{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QSMS5IYKMJECCUN3MEO3GAZ7L2","short_pith_number":"pith:QSMS5IYK","schema_version":"1.0","canonical_sha256":"84992ea30a62482151bb611db3033f5ea5b943248f78a3fb890223ad52bc951e","source":{"kind":"arxiv","id":"2511.11927","version":2},"attestation_state":"computed","paper":{"title":"Sparse corruption in low-rank matrix inference: the PCA benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","cond-mat.stat-mech","cs.LG"],"primary_cat":"stat.ML","authors_text":"Gabriele Sicuro, Pierpaolo Vivo, Urte Adomaityte","submitted_at":"2025-11-14T23:09:54Z","abstract_excerpt":"Principal Component Analysis (PCA) is a standard tool for extracting a low-rank signal from noisy observations. It is known that applying PCA to a rank-one signal corrupted by a dense, homogeneous noise, in the large matrix size limit, the celebrated BBP transition occurs, where the emergence of an outlying eigenvalue and the alignment of the corresponding eigenvector occur at the same critical signal strength. Here we study the case of sparse noise corruption. The noise matrix is modelled as the adjacency matrix of a weighted undirected graph with finite average connectivity. Using the replic"},"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":"2511.11927","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-11-14T23:09:54Z","cross_cats_sorted":["cond-mat.dis-nn","cond-mat.stat-mech","cs.LG"],"title_canon_sha256":"7cd70fff7f02a5b989e2adc30ce8c1e0afb4113ea61f11564a23ea364b9a4d10","abstract_canon_sha256":"ca9801be31f20890d74fae3e2c60ae76f707e131af7a7b5f67d46b3e7ddb6482"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T02:18:27.730090Z","signature_b64":"zOIX2ano1uKMuweCLmQjrWocMhb5bHJFvueE4r/5JIZITJAW2zMyTmSEXSg9/5q16X8aVPpuEAeOOieH0s7wCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84992ea30a62482151bb611db3033f5ea5b943248f78a3fb890223ad52bc951e","last_reissued_at":"2026-08-11T02:18:27.726081Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T02:18:27.726081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparse corruption in low-rank matrix inference: the PCA benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","cond-mat.stat-mech","cs.LG"],"primary_cat":"stat.ML","authors_text":"Gabriele Sicuro, Pierpaolo Vivo, Urte Adomaityte","submitted_at":"2025-11-14T23:09:54Z","abstract_excerpt":"Principal Component Analysis (PCA) is a standard tool for extracting a low-rank signal from noisy observations. It is known that applying PCA to a rank-one signal corrupted by a dense, homogeneous noise, in the large matrix size limit, the celebrated BBP transition occurs, where the emergence of an outlying eigenvalue and the alignment of the corresponding eigenvector occur at the same critical signal strength. Here we study the case of sparse noise corruption. The noise matrix is modelled as the adjacency matrix of a weighted undirected graph with finite average connectivity. Using the replic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.11927","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/2511.11927/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":"2511.11927","created_at":"2026-08-11T02:18:27.728578+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.11927v2","created_at":"2026-08-11T02:18:27.728578+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.11927","created_at":"2026-08-11T02:18:27.728578+00:00"},{"alias_kind":"pith_short_12","alias_value":"QSMS5IYKMJEC","created_at":"2026-08-11T02:18:27.728578+00:00"},{"alias_kind":"pith_short_16","alias_value":"QSMS5IYKMJECCUN3","created_at":"2026-08-11T02:18:27.728578+00:00"},{"alias_kind":"pith_short_8","alias_value":"QSMS5IYK","created_at":"2026-08-11T02:18:27.728578+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2606.04651","citing_title":"Spectral criteria for generalization in unsupervised Hebbian nets","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2606.28486","citing_title":"Spectral phase transitions and trainability in neural network learning dynamics","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26852","citing_title":"Largest eigenvalue and top eigenvector statistics of large Euclidean random matrices","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26852","citing_title":"Largest eigenvalue and top eigenvector statistics of large Euclidean random matrices","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18523","citing_title":"BBP transition and the leading eigenvector of the spiked Wigner model with inhomogeneous noise","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QSMS5IYKMJECCUN3MEO3GAZ7L2","json":"https://pith.science/pith/QSMS5IYKMJECCUN3MEO3GAZ7L2.json","graph_json":"https://pith.science/api/pith-number/QSMS5IYKMJECCUN3MEO3GAZ7L2/graph.json","events_json":"https://pith.science/api/pith-number/QSMS5IYKMJECCUN3MEO3GAZ7L2/events.json","paper":"https://pith.science/paper/QSMS5IYK"},"agent_actions":{"view_html":"https://pith.science/pith/QSMS5IYKMJECCUN3MEO3GAZ7L2","download_json":"https://pith.science/pith/QSMS5IYKMJECCUN3MEO3GAZ7L2.json","view_paper":"https://pith.science/paper/QSMS5IYK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.11927&json=true","fetch_graph":"https://pith.science/api/pith-number/QSMS5IYKMJECCUN3MEO3GAZ7L2/graph.json","fetch_events":"https://pith.science/api/pith-number/QSMS5IYKMJECCUN3MEO3GAZ7L2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QSMS5IYKMJECCUN3MEO3GAZ7L2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QSMS5IYKMJECCUN3MEO3GAZ7L2/action/storage_attestation","attest_author":"https://pith.science/pith/QSMS5IYKMJECCUN3MEO3GAZ7L2/action/author_attestation","sign_citation":"https://pith.science/pith/QSMS5IYKMJECCUN3MEO3GAZ7L2/action/citation_signature","submit_replication":"https://pith.science/pith/QSMS5IYKMJECCUN3MEO3GAZ7L2/action/replication_record"}},"created_at":"2026-08-11T02:18:27.728578+00:00","updated_at":"2026-08-11T02:18:27.728578+00:00"}