{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DU42IZ6IECCJS7P6JISZDDBV7K","short_pith_number":"pith:DU42IZ6I","schema_version":"1.0","canonical_sha256":"1d39a467c82084997dfe4a25918c35faafa1baece4c7f63f69ba26ab3ba739e4","source":{"kind":"arxiv","id":"1811.00306","version":5},"attestation_state":"computed","paper":{"title":"Consistent estimation of high-dimensional factor models when the factor number is over-estimated","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Haeran Cho, Matteo Barigozzi","submitted_at":"2018-11-01T10:36:27Z","abstract_excerpt":"A high-dimensional $r$-factor model for an $n$-dimensional vector time series is characterised by the presence of a large eigengap (increasing with $n$) between the $r$-th and the $(r+1)$-th largest eigenvalues of the covariance matrix. Consequently, Principal Component (PC) analysis is the most popular estimation method for factor models and its consistency, when $r$ is correctly estimated, is well-established in the literature. However, popular factor number estimators often suffer from the lack of an obvious eigengap in empirical eigenvalues and tend to over-estimate $r$ due, for example, t"},"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":"1811.00306","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2018-11-01T10:36:27Z","cross_cats_sorted":[],"title_canon_sha256":"c71623fd74a97d27c665f388fd26a81a0a4f5cb53c8144a101417e0bec24344d","abstract_canon_sha256":"f09d561234004692c1b3b6ccf5fbb9dffa3f4a294b1d4443e9aff1b7a12e68e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:20:51.848523Z","signature_b64":"A7//K/t+WU7Hzk/fBbM5Qsestl8FQq7aX1WgAo6R6YbdrDRSmklLpFZ+pao70eNSi8kxN3XL99GGDXbIH974Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d39a467c82084997dfe4a25918c35faafa1baece4c7f63f69ba26ab3ba739e4","last_reissued_at":"2026-07-05T02:20:51.848043Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:20:51.848043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Consistent estimation of high-dimensional factor models when the factor number is over-estimated","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Haeran Cho, Matteo Barigozzi","submitted_at":"2018-11-01T10:36:27Z","abstract_excerpt":"A high-dimensional $r$-factor model for an $n$-dimensional vector time series is characterised by the presence of a large eigengap (increasing with $n$) between the $r$-th and the $(r+1)$-th largest eigenvalues of the covariance matrix. Consequently, Principal Component (PC) analysis is the most popular estimation method for factor models and its consistency, when $r$ is correctly estimated, is well-established in the literature. However, popular factor number estimators often suffer from the lack of an obvious eigengap in empirical eigenvalues and tend to over-estimate $r$ due, for example, t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00306","kind":"arxiv","version":5},"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/1811.00306/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":"1811.00306","created_at":"2026-07-05T02:20:51.848098+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.00306v5","created_at":"2026-07-05T02:20:51.848098+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00306","created_at":"2026-07-05T02:20:51.848098+00:00"},{"alias_kind":"pith_short_12","alias_value":"DU42IZ6IECCJ","created_at":"2026-07-05T02:20:51.848098+00:00"},{"alias_kind":"pith_short_16","alias_value":"DU42IZ6IECCJS7P6","created_at":"2026-07-05T02:20:51.848098+00:00"},{"alias_kind":"pith_short_8","alias_value":"DU42IZ6I","created_at":"2026-07-05T02:20:51.848098+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.01252","citing_title":"Learning Latent Factors from Diversified Projections and its Applications to Over-Estimated and Weak Factors","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DU42IZ6IECCJS7P6JISZDDBV7K","json":"https://pith.science/pith/DU42IZ6IECCJS7P6JISZDDBV7K.json","graph_json":"https://pith.science/api/pith-number/DU42IZ6IECCJS7P6JISZDDBV7K/graph.json","events_json":"https://pith.science/api/pith-number/DU42IZ6IECCJS7P6JISZDDBV7K/events.json","paper":"https://pith.science/paper/DU42IZ6I"},"agent_actions":{"view_html":"https://pith.science/pith/DU42IZ6IECCJS7P6JISZDDBV7K","download_json":"https://pith.science/pith/DU42IZ6IECCJS7P6JISZDDBV7K.json","view_paper":"https://pith.science/paper/DU42IZ6I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.00306&json=true","fetch_graph":"https://pith.science/api/pith-number/DU42IZ6IECCJS7P6JISZDDBV7K/graph.json","fetch_events":"https://pith.science/api/pith-number/DU42IZ6IECCJS7P6JISZDDBV7K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DU42IZ6IECCJS7P6JISZDDBV7K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DU42IZ6IECCJS7P6JISZDDBV7K/action/storage_attestation","attest_author":"https://pith.science/pith/DU42IZ6IECCJS7P6JISZDDBV7K/action/author_attestation","sign_citation":"https://pith.science/pith/DU42IZ6IECCJS7P6JISZDDBV7K/action/citation_signature","submit_replication":"https://pith.science/pith/DU42IZ6IECCJS7P6JISZDDBV7K/action/replication_record"}},"created_at":"2026-07-05T02:20:51.848098+00:00","updated_at":"2026-07-05T02:20:51.848098+00:00"}