{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6XZTDN2VAG6AVV3EVDKB6BMBPW","short_pith_number":"pith:6XZTDN2V","schema_version":"1.0","canonical_sha256":"f5f331b75501bc0ad764a8d41f05817daa6934507218942f8ef088f5eb476ebc","source":{"kind":"arxiv","id":"2006.11941","version":1},"attestation_state":"computed","paper":{"title":"VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chao Ma, Cheng Zhang, Jos\\'e Miguel Hern\\'andez-Lobato, Richard Turner, Sebastian Tschiatschek","submitted_at":"2020-06-21T23:47:32Z","abstract_excerpt":"Deep generative models often perform poorly in real-world applications due to the heterogeneity of natural data sets. Heterogeneity arises from data containing different types of features (categorical, ordinal, continuous, etc.) and features of the same type having different marginal distributions. We propose an extension of variational autoencoders (VAEs) called VAEM to handle such heterogeneous data. VAEM is a deep generative model that is trained in a two stage manner such that the first stage provides a more uniform representation of the data to the second stage, thereby sidestepping the p"},"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":"2006.11941","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-21T23:47:32Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"420794102ce06f2f48b255a171f6926afb1b75f3f2ac138b3bbcdc2712adda36","abstract_canon_sha256":"628473d463e06da8864b9c00adb9b2189b66937530276c209d2e2373c5f43005"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:11:55.057080Z","signature_b64":"iRXOOv8WenqDtCpHZTxlGG+b9S7n8yyo340oAbnMGjAUh56eSgJu96x7w7pECnvnNMjp5/grpTNu739EhlhKCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5f331b75501bc0ad764a8d41f05817daa6934507218942f8ef088f5eb476ebc","last_reissued_at":"2026-07-05T01:11:55.056708Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:11:55.056708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chao Ma, Cheng Zhang, Jos\\'e Miguel Hern\\'andez-Lobato, Richard Turner, Sebastian Tschiatschek","submitted_at":"2020-06-21T23:47:32Z","abstract_excerpt":"Deep generative models often perform poorly in real-world applications due to the heterogeneity of natural data sets. Heterogeneity arises from data containing different types of features (categorical, ordinal, continuous, etc.) and features of the same type having different marginal distributions. We propose an extension of variational autoencoders (VAEs) called VAEM to handle such heterogeneous data. VAEM is a deep generative model that is trained in a two stage manner such that the first stage provides a more uniform representation of the data to the second stage, thereby sidestepping the p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.11941","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.11941/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":"2006.11941","created_at":"2026-07-05T01:11:55.056769+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.11941v1","created_at":"2026-07-05T01:11:55.056769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.11941","created_at":"2026-07-05T01:11:55.056769+00:00"},{"alias_kind":"pith_short_12","alias_value":"6XZTDN2VAG6A","created_at":"2026-07-05T01:11:55.056769+00:00"},{"alias_kind":"pith_short_16","alias_value":"6XZTDN2VAG6AVV3E","created_at":"2026-07-05T01:11:55.056769+00:00"},{"alias_kind":"pith_short_8","alias_value":"6XZTDN2V","created_at":"2026-07-05T01:11:55.056769+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.05257","citing_title":"Extending Tabular Denoising Diffusion Probabilistic Models for Time-Series Data Generation","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6XZTDN2VAG6AVV3EVDKB6BMBPW","json":"https://pith.science/pith/6XZTDN2VAG6AVV3EVDKB6BMBPW.json","graph_json":"https://pith.science/api/pith-number/6XZTDN2VAG6AVV3EVDKB6BMBPW/graph.json","events_json":"https://pith.science/api/pith-number/6XZTDN2VAG6AVV3EVDKB6BMBPW/events.json","paper":"https://pith.science/paper/6XZTDN2V"},"agent_actions":{"view_html":"https://pith.science/pith/6XZTDN2VAG6AVV3EVDKB6BMBPW","download_json":"https://pith.science/pith/6XZTDN2VAG6AVV3EVDKB6BMBPW.json","view_paper":"https://pith.science/paper/6XZTDN2V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.11941&json=true","fetch_graph":"https://pith.science/api/pith-number/6XZTDN2VAG6AVV3EVDKB6BMBPW/graph.json","fetch_events":"https://pith.science/api/pith-number/6XZTDN2VAG6AVV3EVDKB6BMBPW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6XZTDN2VAG6AVV3EVDKB6BMBPW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6XZTDN2VAG6AVV3EVDKB6BMBPW/action/storage_attestation","attest_author":"https://pith.science/pith/6XZTDN2VAG6AVV3EVDKB6BMBPW/action/author_attestation","sign_citation":"https://pith.science/pith/6XZTDN2VAG6AVV3EVDKB6BMBPW/action/citation_signature","submit_replication":"https://pith.science/pith/6XZTDN2VAG6AVV3EVDKB6BMBPW/action/replication_record"}},"created_at":"2026-07-05T01:11:55.056769+00:00","updated_at":"2026-07-05T01:11:55.056769+00:00"}