{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KHQQIAEPZBXDCX5CPJ4XFMLW2I","short_pith_number":"pith:KHQQIAEP","schema_version":"1.0","canonical_sha256":"51e104008fc86e315fa27a7972b176d20f557d1dda317c22bc26d2daec8f4a07","source":{"kind":"arxiv","id":"1806.04465","version":1},"attestation_state":"computed","paper":{"title":"Gaussian mixture models with Wasserstein distance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Benoit Gaujac, David Barber, Ilya Feige","submitted_at":"2018-06-12T12:35:10Z","abstract_excerpt":"Generative models with both discrete and continuous latent variables are highly motivated by the structure of many real-world data sets. They present, however, subtleties in training often manifesting in the discrete latent being under leveraged. In this paper, we show that such models are more amenable to training when using the Optimal Transport framework of Wasserstein Autoencoders. We find our discrete latent variable to be fully leveraged by the model when trained, without any modifications to the objective function or significant fine tuning. Our model generates comparable samples to oth"},"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":"1806.04465","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-12T12:35:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a678a062c7ae6973ec5f41379226d5b5211b5324334e16bc4abe6f64f0f43fa0","abstract_canon_sha256":"9640c4aa3105dd50c6d38624aa73ec2e7b9549f88b4165c3a1eacdbd85f7399a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:35.413918Z","signature_b64":"sp69+1VQMd7rL9gJrqX1NvWnOqLwNM7NK03Wx3Olc4jvaZQaqQmPL5gQ5uMhZF1PttcC8EfYdFvj1QvRO2VWDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51e104008fc86e315fa27a7972b176d20f557d1dda317c22bc26d2daec8f4a07","last_reissued_at":"2026-05-18T00:13:35.413237Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:35.413237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gaussian mixture models with Wasserstein distance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Benoit Gaujac, David Barber, Ilya Feige","submitted_at":"2018-06-12T12:35:10Z","abstract_excerpt":"Generative models with both discrete and continuous latent variables are highly motivated by the structure of many real-world data sets. They present, however, subtleties in training often manifesting in the discrete latent being under leveraged. In this paper, we show that such models are more amenable to training when using the Optimal Transport framework of Wasserstein Autoencoders. We find our discrete latent variable to be fully leveraged by the model when trained, without any modifications to the objective function or significant fine tuning. Our model generates comparable samples to oth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.04465","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":"1806.04465","created_at":"2026-05-18T00:13:35.413373+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.04465v1","created_at":"2026-05-18T00:13:35.413373+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.04465","created_at":"2026-05-18T00:13:35.413373+00:00"},{"alias_kind":"pith_short_12","alias_value":"KHQQIAEPZBXD","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KHQQIAEPZBXDCX5C","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KHQQIAEP","created_at":"2026-05-18T12:32:33.847187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1802.03426","citing_title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KHQQIAEPZBXDCX5CPJ4XFMLW2I","json":"https://pith.science/pith/KHQQIAEPZBXDCX5CPJ4XFMLW2I.json","graph_json":"https://pith.science/api/pith-number/KHQQIAEPZBXDCX5CPJ4XFMLW2I/graph.json","events_json":"https://pith.science/api/pith-number/KHQQIAEPZBXDCX5CPJ4XFMLW2I/events.json","paper":"https://pith.science/paper/KHQQIAEP"},"agent_actions":{"view_html":"https://pith.science/pith/KHQQIAEPZBXDCX5CPJ4XFMLW2I","download_json":"https://pith.science/pith/KHQQIAEPZBXDCX5CPJ4XFMLW2I.json","view_paper":"https://pith.science/paper/KHQQIAEP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.04465&json=true","fetch_graph":"https://pith.science/api/pith-number/KHQQIAEPZBXDCX5CPJ4XFMLW2I/graph.json","fetch_events":"https://pith.science/api/pith-number/KHQQIAEPZBXDCX5CPJ4XFMLW2I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KHQQIAEPZBXDCX5CPJ4XFMLW2I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KHQQIAEPZBXDCX5CPJ4XFMLW2I/action/storage_attestation","attest_author":"https://pith.science/pith/KHQQIAEPZBXDCX5CPJ4XFMLW2I/action/author_attestation","sign_citation":"https://pith.science/pith/KHQQIAEPZBXDCX5CPJ4XFMLW2I/action/citation_signature","submit_replication":"https://pith.science/pith/KHQQIAEPZBXDCX5CPJ4XFMLW2I/action/replication_record"}},"created_at":"2026-05-18T00:13:35.413373+00:00","updated_at":"2026-05-18T00:13:35.413373+00:00"}