Phillip B. Nicol, Rafael A. Irizarry, Rong Ma, Tavor Z. Baharav","submitted_at":"2025-07-29T19:03:01Z","abstract_excerpt":"Modern data analysis increasingly requires identifying shared latent structure across multiple high-dimensional datasets. A commonly used model assumes that the data matrices are noisy observations of low-rank matrices with a shared singular subspace. In this case, two primary methods have emerged for estimating this shared structure, which vary in how they integrate information across datasets. The first approach, termed Stack-SVD, concatenates all the datasets, and then performs a singular value decomposition (SVD). The second approach, termed SVD-Stack, first performs an SVD separately for "},"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":"2507.22170","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-07-29T19:03:01Z","cross_cats_sorted":["cs.LG","math.ST","stat.ME","stat.TH"],"title_canon_sha256":"35bf183f8e5670a8aececbd1f9f9ff209832b6415483b7e144c518b1fa48c056","abstract_canon_sha256":"ea23fe9e54eabd292ab29817ea29a0134ba4147a9e2c3654f515ec3116e327af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:17.593244Z","signature_b64":"KG3ti16SIzUpMoWkrZeF/7uARepYQiicvglGLmu+tSrBiLKW///6N4QbJTFKNJoxJfNH9TOf9pBdI4RMN4B4DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ac9c5bad8acdf4d593d3058c66312c813c0a2e0ad50c9333347ed0b8320ce98","last_reissued_at":"2026-07-05T11:45:17.592693Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:17.592693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stacked SVD or SVD stacked? A Random Matrix Theory perspective on data integration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.ME","stat.TH"],"primary_cat":"stat.ML","authors_text":"Phillip B. Nicol, Rafael A. Irizarry, Rong Ma, Tavor Z. Baharav","submitted_at":"2025-07-29T19:03:01Z","abstract_excerpt":"Modern data analysis increasingly requires identifying shared latent structure across multiple high-dimensional datasets. A commonly used model assumes that the data matrices are noisy observations of low-rank matrices with a shared singular subspace. In this case, two primary methods have emerged for estimating this shared structure, which vary in how they integrate information across datasets. The first approach, termed Stack-SVD, concatenates all the datasets, and then performs a singular value decomposition (SVD). The second approach, termed SVD-Stack, first performs an SVD separately for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22170","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/2507.22170/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":"2507.22170","created_at":"2026-07-05T11:45:17.592757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.22170v1","created_at":"2026-07-05T11:45:17.592757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22170","created_at":"2026-07-05T11:45:17.592757+00:00"},{"alias_kind":"pith_short_12","alias_value":"HLE4LOWYVTPU","created_at":"2026-07-05T11:45:17.592757+00:00"},{"alias_kind":"pith_short_16","alias_value":"HLE4LOWYVTPU2WJ5","created_at":"2026-07-05T11:45:17.592757+00:00"},{"alias_kind":"pith_short_8","alias_value":"HLE4LOWY","created_at":"2026-07-05T11:45:17.592757+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06330","citing_title":"Direct and efficient estimation of bilinear forms in staggered tensor panels","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2606.11570","citing_title":"Enhancing Spectral Embedding through Robust and Flexible Knowledge Transfer in Electronic Health Records","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24662","citing_title":"Information bottleneck for learning the phase space of dynamics from high-dimensional experimental data","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HLE4LOWYVTPU2WJ5GBMMMYYSZA","json":"https://pith.science/pith/HLE4LOWYVTPU2WJ5GBMMMYYSZA.json","graph_json":"https://pith.science/api/pith-number/HLE4LOWYVTPU2WJ5GBMMMYYSZA/graph.json","events_json":"https://pith.science/api/pith-number/HLE4LOWYVTPU2WJ5GBMMMYYSZA/events.json","paper":"https://pith.science/paper/HLE4LOWY"},"agent_actions":{"view_html":"https://pith.science/pith/HLE4LOWYVTPU2WJ5GBMMMYYSZA","download_json":"https://pith.science/pith/HLE4LOWYVTPU2WJ5GBMMMYYSZA.json","view_paper":"https://pith.science/paper/HLE4LOWY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.22170&json=true","fetch_graph":"https://pith.science/api/pith-number/HLE4LOWYVTPU2WJ5GBMMMYYSZA/graph.json","fetch_events":"https://pith.science/api/pith-number/HLE4LOWYVTPU2WJ5GBMMMYYSZA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HLE4LOWYVTPU2WJ5GBMMMYYSZA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HLE4LOWYVTPU2WJ5GBMMMYYSZA/action/storage_attestation","attest_author":"https://pith.science/pith/HLE4LOWYVTPU2WJ5GBMMMYYSZA/action/author_attestation","sign_citation":"https://pith.science/pith/HLE4LOWYVTPU2WJ5GBMMMYYSZA/action/citation_signature","submit_replication":"https://pith.science/pith/HLE4LOWYVTPU2WJ5GBMMMYYSZA/action/replication_record"}},"created_at":"2026-07-05T11:45:17.592757+00:00","updated_at":"2026-07-05T11:45:17.592757+00:00"}