{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:KSM7EUV4LUAI4CHRTGR64AJUOX","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":"eca8a44caf66e4bdbd943b217f0a2a2b2f8e5604c8f79095f8f790fb252c9fb6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-21T21:23:12Z","title_canon_sha256":"8264d49848ea4edcaa859a07bc4e8a513ed57992dcebbbeb3959ea0f4887d241"},"schema_version":"1.0","source":{"id":"1906.09333","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.09333","created_at":"2026-07-05T01:30:48Z"},{"alias_kind":"arxiv_version","alias_value":"1906.09333v2","created_at":"2026-07-05T01:30:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.09333","created_at":"2026-07-05T01:30:48Z"},{"alias_kind":"pith_short_12","alias_value":"KSM7EUV4LUAI","created_at":"2026-07-05T01:30:48Z"},{"alias_kind":"pith_short_16","alias_value":"KSM7EUV4LUAI4CHR","created_at":"2026-07-05T01:30:48Z"},{"alias_kind":"pith_short_8","alias_value":"KSM7EUV4","created_at":"2026-07-05T01:30:48Z"}],"graph_snapshots":[{"event_id":"sha256:a7d0a856e77df8061d85ea7e14347bee783fffa78781033285c295cf1c022353","target":"graph","created_at":"2026-07-05T01:30:48Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1906.09333/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a semi-supervised generative model, SeGMA, which learns a joint probability distribution of data and their classes and which is implemented in a typical Wasserstein auto-encoder framework. We choose a mixture of Gaussians as a target distribution in latent space, which provides a natural splitting of data into clusters. To connect Gaussian components with correct classes, we use a small amount of labeled data and a Gaussian classifier induced by the target distribution. SeGMA is optimized efficiently due to the use of Cramer-Wold distance as a maximum mean discrepancy penalty, which","authors_text":"Bernhard C. Geiger, Jacek Tabor, Maciej Wo{\\l}czyk, Marek \\'Smieja","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-21T21:23:12Z","title":"SeGMA: Semi-Supervised Gaussian Mixture Auto-Encoder"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.09333","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:d3da1675696d9d460cea38960526dc4cd7961eb44d5915c70f56a9c7bbc78d60","target":"record","created_at":"2026-07-05T01:30:48Z","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":"eca8a44caf66e4bdbd943b217f0a2a2b2f8e5604c8f79095f8f790fb252c9fb6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-21T21:23:12Z","title_canon_sha256":"8264d49848ea4edcaa859a07bc4e8a513ed57992dcebbbeb3959ea0f4887d241"},"schema_version":"1.0","source":{"id":"1906.09333","kind":"arxiv","version":2}},"canonical_sha256":"5499f252bc5d008e08f199a3ee013475d0f96ba8c41f2f8035a9ecc4658dee84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5499f252bc5d008e08f199a3ee013475d0f96ba8c41f2f8035a9ecc4658dee84","first_computed_at":"2026-07-05T01:30:48.621307Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:30:48.621307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nnMXKPSGeTgEGDVenkZ/dWo9x+xkI+QgpgLAdFqYH0P6+koXkpcjV33o/+FPbJRcoHKrbe7t/Evz9pV2/DDNBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:30:48.621762Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.09333","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d3da1675696d9d460cea38960526dc4cd7961eb44d5915c70f56a9c7bbc78d60","sha256:a7d0a856e77df8061d85ea7e14347bee783fffa78781033285c295cf1c022353"],"state_sha256":"43cfb0185e03a909539c4266af5498ef49747b9fabad5ea1496f32d224f5a0e1"}