{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XLZQLNDABPFSP5UI6CJL25ETXC","short_pith_number":"pith:XLZQLNDA","schema_version":"1.0","canonical_sha256":"baf305b4600bcb27f688f092bd7493b8a01fac266ab39b3e378559a723bb011d","source":{"kind":"arxiv","id":"2103.09316","version":3},"attestation_state":"computed","paper":{"title":"Are deep learning models superior for missing data imputation in large surveys? Evidence from an empirical comparison","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fan Li, Jason Poulos, Olanrewaju Akande, Zhenhua Wang","submitted_at":"2021-03-14T16:24:04Z","abstract_excerpt":"Multiple imputation (MI) is a popular approach for dealing with missing data arising from non-response in sample surveys. Multiple imputation by chained equations (MICE) is one of the most widely used MI algorithms for multivariate data, but it lacks theoretical foundation and is computationally intensive. Recently, missing data imputation methods based on deep learning models have been developed with encouraging results in small studies. However, there has been limited research on evaluating their performance in realistic settings compared to MICE, particularly in big surveys. We conduct exte"},"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":"2103.09316","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-14T16:24:04Z","cross_cats_sorted":["stat.AP","stat.ML"],"title_canon_sha256":"176c920b0e9a37c5cf54a5f3ba4ef7e817bf9b64645afbdf2eccab7f41ac7597","abstract_canon_sha256":"7f188511943a42dfafac10b309d6444c4c46f98032c1e6c41e5de76f5300269f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:29.497585Z","signature_b64":"TpjxnMRwlpDPIeOHPl5xRM2ZZTrZEcrDVwuDHDKFfqMDUpXSUKQZzxKhM1+zLhI25J03VbyVa7et4Pkj/+JyAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"baf305b4600bcb27f688f092bd7493b8a01fac266ab39b3e378559a723bb011d","last_reissued_at":"2026-07-05T04:06:29.497190Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:29.497190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are deep learning models superior for missing data imputation in large surveys? Evidence from an empirical comparison","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fan Li, Jason Poulos, Olanrewaju Akande, Zhenhua Wang","submitted_at":"2021-03-14T16:24:04Z","abstract_excerpt":"Multiple imputation (MI) is a popular approach for dealing with missing data arising from non-response in sample surveys. Multiple imputation by chained equations (MICE) is one of the most widely used MI algorithms for multivariate data, but it lacks theoretical foundation and is computationally intensive. Recently, missing data imputation methods based on deep learning models have been developed with encouraging results in small studies. However, there has been limited research on evaluating their performance in realistic settings compared to MICE, particularly in big surveys. We conduct exte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.09316","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/2103.09316/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":"2103.09316","created_at":"2026-07-05T04:06:29.497254+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.09316v3","created_at":"2026-07-05T04:06:29.497254+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.09316","created_at":"2026-07-05T04:06:29.497254+00:00"},{"alias_kind":"pith_short_12","alias_value":"XLZQLNDABPFS","created_at":"2026-07-05T04:06:29.497254+00:00"},{"alias_kind":"pith_short_16","alias_value":"XLZQLNDABPFSP5UI","created_at":"2026-07-05T04:06:29.497254+00:00"},{"alias_kind":"pith_short_8","alias_value":"XLZQLNDA","created_at":"2026-07-05T04:06:29.497254+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07767","citing_title":"Distributionally Faithful Imputation via Positive Semi-Definite Kernel Density Estimation","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XLZQLNDABPFSP5UI6CJL25ETXC","json":"https://pith.science/pith/XLZQLNDABPFSP5UI6CJL25ETXC.json","graph_json":"https://pith.science/api/pith-number/XLZQLNDABPFSP5UI6CJL25ETXC/graph.json","events_json":"https://pith.science/api/pith-number/XLZQLNDABPFSP5UI6CJL25ETXC/events.json","paper":"https://pith.science/paper/XLZQLNDA"},"agent_actions":{"view_html":"https://pith.science/pith/XLZQLNDABPFSP5UI6CJL25ETXC","download_json":"https://pith.science/pith/XLZQLNDABPFSP5UI6CJL25ETXC.json","view_paper":"https://pith.science/paper/XLZQLNDA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.09316&json=true","fetch_graph":"https://pith.science/api/pith-number/XLZQLNDABPFSP5UI6CJL25ETXC/graph.json","fetch_events":"https://pith.science/api/pith-number/XLZQLNDABPFSP5UI6CJL25ETXC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XLZQLNDABPFSP5UI6CJL25ETXC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XLZQLNDABPFSP5UI6CJL25ETXC/action/storage_attestation","attest_author":"https://pith.science/pith/XLZQLNDABPFSP5UI6CJL25ETXC/action/author_attestation","sign_citation":"https://pith.science/pith/XLZQLNDABPFSP5UI6CJL25ETXC/action/citation_signature","submit_replication":"https://pith.science/pith/XLZQLNDABPFSP5UI6CJL25ETXC/action/replication_record"}},"created_at":"2026-07-05T04:06:29.497254+00:00","updated_at":"2026-07-05T04:06:29.497254+00:00"}