{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2APJDKXGPNRMQQEDYE5WBSPMEH","short_pith_number":"pith:2APJDKXG","schema_version":"1.0","canonical_sha256":"d01e91aae67b62c84083c13b60c9ec21eda25b698495c8bd20bc5054f8b16098","source":{"kind":"arxiv","id":"1909.12116","version":4},"attestation_state":"computed","paper":{"title":"Optimal Transport driven CycleGAN for Unsupervised Learning in Inverse Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV","stat.ML"],"primary_cat":"cs.CV","authors_text":"Byeongsu Sim, Chanyong Jung, Gyutaek Oh, Jeongsol Kim, Jong Chul Ye","submitted_at":"2019-09-25T11:28:49Z","abstract_excerpt":"To improve the performance of classical generative adversarial network (GAN), Wasserstein generative adversarial networks (W-GAN) was developed as a Kantorovich dual formulation of the optimal transport (OT) problem using Wasserstein-1 distance. However, it was not clear how cycleGAN-type generative models can be derived from the optimal transport theory. Here we show that a novel cycleGAN architecture can be derived as a Kantorovich dual OT formulation if a penalized least square (PLS) cost with deep learning-based inverse path penalty is used as a transportation cost. One of the most importa"},"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":"1909.12116","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-25T11:28:49Z","cross_cats_sorted":["cs.LG","eess.IV","stat.ML"],"title_canon_sha256":"0c8473461658acd880354a5bdedfc2c987dd71d107658482398b65f4a63d95a9","abstract_canon_sha256":"8ba805854e0cb3b0b479f11b7fc443daf5bed57e9c4da5d71e0f5f9aa6970c4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:31:22.019427Z","signature_b64":"BD+KFtdkiN7ZZLaiuj1jlv5MUBLsBS2iWbyriQRywAy7coI/Fche7w+/YCCesLhRwuF51Oxt5XnessQFS5asDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d01e91aae67b62c84083c13b60c9ec21eda25b698495c8bd20bc5054f8b16098","last_reissued_at":"2026-07-05T01:31:22.019008Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:31:22.019008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Transport driven CycleGAN for Unsupervised Learning in Inverse Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV","stat.ML"],"primary_cat":"cs.CV","authors_text":"Byeongsu Sim, Chanyong Jung, Gyutaek Oh, Jeongsol Kim, Jong Chul Ye","submitted_at":"2019-09-25T11:28:49Z","abstract_excerpt":"To improve the performance of classical generative adversarial network (GAN), Wasserstein generative adversarial networks (W-GAN) was developed as a Kantorovich dual formulation of the optimal transport (OT) problem using Wasserstein-1 distance. However, it was not clear how cycleGAN-type generative models can be derived from the optimal transport theory. Here we show that a novel cycleGAN architecture can be derived as a Kantorovich dual OT formulation if a penalized least square (PLS) cost with deep learning-based inverse path penalty is used as a transportation cost. One of the most importa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.12116","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/1909.12116/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":"1909.12116","created_at":"2026-07-05T01:31:22.019064+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.12116v4","created_at":"2026-07-05T01:31:22.019064+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.12116","created_at":"2026-07-05T01:31:22.019064+00:00"},{"alias_kind":"pith_short_12","alias_value":"2APJDKXGPNRM","created_at":"2026-07-05T01:31:22.019064+00:00"},{"alias_kind":"pith_short_16","alias_value":"2APJDKXGPNRMQQED","created_at":"2026-07-05T01:31:22.019064+00:00"},{"alias_kind":"pith_short_8","alias_value":"2APJDKXG","created_at":"2026-07-05T01:31:22.019064+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30230","citing_title":"A Distributionally Robust Framework for Learned Reconstructions in Inverse Problems","ref_index":123,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2APJDKXGPNRMQQEDYE5WBSPMEH","json":"https://pith.science/pith/2APJDKXGPNRMQQEDYE5WBSPMEH.json","graph_json":"https://pith.science/api/pith-number/2APJDKXGPNRMQQEDYE5WBSPMEH/graph.json","events_json":"https://pith.science/api/pith-number/2APJDKXGPNRMQQEDYE5WBSPMEH/events.json","paper":"https://pith.science/paper/2APJDKXG"},"agent_actions":{"view_html":"https://pith.science/pith/2APJDKXGPNRMQQEDYE5WBSPMEH","download_json":"https://pith.science/pith/2APJDKXGPNRMQQEDYE5WBSPMEH.json","view_paper":"https://pith.science/paper/2APJDKXG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.12116&json=true","fetch_graph":"https://pith.science/api/pith-number/2APJDKXGPNRMQQEDYE5WBSPMEH/graph.json","fetch_events":"https://pith.science/api/pith-number/2APJDKXGPNRMQQEDYE5WBSPMEH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2APJDKXGPNRMQQEDYE5WBSPMEH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2APJDKXGPNRMQQEDYE5WBSPMEH/action/storage_attestation","attest_author":"https://pith.science/pith/2APJDKXGPNRMQQEDYE5WBSPMEH/action/author_attestation","sign_citation":"https://pith.science/pith/2APJDKXGPNRMQQEDYE5WBSPMEH/action/citation_signature","submit_replication":"https://pith.science/pith/2APJDKXGPNRMQQEDYE5WBSPMEH/action/replication_record"}},"created_at":"2026-07-05T01:31:22.019064+00:00","updated_at":"2026-07-05T01:31:22.019064+00:00"}