{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:H2AQP32DS2KMVFJD5PU3UQIHZA","short_pith_number":"pith:H2AQP32D","schema_version":"1.0","canonical_sha256":"3e8107ef439694ca9523ebe9ba4107c818926577dfc2bb7ae28f820e60aeb3b8","source":{"kind":"arxiv","id":"2205.15269","version":2},"attestation_state":"computed","paper":{"title":"Kernel Neural Optimal Transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Korotin, Daniil Selikhanovych, Evgeny Burnaev","submitted_at":"2022-05-30T17:26:06Z","abstract_excerpt":"We study the Neural Optimal Transport (NOT) algorithm which uses the general optimal transport formulation and learns stochastic transport plans. We show that NOT with the weak quadratic cost might learn fake plans which are not optimal. To resolve this issue, we introduce kernel weak quadratic costs. We show that they provide improved theoretical guarantees and practical performance. We test NOT with kernel costs on the unpaired image-to-image translation task."},"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":"2205.15269","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-30T17:26:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6fc239ba8b7ca520c6b5a8e81fb0501815d12239f119985b52799a40808f69bb","abstract_canon_sha256":"ef9367a7f78406729ca33103f6b03b7788b890d4fdca8681d9e4a0d5883a83fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:02.883953Z","signature_b64":"tEWxCuctRmWQEWjNkfNdssiwGiAt98rBxw38SQhhmgjp+gqmuMAOa5Vise8nW9LuszjOwkmWhuYzHHIyp/sXAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e8107ef439694ca9523ebe9ba4107c818926577dfc2bb7ae28f820e60aeb3b8","last_reissued_at":"2026-07-05T05:47:02.883401Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:02.883401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kernel Neural Optimal Transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Korotin, Daniil Selikhanovych, Evgeny Burnaev","submitted_at":"2022-05-30T17:26:06Z","abstract_excerpt":"We study the Neural Optimal Transport (NOT) algorithm which uses the general optimal transport formulation and learns stochastic transport plans. We show that NOT with the weak quadratic cost might learn fake plans which are not optimal. To resolve this issue, we introduce kernel weak quadratic costs. We show that they provide improved theoretical guarantees and practical performance. We test NOT with kernel costs on the unpaired image-to-image translation task."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15269","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/2205.15269/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":"2205.15269","created_at":"2026-07-05T05:47:02.883460+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.15269v2","created_at":"2026-07-05T05:47:02.883460+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15269","created_at":"2026-07-05T05:47:02.883460+00:00"},{"alias_kind":"pith_short_12","alias_value":"H2AQP32DS2KM","created_at":"2026-07-05T05:47:02.883460+00:00"},{"alias_kind":"pith_short_16","alias_value":"H2AQP32DS2KMVFJD","created_at":"2026-07-05T05:47:02.883460+00:00"},{"alias_kind":"pith_short_8","alias_value":"H2AQP32D","created_at":"2026-07-05T05:47:02.883460+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27678","citing_title":"Two-Stage Cross-Domain Cervical Abnormality Screening with Cytopathological Image Synthesis and Knowledge Distillation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10792","citing_title":"Implicit Neural Optimal Transport via Fixed-Point Optimization","ref_index":148,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H2AQP32DS2KMVFJD5PU3UQIHZA","json":"https://pith.science/pith/H2AQP32DS2KMVFJD5PU3UQIHZA.json","graph_json":"https://pith.science/api/pith-number/H2AQP32DS2KMVFJD5PU3UQIHZA/graph.json","events_json":"https://pith.science/api/pith-number/H2AQP32DS2KMVFJD5PU3UQIHZA/events.json","paper":"https://pith.science/paper/H2AQP32D"},"agent_actions":{"view_html":"https://pith.science/pith/H2AQP32DS2KMVFJD5PU3UQIHZA","download_json":"https://pith.science/pith/H2AQP32DS2KMVFJD5PU3UQIHZA.json","view_paper":"https://pith.science/paper/H2AQP32D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.15269&json=true","fetch_graph":"https://pith.science/api/pith-number/H2AQP32DS2KMVFJD5PU3UQIHZA/graph.json","fetch_events":"https://pith.science/api/pith-number/H2AQP32DS2KMVFJD5PU3UQIHZA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H2AQP32DS2KMVFJD5PU3UQIHZA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H2AQP32DS2KMVFJD5PU3UQIHZA/action/storage_attestation","attest_author":"https://pith.science/pith/H2AQP32DS2KMVFJD5PU3UQIHZA/action/author_attestation","sign_citation":"https://pith.science/pith/H2AQP32DS2KMVFJD5PU3UQIHZA/action/citation_signature","submit_replication":"https://pith.science/pith/H2AQP32DS2KMVFJD5PU3UQIHZA/action/replication_record"}},"created_at":"2026-07-05T05:47:02.883460+00:00","updated_at":"2026-07-05T05:47:02.883460+00:00"}