{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LEIKKPCH54SRQSTUVRWXJSKQIY","short_pith_number":"pith:LEIKKPCH","schema_version":"1.0","canonical_sha256":"5910a53c47ef25184a74ac6d74c9504609d119588dbe8faa3e93ec153cff6e46","source":{"kind":"arxiv","id":"2205.15150","version":3},"attestation_state":"computed","paper":{"title":"Principal Component Analysis based frameworks for efficient missing data imputation algorithms","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hoang Thien Ly, Hugo L. Hammer, Michael Alexander Riegler, P{\\aa}l Halvorsen, Thu Nguyen","submitted_at":"2022-05-30T14:47:27Z","abstract_excerpt":"Missing data is a commonly occurring problem in practice. Many imputation methods have been developed to fill in the missing entries. However, not all of them can scale to high-dimensional data, especially the multiple imputation techniques. Meanwhile, the data nowadays tends toward high-dimensional. Therefore, in this work, we propose Principal Component Analysis Imputation (PCAI), a simple but versatile framework based on Principal Component Analysis (PCA) to speed up the imputation process and alleviate memory issues of many available imputation techniques, without sacrificing the imputatio"},"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":"2205.15150","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-30T14:47:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bbf06e4195e844433a2f2e8f952fb92136db84453d6405f8247cc64a4b6905e5","abstract_canon_sha256":"604bd1910c96197535fa627a4648f23d9840e5b32806824e121d675fd6158df2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:52:20.297721Z","signature_b64":"9yxgq+E0GUcCqQw2wjDtPAKDL6Gu5PaL9STnuoj1xUpZoR9pWymhh7lwGgFKJh2oSMakmJCJVQ/2DUcMhqm/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5910a53c47ef25184a74ac6d74c9504609d119588dbe8faa3e93ec153cff6e46","last_reissued_at":"2026-07-05T05:52:20.297356Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:52:20.297356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Principal Component Analysis based frameworks for efficient missing data imputation algorithms","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hoang Thien Ly, Hugo L. Hammer, Michael Alexander Riegler, P{\\aa}l Halvorsen, Thu Nguyen","submitted_at":"2022-05-30T14:47:27Z","abstract_excerpt":"Missing data is a commonly occurring problem in practice. Many imputation methods have been developed to fill in the missing entries. However, not all of them can scale to high-dimensional data, especially the multiple imputation techniques. Meanwhile, the data nowadays tends toward high-dimensional. Therefore, in this work, we propose Principal Component Analysis Imputation (PCAI), a simple but versatile framework based on Principal Component Analysis (PCA) to speed up the imputation process and alleviate memory issues of many available imputation techniques, without sacrificing the imputatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15150","kind":"arxiv","version":3},"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/2205.15150/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":"2205.15150","created_at":"2026-07-05T05:52:20.297414+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.15150v3","created_at":"2026-07-05T05:52:20.297414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15150","created_at":"2026-07-05T05:52:20.297414+00:00"},{"alias_kind":"pith_short_12","alias_value":"LEIKKPCH54SR","created_at":"2026-07-05T05:52:20.297414+00:00"},{"alias_kind":"pith_short_16","alias_value":"LEIKKPCH54SRQSTU","created_at":"2026-07-05T05:52:20.297414+00:00"},{"alias_kind":"pith_short_8","alias_value":"LEIKKPCH","created_at":"2026-07-05T05:52:20.297414+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/LEIKKPCH54SRQSTUVRWXJSKQIY","json":"https://pith.science/pith/LEIKKPCH54SRQSTUVRWXJSKQIY.json","graph_json":"https://pith.science/api/pith-number/LEIKKPCH54SRQSTUVRWXJSKQIY/graph.json","events_json":"https://pith.science/api/pith-number/LEIKKPCH54SRQSTUVRWXJSKQIY/events.json","paper":"https://pith.science/paper/LEIKKPCH"},"agent_actions":{"view_html":"https://pith.science/pith/LEIKKPCH54SRQSTUVRWXJSKQIY","download_json":"https://pith.science/pith/LEIKKPCH54SRQSTUVRWXJSKQIY.json","view_paper":"https://pith.science/paper/LEIKKPCH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.15150&json=true","fetch_graph":"https://pith.science/api/pith-number/LEIKKPCH54SRQSTUVRWXJSKQIY/graph.json","fetch_events":"https://pith.science/api/pith-number/LEIKKPCH54SRQSTUVRWXJSKQIY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LEIKKPCH54SRQSTUVRWXJSKQIY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LEIKKPCH54SRQSTUVRWXJSKQIY/action/storage_attestation","attest_author":"https://pith.science/pith/LEIKKPCH54SRQSTUVRWXJSKQIY/action/author_attestation","sign_citation":"https://pith.science/pith/LEIKKPCH54SRQSTUVRWXJSKQIY/action/citation_signature","submit_replication":"https://pith.science/pith/LEIKKPCH54SRQSTUVRWXJSKQIY/action/replication_record"}},"created_at":"2026-07-05T05:52:20.297414+00:00","updated_at":"2026-07-05T05:52:20.297414+00:00"}