{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:CFMUPKOA5M55NPSAGMIKVDICEX","short_pith_number":"pith:CFMUPKOA","canonical_record":{"source":{"id":"1812.02633","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-12-06T16:14:17Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"87008cb98ad84e0ba584be1b3fcf2b1b1bbec69b985fc69f0022989589041961","abstract_canon_sha256":"bcc5f38297c7b294cbf29194ce370f55b4e8c677c044b8a3915a011350795dd4"},"schema_version":"1.0"},"canonical_sha256":"115947a9c0eb3bd6be403310aa8d0225ebab9606868f9c79af808883a1d07a1a","source":{"kind":"arxiv","id":"1812.02633","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.02633","created_at":"2026-05-17T23:54:53Z"},{"alias_kind":"arxiv_version","alias_value":"1812.02633v2","created_at":"2026-05-17T23:54:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02633","created_at":"2026-05-17T23:54:53Z"},{"alias_kind":"pith_short_12","alias_value":"CFMUPKOA5M55","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"CFMUPKOA5M55NPSA","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"CFMUPKOA","created_at":"2026-05-18T12:32:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:CFMUPKOA5M55NPSAGMIKVDICEX","target":"record","payload":{"canonical_record":{"source":{"id":"1812.02633","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-12-06T16:14:17Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"87008cb98ad84e0ba584be1b3fcf2b1b1bbec69b985fc69f0022989589041961","abstract_canon_sha256":"bcc5f38297c7b294cbf29194ce370f55b4e8c677c044b8a3915a011350795dd4"},"schema_version":"1.0"},"canonical_sha256":"115947a9c0eb3bd6be403310aa8d0225ebab9606868f9c79af808883a1d07a1a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:53.321072Z","signature_b64":"ycsET81xy5rPH2/QQHojRiLBzpy5tlbIurDgFvfq4YYZ0jqkB5yp0AlvQWEQg8jpMTl/BDvV/Q6qTr5KBFFACQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"115947a9c0eb3bd6be403310aa8d0225ebab9606868f9c79af808883a1d07a1a","last_reissued_at":"2026-05-17T23:54:53.320572Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:53.320572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.02633","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:54:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1xJ2eIEoTdXvjShm1e0rNPtthktYGv5KKuyothM3BMVKt2OPi4L7A2auYaSTbGqQsx6Xvqotkb+oR3eEPcCRDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T13:45:37.465400Z"},"content_sha256":"9cf8760e4c0b88a0212d72753b5afb15d1bfe563cbe06f48b34d6fe917c2242a","schema_version":"1.0","event_id":"sha256:9cf8760e4c0b88a0212d72753b5afb15d1bfe563cbe06f48b34d6fe917c2242a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:CFMUPKOA5M55NPSAGMIKVDICEX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MIWAE: Deep Generative Modelling and Imputation of Incomplete Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Jes Frellsen, Pierre-Alexandre Mattei","submitted_at":"2018-12-06T16:14:17Z","abstract_excerpt":"We consider the problem of handling missing data with deep latent variable models (DLVMs). First, we present a simple technique to train DLVMs when the training set contains missing-at-random data. Our approach, called MIWAE, is based on the importance-weighted autoencoder (IWAE), and maximises a potentially tight lower bound of the log-likelihood of the observed data. Compared to the original IWAE, our algorithm does not induce any additional computational overhead due to the missing data. We also develop Monte Carlo techniques for single and multiple imputation using a DLVM trained on an inc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02633","kind":"arxiv","version":2},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:54:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+dJAbY9XUCQEz1F6i34iNc8/sSpqfu5UF49OTMD0X5L1N6v59zM9qGc70oqHmFL87/R7sFmKgGZpm2TBIC21Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T13:45:37.466008Z"},"content_sha256":"311e224ff8481e7704bc4027020b5bb4ede4da8ec501327b8af49e5cd24da251","schema_version":"1.0","event_id":"sha256:311e224ff8481e7704bc4027020b5bb4ede4da8ec501327b8af49e5cd24da251"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CFMUPKOA5M55NPSAGMIKVDICEX/bundle.json","state_url":"https://pith.science/pith/CFMUPKOA5M55NPSAGMIKVDICEX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CFMUPKOA5M55NPSAGMIKVDICEX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-01T13:45:37Z","links":{"resolver":"https://pith.science/pith/CFMUPKOA5M55NPSAGMIKVDICEX","bundle":"https://pith.science/pith/CFMUPKOA5M55NPSAGMIKVDICEX/bundle.json","state":"https://pith.science/pith/CFMUPKOA5M55NPSAGMIKVDICEX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CFMUPKOA5M55NPSAGMIKVDICEX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:CFMUPKOA5M55NPSAGMIKVDICEX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bcc5f38297c7b294cbf29194ce370f55b4e8c677c044b8a3915a011350795dd4","cross_cats_sorted":["cs.LG","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-12-06T16:14:17Z","title_canon_sha256":"87008cb98ad84e0ba584be1b3fcf2b1b1bbec69b985fc69f0022989589041961"},"schema_version":"1.0","source":{"id":"1812.02633","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.02633","created_at":"2026-05-17T23:54:53Z"},{"alias_kind":"arxiv_version","alias_value":"1812.02633v2","created_at":"2026-05-17T23:54:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02633","created_at":"2026-05-17T23:54:53Z"},{"alias_kind":"pith_short_12","alias_value":"CFMUPKOA5M55","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"CFMUPKOA5M55NPSA","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"CFMUPKOA","created_at":"2026-05-18T12:32:16Z"}],"graph_snapshots":[{"event_id":"sha256:311e224ff8481e7704bc4027020b5bb4ede4da8ec501327b8af49e5cd24da251","target":"graph","created_at":"2026-05-17T23:54:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We consider the problem of handling missing data with deep latent variable models (DLVMs). First, we present a simple technique to train DLVMs when the training set contains missing-at-random data. Our approach, called MIWAE, is based on the importance-weighted autoencoder (IWAE), and maximises a potentially tight lower bound of the log-likelihood of the observed data. Compared to the original IWAE, our algorithm does not induce any additional computational overhead due to the missing data. We also develop Monte Carlo techniques for single and multiple imputation using a DLVM trained on an inc","authors_text":"Jes Frellsen, Pierre-Alexandre Mattei","cross_cats":["cs.LG","stat.ME"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-12-06T16:14:17Z","title":"MIWAE: Deep Generative Modelling and Imputation of Incomplete Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02633","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9cf8760e4c0b88a0212d72753b5afb15d1bfe563cbe06f48b34d6fe917c2242a","target":"record","created_at":"2026-05-17T23:54:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bcc5f38297c7b294cbf29194ce370f55b4e8c677c044b8a3915a011350795dd4","cross_cats_sorted":["cs.LG","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-12-06T16:14:17Z","title_canon_sha256":"87008cb98ad84e0ba584be1b3fcf2b1b1bbec69b985fc69f0022989589041961"},"schema_version":"1.0","source":{"id":"1812.02633","kind":"arxiv","version":2}},"canonical_sha256":"115947a9c0eb3bd6be403310aa8d0225ebab9606868f9c79af808883a1d07a1a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"115947a9c0eb3bd6be403310aa8d0225ebab9606868f9c79af808883a1d07a1a","first_computed_at":"2026-05-17T23:54:53.320572Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:53.320572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ycsET81xy5rPH2/QQHojRiLBzpy5tlbIurDgFvfq4YYZ0jqkB5yp0AlvQWEQg8jpMTl/BDvV/Q6qTr5KBFFACQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:53.321072Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.02633","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9cf8760e4c0b88a0212d72753b5afb15d1bfe563cbe06f48b34d6fe917c2242a","sha256:311e224ff8481e7704bc4027020b5bb4ede4da8ec501327b8af49e5cd24da251"],"state_sha256":"ac431f935fd5817b8a3c4451664af376cf3cf2768ce7ef3859eec9133d2a5f40"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k3oMqqN5MxoAE61t3zc3CwWx1RV7aLw7X9fXDHWxuVbqOOUsnZJqlmkdMxMnu8Fcw5c+QsSJ0tRJYzhqaXYvCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T13:45:37.469050Z","bundle_sha256":"134f7f32711f4d8b1834151474961511920fadafaa9370e82a21417fa84d54a5"}}