{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BPGMG4HF2XN6AXFXPVXMMCNUQD","short_pith_number":"pith:BPGMG4HF","schema_version":"1.0","canonical_sha256":"0bccc370e5d5dbe05cb77d6ec609b480d32d089062214543d18e27fda51a2520","source":{"kind":"arxiv","id":"1909.13082","version":4},"attestation_state":"computed","paper":{"title":"Wasserstein-2 Generative Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Korotin, Alexander Safin, Arip Asadulaev, Evgeny Burnaev, Vage Egiazarian","submitted_at":"2019-09-28T12:42:12Z","abstract_excerpt":"We propose a novel end-to-end non-minimax algorithm for training optimal transport mappings for the quadratic cost (Wasserstein-2 distance). The algorithm uses input convex neural networks and a cycle-consistency regularization to approximate Wasserstein-2 distance. In contrast to popular entropic and quadratic regularizers, cycle-consistency does not introduce bias and scales well to high dimensions. From the theoretical side, we estimate the properties of the generative mapping fitted by our algorithm. From the practical side, we evaluate our algorithm on a wide range of tasks: image-to-imag"},"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":"1909.13082","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-28T12:42:12Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"14a553b4cec2adc471c110a93f7e04e0c46c9534bf07ed7efc686b944adb56f2","abstract_canon_sha256":"e16a89e3b38c2720cae3fdc60bb342077d870aba24fc3337f766cd721e4e05f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:58:29.087905Z","signature_b64":"3FQsP/vY6NMbUgbEUOxyDErKAzFfBTY25aks1oxDg2ElqnvQTfDK/5bSGdeXGOZZRmQoPBFTZLeTcY9FaOf/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bccc370e5d5dbe05cb77d6ec609b480d32d089062214543d18e27fda51a2520","last_reissued_at":"2026-07-05T01:58:29.087442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:58:29.087442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Wasserstein-2 Generative Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Korotin, Alexander Safin, Arip Asadulaev, Evgeny Burnaev, Vage Egiazarian","submitted_at":"2019-09-28T12:42:12Z","abstract_excerpt":"We propose a novel end-to-end non-minimax algorithm for training optimal transport mappings for the quadratic cost (Wasserstein-2 distance). The algorithm uses input convex neural networks and a cycle-consistency regularization to approximate Wasserstein-2 distance. In contrast to popular entropic and quadratic regularizers, cycle-consistency does not introduce bias and scales well to high dimensions. From the theoretical side, we estimate the properties of the generative mapping fitted by our algorithm. From the practical side, we evaluate our algorithm on a wide range of tasks: image-to-imag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.13082","kind":"arxiv","version":4},"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/1909.13082/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":"1909.13082","created_at":"2026-07-05T01:58:29.087515+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.13082v4","created_at":"2026-07-05T01:58:29.087515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.13082","created_at":"2026-07-05T01:58:29.087515+00:00"},{"alias_kind":"pith_short_12","alias_value":"BPGMG4HF2XN6","created_at":"2026-07-05T01:58:29.087515+00:00"},{"alias_kind":"pith_short_16","alias_value":"BPGMG4HF2XN6AXFX","created_at":"2026-07-05T01:58:29.087515+00:00"},{"alias_kind":"pith_short_8","alias_value":"BPGMG4HF","created_at":"2026-07-05T01:58:29.087515+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10792","citing_title":"Implicit Neural Optimal Transport via Fixed-Point Optimization","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05569","citing_title":"Stability of the Monge Map in Semi-Dual Optimal Transport","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05569","citing_title":"Stability of the Monge Map in Semi-Dual Optimal Transport","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10792","citing_title":"Implicit Neural Optimal Transport via Fixed-Point Optimization","ref_index":235,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05569","citing_title":"Stability of the Monge Map in Semi-Dual Optimal Transport","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21849","citing_title":"Beyond Expected Information Gain: Stable Bayesian Optimal Experimental Design with Integral Probability Metrics and Plug-and-Play Extensions","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BPGMG4HF2XN6AXFXPVXMMCNUQD","json":"https://pith.science/pith/BPGMG4HF2XN6AXFXPVXMMCNUQD.json","graph_json":"https://pith.science/api/pith-number/BPGMG4HF2XN6AXFXPVXMMCNUQD/graph.json","events_json":"https://pith.science/api/pith-number/BPGMG4HF2XN6AXFXPVXMMCNUQD/events.json","paper":"https://pith.science/paper/BPGMG4HF"},"agent_actions":{"view_html":"https://pith.science/pith/BPGMG4HF2XN6AXFXPVXMMCNUQD","download_json":"https://pith.science/pith/BPGMG4HF2XN6AXFXPVXMMCNUQD.json","view_paper":"https://pith.science/paper/BPGMG4HF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.13082&json=true","fetch_graph":"https://pith.science/api/pith-number/BPGMG4HF2XN6AXFXPVXMMCNUQD/graph.json","fetch_events":"https://pith.science/api/pith-number/BPGMG4HF2XN6AXFXPVXMMCNUQD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BPGMG4HF2XN6AXFXPVXMMCNUQD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BPGMG4HF2XN6AXFXPVXMMCNUQD/action/storage_attestation","attest_author":"https://pith.science/pith/BPGMG4HF2XN6AXFXPVXMMCNUQD/action/author_attestation","sign_citation":"https://pith.science/pith/BPGMG4HF2XN6AXFXPVXMMCNUQD/action/citation_signature","submit_replication":"https://pith.science/pith/BPGMG4HF2XN6AXFXPVXMMCNUQD/action/replication_record"}},"created_at":"2026-07-05T01:58:29.087515+00:00","updated_at":"2026-07-05T01:58:29.087515+00:00"}