{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UGEQWWILUFWZA3HNEWTMRRFIZP","short_pith_number":"pith:UGEQWWIL","schema_version":"1.0","canonical_sha256":"a1890b590ba16d906ced25a6c8c4a8cbd495b0c7fe4e8f9e1ebda6557b7f8c4b","source":{"kind":"arxiv","id":"1902.09599","version":1},"attestation_state":"computed","paper":{"title":"MisGAN: Learning from Incomplete Data with Generative Adversarial Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Marlin, Bo Jiang, Steven Cheng-Xian Li","submitted_at":"2019-02-25T20:24:35Z","abstract_excerpt":"Generative adversarial networks (GANs) have been shown to provide an effective way to model complex distributions and have obtained impressive results on various challenging tasks. However, typical GANs require fully-observed data during training. In this paper, we present a GAN-based framework for learning from complex, high-dimensional incomplete data. The proposed framework learns a complete data generator along with a mask generator that models the missing data distribution. We further demonstrate how to impute missing data by equipping our framework with an adversarially trained imputer. "},"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":"1902.09599","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-02-25T20:24:35Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6bfd59eea1d19597cf97acd69af559269222fbf75229bb5bdbb45a8b7808930e","abstract_canon_sha256":"e9c03fbf1984108e00df8221f390931b06201b10269d6862b401232963d4af4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:45.151462Z","signature_b64":"UrWjKTuAxTss7mg2ayhaj4m8Sz8BIuxVdBRb6Xqo6/+8J9D27qBhJVxS0G8R2ilC2vl3c4sxgjrFTRUUxUJsCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1890b590ba16d906ced25a6c8c4a8cbd495b0c7fe4e8f9e1ebda6557b7f8c4b","last_reissued_at":"2026-05-17T23:52:45.150863Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:45.150863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MisGAN: Learning from Incomplete Data with Generative Adversarial Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Marlin, Bo Jiang, Steven Cheng-Xian Li","submitted_at":"2019-02-25T20:24:35Z","abstract_excerpt":"Generative adversarial networks (GANs) have been shown to provide an effective way to model complex distributions and have obtained impressive results on various challenging tasks. However, typical GANs require fully-observed data during training. In this paper, we present a GAN-based framework for learning from complex, high-dimensional incomplete data. The proposed framework learns a complete data generator along with a mask generator that models the missing data distribution. We further demonstrate how to impute missing data by equipping our framework with an adversarially trained imputer. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.09599","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":"1902.09599","created_at":"2026-05-17T23:52:45.150952+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.09599v1","created_at":"2026-05-17T23:52:45.150952+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.09599","created_at":"2026-05-17T23:52:45.150952+00:00"},{"alias_kind":"pith_short_12","alias_value":"UGEQWWILUFWZ","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"UGEQWWILUFWZA3HN","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"UGEQWWIL","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.20098","citing_title":"Incomplete Data, Complete Dynamics: A Diffusion Approach","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01676","citing_title":"Missingness-aware Data Imputation via AI-powered Bayesian Generative Modeling","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UGEQWWILUFWZA3HNEWTMRRFIZP","json":"https://pith.science/pith/UGEQWWILUFWZA3HNEWTMRRFIZP.json","graph_json":"https://pith.science/api/pith-number/UGEQWWILUFWZA3HNEWTMRRFIZP/graph.json","events_json":"https://pith.science/api/pith-number/UGEQWWILUFWZA3HNEWTMRRFIZP/events.json","paper":"https://pith.science/paper/UGEQWWIL"},"agent_actions":{"view_html":"https://pith.science/pith/UGEQWWILUFWZA3HNEWTMRRFIZP","download_json":"https://pith.science/pith/UGEQWWILUFWZA3HNEWTMRRFIZP.json","view_paper":"https://pith.science/paper/UGEQWWIL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.09599&json=true","fetch_graph":"https://pith.science/api/pith-number/UGEQWWILUFWZA3HNEWTMRRFIZP/graph.json","fetch_events":"https://pith.science/api/pith-number/UGEQWWILUFWZA3HNEWTMRRFIZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UGEQWWILUFWZA3HNEWTMRRFIZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UGEQWWILUFWZA3HNEWTMRRFIZP/action/storage_attestation","attest_author":"https://pith.science/pith/UGEQWWILUFWZA3HNEWTMRRFIZP/action/author_attestation","sign_citation":"https://pith.science/pith/UGEQWWILUFWZA3HNEWTMRRFIZP/action/citation_signature","submit_replication":"https://pith.science/pith/UGEQWWILUFWZA3HNEWTMRRFIZP/action/replication_record"}},"created_at":"2026-05-17T23:52:45.150952+00:00","updated_at":"2026-05-17T23:52:45.150952+00:00"}