{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:V33DCX7ICJOK3NJMI63QSFLOMX","short_pith_number":"pith:V33DCX7I","schema_version":"1.0","canonical_sha256":"aef6315fe8125cadb52c47b709156e65e14de029c3e60d94e14680a937b6e946","source":{"kind":"arxiv","id":"1907.04050","version":1},"attestation_state":"computed","paper":{"title":"k-GANs: Ensemble of Generative Models with Semi-Discrete Optimal Transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Luca Ambrogioni, Marcel van Gerven, Umut G\\\"u\\c{c}l\\\"u","submitted_at":"2019-07-09T08:57:49Z","abstract_excerpt":"Generative adversarial networks (GANs) are the state of the art in generative modeling. Unfortunately, most GAN methods are susceptible to mode collapse, meaning that they tend to capture only a subset of the modes of the true distribution. A possible way of dealing with this problem is to use an ensemble of GANs, where (ideally) each network models a single mode. In this paper, we introduce a principled method for training an ensemble of GANs using semi-discrete optimal transport theory. In our approach, each generative network models the transportation map between a point mass (Dirac measure"},"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":"1907.04050","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-07-09T08:57:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"90b7c6e14d4a200972dddc174c6bb163716780f891d2fe287cae7c48b556789c","abstract_canon_sha256":"7f5611ea843c2debfd97406fea4ea4aeb7475465b6d94919d7f728364a78e4f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:05.841208Z","signature_b64":"yhwoUMAa4RuEWM/pQQcaWHVIlY8YJIke7BT3JlR0GGhI9AiHkXt3FevCa/w/Zy9Hnwj0ajkIIK/2FQF9W9RjCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aef6315fe8125cadb52c47b709156e65e14de029c3e60d94e14680a937b6e946","last_reissued_at":"2026-05-17T23:41:05.840441Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:05.840441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"k-GANs: Ensemble of Generative Models with Semi-Discrete Optimal Transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Luca Ambrogioni, Marcel van Gerven, Umut G\\\"u\\c{c}l\\\"u","submitted_at":"2019-07-09T08:57:49Z","abstract_excerpt":"Generative adversarial networks (GANs) are the state of the art in generative modeling. Unfortunately, most GAN methods are susceptible to mode collapse, meaning that they tend to capture only a subset of the modes of the true distribution. A possible way of dealing with this problem is to use an ensemble of GANs, where (ideally) each network models a single mode. In this paper, we introduce a principled method for training an ensemble of GANs using semi-discrete optimal transport theory. In our approach, each generative network models the transportation map between a point mass (Dirac measure"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.04050","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":"1907.04050","created_at":"2026-05-17T23:41:05.840561+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.04050v1","created_at":"2026-05-17T23:41:05.840561+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.04050","created_at":"2026-05-17T23:41:05.840561+00:00"},{"alias_kind":"pith_short_12","alias_value":"V33DCX7ICJOK","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"V33DCX7ICJOK3NJM","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"V33DCX7I","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V33DCX7ICJOK3NJMI63QSFLOMX","json":"https://pith.science/pith/V33DCX7ICJOK3NJMI63QSFLOMX.json","graph_json":"https://pith.science/api/pith-number/V33DCX7ICJOK3NJMI63QSFLOMX/graph.json","events_json":"https://pith.science/api/pith-number/V33DCX7ICJOK3NJMI63QSFLOMX/events.json","paper":"https://pith.science/paper/V33DCX7I"},"agent_actions":{"view_html":"https://pith.science/pith/V33DCX7ICJOK3NJMI63QSFLOMX","download_json":"https://pith.science/pith/V33DCX7ICJOK3NJMI63QSFLOMX.json","view_paper":"https://pith.science/paper/V33DCX7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.04050&json=true","fetch_graph":"https://pith.science/api/pith-number/V33DCX7ICJOK3NJMI63QSFLOMX/graph.json","fetch_events":"https://pith.science/api/pith-number/V33DCX7ICJOK3NJMI63QSFLOMX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V33DCX7ICJOK3NJMI63QSFLOMX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V33DCX7ICJOK3NJMI63QSFLOMX/action/storage_attestation","attest_author":"https://pith.science/pith/V33DCX7ICJOK3NJMI63QSFLOMX/action/author_attestation","sign_citation":"https://pith.science/pith/V33DCX7ICJOK3NJMI63QSFLOMX/action/citation_signature","submit_replication":"https://pith.science/pith/V33DCX7ICJOK3NJMI63QSFLOMX/action/replication_record"}},"created_at":"2026-05-17T23:41:05.840561+00:00","updated_at":"2026-05-17T23:41:05.840561+00:00"}