{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BVG4CROWGEHJJ3UXHVQXEHNHAD","short_pith_number":"pith:BVG4CROW","schema_version":"1.0","canonical_sha256":"0d4dc145d6310e94ee973d61721da700fbcfeb6abfdde172554c5c08724ccfc8","source":{"kind":"arxiv","id":"2110.02999","version":2},"attestation_state":"computed","paper":{"title":"Generative Modeling with Optimal Transport Maps","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Korotin, Evgeny Burnaev, Litu Rout","submitted_at":"2021-10-06T18:17:02Z","abstract_excerpt":"With the discovery of Wasserstein GANs, Optimal Transport (OT) has become a powerful tool for large-scale generative modeling tasks. In these tasks, OT cost is typically used as the loss for training GANs. In contrast to this approach, we show that the OT map itself can be used as a generative model, providing comparable performance. Previous analogous approaches consider OT maps as generative models only in the latent spaces due to their poor performance in the original high-dimensional ambient space. In contrast, we apply OT maps directly in the ambient space, e.g., a space of high-dimension"},"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":"2110.02999","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-06T18:17:02Z","cross_cats_sorted":[],"title_canon_sha256":"ce9e6ab2ab92475c32064ab2eb7c2083da7e79f6e5a573916c6b1763f69a2cbf","abstract_canon_sha256":"02dfb960042b20c0d5b1008257670b4ceeccf17f12a1cebb11ad07acee26347b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:02:19.859102Z","signature_b64":"yvVJtSB0yum2uKn9GJOX5Q8cX0MSAP5+mHLXLwIuKDztis17fJgqbzxa+TvLY7pBo7o49SjOazNVkMYTW2zjAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d4dc145d6310e94ee973d61721da700fbcfeb6abfdde172554c5c08724ccfc8","last_reissued_at":"2026-07-05T04:02:19.858483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:02:19.858483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Modeling with Optimal Transport Maps","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Korotin, Evgeny Burnaev, Litu Rout","submitted_at":"2021-10-06T18:17:02Z","abstract_excerpt":"With the discovery of Wasserstein GANs, Optimal Transport (OT) has become a powerful tool for large-scale generative modeling tasks. In these tasks, OT cost is typically used as the loss for training GANs. In contrast to this approach, we show that the OT map itself can be used as a generative model, providing comparable performance. Previous analogous approaches consider OT maps as generative models only in the latent spaces due to their poor performance in the original high-dimensional ambient space. In contrast, we apply OT maps directly in the ambient space, e.g., a space of high-dimension"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.02999","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2110.02999/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2110.02999","created_at":"2026-07-05T04:02:19.858570+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.02999v2","created_at":"2026-07-05T04:02:19.858570+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.02999","created_at":"2026-07-05T04:02:19.858570+00:00"},{"alias_kind":"pith_short_12","alias_value":"BVG4CROWGEHJ","created_at":"2026-07-05T04:02:19.858570+00:00"},{"alias_kind":"pith_short_16","alias_value":"BVG4CROWGEHJJ3UX","created_at":"2026-07-05T04:02:19.858570+00:00"},{"alias_kind":"pith_short_8","alias_value":"BVG4CROW","created_at":"2026-07-05T04:02:19.858570+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05569","citing_title":"Stability of the Monge Map in Semi-Dual Optimal Transport","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05569","citing_title":"Stability of the Monge Map in Semi-Dual Optimal Transport","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10792","citing_title":"Implicit Neural Optimal Transport via Fixed-Point Optimization","ref_index":177,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05569","citing_title":"Stability of the Monge Map in Semi-Dual Optimal Transport","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2209.03003","citing_title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BVG4CROWGEHJJ3UXHVQXEHNHAD","json":"https://pith.science/pith/BVG4CROWGEHJJ3UXHVQXEHNHAD.json","graph_json":"https://pith.science/api/pith-number/BVG4CROWGEHJJ3UXHVQXEHNHAD/graph.json","events_json":"https://pith.science/api/pith-number/BVG4CROWGEHJJ3UXHVQXEHNHAD/events.json","paper":"https://pith.science/paper/BVG4CROW"},"agent_actions":{"view_html":"https://pith.science/pith/BVG4CROWGEHJJ3UXHVQXEHNHAD","download_json":"https://pith.science/pith/BVG4CROWGEHJJ3UXHVQXEHNHAD.json","view_paper":"https://pith.science/paper/BVG4CROW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.02999&json=true","fetch_graph":"https://pith.science/api/pith-number/BVG4CROWGEHJJ3UXHVQXEHNHAD/graph.json","fetch_events":"https://pith.science/api/pith-number/BVG4CROWGEHJJ3UXHVQXEHNHAD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BVG4CROWGEHJJ3UXHVQXEHNHAD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BVG4CROWGEHJJ3UXHVQXEHNHAD/action/storage_attestation","attest_author":"https://pith.science/pith/BVG4CROWGEHJJ3UXHVQXEHNHAD/action/author_attestation","sign_citation":"https://pith.science/pith/BVG4CROWGEHJJ3UXHVQXEHNHAD/action/citation_signature","submit_replication":"https://pith.science/pith/BVG4CROWGEHJJ3UXHVQXEHNHAD/action/replication_record"}},"created_at":"2026-07-05T04:02:19.858570+00:00","updated_at":"2026-07-05T04:02:19.858570+00:00"}