{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CQJ2CAXVPIOKAWMZODAI2KZ5PU","short_pith_number":"pith:CQJ2CAXV","schema_version":"1.0","canonical_sha256":"1413a102f57a1ca0599970c08d2b3d7d09b71d85938b012b76844e2b9e4af2c2","source":{"kind":"arxiv","id":"1902.10666","version":1},"attestation_state":"computed","paper":{"title":"Improving Missing Data Imputation with Deep Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christian A. Hammerschmidt, Radu State, Ramiro D. Camino","submitted_at":"2019-02-27T18:01:06Z","abstract_excerpt":"Datasets with missing values are very common on industry applications, and they can have a negative impact on machine learning models. Recent studies introduced solutions to the problem of imputing missing values based on deep generative models. Previous experiments with Generative Adversarial Networks and Variational Autoencoders showed interesting results in this domain, but it is not clear which method is preferable for different use cases. The goal of this work is twofold: we present a comparison between missing data imputation solutions based on deep generative models, and we propose impr"},"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":"1902.10666","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-27T18:01:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"97a883c324985792d4cfd513067290e762fa436eb35337c13dc1087cb97f28d2","abstract_canon_sha256":"f509d2aefb7edb81c4620867f6595712d25c110b1d2c9f96f603031dbc4e4801"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:30.259433Z","signature_b64":"FsJK/qt49YjU67q0om6tv4P6pXyaENllRpniIw8OzxfBbtF/atuJGyeHOwGdZSOeue+VDckBgxIWfYpZ+3f3BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1413a102f57a1ca0599970c08d2b3d7d09b71d85938b012b76844e2b9e4af2c2","last_reissued_at":"2026-05-17T23:52:30.258773Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:30.258773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Missing Data Imputation with Deep Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christian A. Hammerschmidt, Radu State, Ramiro D. Camino","submitted_at":"2019-02-27T18:01:06Z","abstract_excerpt":"Datasets with missing values are very common on industry applications, and they can have a negative impact on machine learning models. Recent studies introduced solutions to the problem of imputing missing values based on deep generative models. Previous experiments with Generative Adversarial Networks and Variational Autoencoders showed interesting results in this domain, but it is not clear which method is preferable for different use cases. The goal of this work is twofold: we present a comparison between missing data imputation solutions based on deep generative models, and we propose impr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.10666","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":""},"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":"1902.10666","created_at":"2026-05-17T23:52:30.258901+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.10666v1","created_at":"2026-05-17T23:52:30.258901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.10666","created_at":"2026-05-17T23:52:30.258901+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQJ2CAXVPIOK","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQJ2CAXVPIOKAWMZ","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQJ2CAXV","created_at":"2026-05-18T12:33:15.570797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2507.09028","citing_title":"From Classical Machine Learning to Emerging Foundation Models: Review on Multimodal Data Integration for Cancer Research","ref_index":192,"is_internal_anchor":true},{"citing_arxiv_id":"2511.04903","citing_title":"Efficacy Analysis in Clinical Trials: A Comprehensive Review of Statistical and Machine Learning Approaches","ref_index":154,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CQJ2CAXVPIOKAWMZODAI2KZ5PU","json":"https://pith.science/pith/CQJ2CAXVPIOKAWMZODAI2KZ5PU.json","graph_json":"https://pith.science/api/pith-number/CQJ2CAXVPIOKAWMZODAI2KZ5PU/graph.json","events_json":"https://pith.science/api/pith-number/CQJ2CAXVPIOKAWMZODAI2KZ5PU/events.json","paper":"https://pith.science/paper/CQJ2CAXV"},"agent_actions":{"view_html":"https://pith.science/pith/CQJ2CAXVPIOKAWMZODAI2KZ5PU","download_json":"https://pith.science/pith/CQJ2CAXVPIOKAWMZODAI2KZ5PU.json","view_paper":"https://pith.science/paper/CQJ2CAXV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.10666&json=true","fetch_graph":"https://pith.science/api/pith-number/CQJ2CAXVPIOKAWMZODAI2KZ5PU/graph.json","fetch_events":"https://pith.science/api/pith-number/CQJ2CAXVPIOKAWMZODAI2KZ5PU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQJ2CAXVPIOKAWMZODAI2KZ5PU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQJ2CAXVPIOKAWMZODAI2KZ5PU/action/storage_attestation","attest_author":"https://pith.science/pith/CQJ2CAXVPIOKAWMZODAI2KZ5PU/action/author_attestation","sign_citation":"https://pith.science/pith/CQJ2CAXVPIOKAWMZODAI2KZ5PU/action/citation_signature","submit_replication":"https://pith.science/pith/CQJ2CAXVPIOKAWMZODAI2KZ5PU/action/replication_record"}},"created_at":"2026-05-17T23:52:30.258901+00:00","updated_at":"2026-05-17T23:52:30.258901+00:00"}