{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:Y5TPOOYW3XMYGLSKFMQKKGGT2P","short_pith_number":"pith:Y5TPOOYW","schema_version":"1.0","canonical_sha256":"c766f73b16ddd9832e4a2b20a518d3d3d6cff8cd2fe49456692bac1109572c67","source":{"kind":"arxiv","id":"1803.05573","version":1},"attestation_state":"computed","paper":{"title":"Improving GANs Using Optimal Transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alec Radford, Dimitris Metaxas, Han Zhang, Tim Salimans","submitted_at":"2018-03-15T02:34:46Z","abstract_excerpt":"We present Optimal Transport GAN (OT-GAN), a variant of generative adversarial nets minimizing a new metric measuring the distance between the generator distribution and the data distribution. This metric, which we call mini-batch energy distance, combines optimal transport in primal form with an energy distance defined in an adversarially learned feature space, resulting in a highly discriminative distance function with unbiased mini-batch gradients. Experimentally we show OT-GAN to be highly stable when trained with large mini-batches, and we present state-of-the-art results on several popul"},"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":"1803.05573","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-15T02:34:46Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"97ac7ba7b0d02c48e62b57250349661f07663c9e1d5ea97f0a0143d1686e35bb","abstract_canon_sha256":"652463e350221f545cb26b5a12e401ab1690b0a9216d947018fac4bfac6ecad2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:55.117075Z","signature_b64":"7TWZ5+bnbmJdWmYzcIYL9D2jHMB3cEV+ZFCPBGO8eb/apMr5SutGH4Gggd86Qauqri3vYz/iMWF+olO7UN8WBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c766f73b16ddd9832e4a2b20a518d3d3d6cff8cd2fe49456692bac1109572c67","last_reissued_at":"2026-05-18T00:20:55.116716Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:55.116716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving GANs Using Optimal Transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alec Radford, Dimitris Metaxas, Han Zhang, Tim Salimans","submitted_at":"2018-03-15T02:34:46Z","abstract_excerpt":"We present Optimal Transport GAN (OT-GAN), a variant of generative adversarial nets minimizing a new metric measuring the distance between the generator distribution and the data distribution. This metric, which we call mini-batch energy distance, combines optimal transport in primal form with an energy distance defined in an adversarially learned feature space, resulting in a highly discriminative distance function with unbiased mini-batch gradients. Experimentally we show OT-GAN to be highly stable when trained with large mini-batches, and we present state-of-the-art results on several popul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.05573","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":"1803.05573","created_at":"2026-05-18T00:20:55.116778+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.05573v1","created_at":"2026-05-18T00:20:55.116778+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.05573","created_at":"2026-05-18T00:20:55.116778+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y5TPOOYW3XMY","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y5TPOOYW3XMYGLSK","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y5TPOOYW","created_at":"2026-05-18T12:33:04.347982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.09691","citing_title":"Adversarial Computation of Optimal Transport Maps","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2404.15261","citing_title":"Resistance Distance and Linearized Optimal Transport on Graphs","ref_index":69,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y5TPOOYW3XMYGLSKFMQKKGGT2P","json":"https://pith.science/pith/Y5TPOOYW3XMYGLSKFMQKKGGT2P.json","graph_json":"https://pith.science/api/pith-number/Y5TPOOYW3XMYGLSKFMQKKGGT2P/graph.json","events_json":"https://pith.science/api/pith-number/Y5TPOOYW3XMYGLSKFMQKKGGT2P/events.json","paper":"https://pith.science/paper/Y5TPOOYW"},"agent_actions":{"view_html":"https://pith.science/pith/Y5TPOOYW3XMYGLSKFMQKKGGT2P","download_json":"https://pith.science/pith/Y5TPOOYW3XMYGLSKFMQKKGGT2P.json","view_paper":"https://pith.science/paper/Y5TPOOYW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.05573&json=true","fetch_graph":"https://pith.science/api/pith-number/Y5TPOOYW3XMYGLSKFMQKKGGT2P/graph.json","fetch_events":"https://pith.science/api/pith-number/Y5TPOOYW3XMYGLSKFMQKKGGT2P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y5TPOOYW3XMYGLSKFMQKKGGT2P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y5TPOOYW3XMYGLSKFMQKKGGT2P/action/storage_attestation","attest_author":"https://pith.science/pith/Y5TPOOYW3XMYGLSKFMQKKGGT2P/action/author_attestation","sign_citation":"https://pith.science/pith/Y5TPOOYW3XMYGLSKFMQKKGGT2P/action/citation_signature","submit_replication":"https://pith.science/pith/Y5TPOOYW3XMYGLSKFMQKKGGT2P/action/replication_record"}},"created_at":"2026-05-18T00:20:55.116778+00:00","updated_at":"2026-05-18T00:20:55.116778+00:00"}