{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:G5IW5KLCIY6HJTFM67ULFPRG3U","short_pith_number":"pith:G5IW5KLC","schema_version":"1.0","canonical_sha256":"37516ea962463c74ccacf7e8b2be26dd111514348aa2d65ca52bb3f639646d7f","source":{"kind":"arxiv","id":"2010.05862","version":1},"attestation_state":"computed","paper":{"title":"Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Rama Chellappa, Soheil Feizi, Yogesh Balaji","submitted_at":"2020-10-12T17:13:40Z","abstract_excerpt":"Optimal Transport (OT) distances such as Wasserstein have been used in several areas such as GANs and domain adaptation. OT, however, is very sensitive to outliers (samples with large noise) in the data since in its objective function, every sample, including outliers, is weighed similarly due to the marginal constraints. To remedy this issue, robust formulations of OT with unbalanced marginal constraints have previously been proposed. However, employing these methods in deep learning problems such as GANs and domain adaptation is challenging due to the instability of their dual optimization s"},"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":"2010.05862","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-10-12T17:13:40Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"58d2bf97929de0c1b10ab64e729ebe195d56b510f1127a16829faf8748f4318e","abstract_canon_sha256":"065ace4ba544158ebf8521e89a41b0783add76d7bccf81e9ed93ce8f9015f6e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:42:11.186686Z","signature_b64":"oGffRjdVhYduEoc6GWxzKIGj3mT9TA2G1fG/LtvnshFrYIT0n34jACy/2MfQDBDPcSJHCsrcVmb85s6DT7OoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37516ea962463c74ccacf7e8b2be26dd111514348aa2d65ca52bb3f639646d7f","last_reissued_at":"2026-07-05T01:42:11.186206Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:42:11.186206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Rama Chellappa, Soheil Feizi, Yogesh Balaji","submitted_at":"2020-10-12T17:13:40Z","abstract_excerpt":"Optimal Transport (OT) distances such as Wasserstein have been used in several areas such as GANs and domain adaptation. OT, however, is very sensitive to outliers (samples with large noise) in the data since in its objective function, every sample, including outliers, is weighed similarly due to the marginal constraints. To remedy this issue, robust formulations of OT with unbalanced marginal constraints have previously been proposed. However, employing these methods in deep learning problems such as GANs and domain adaptation is challenging due to the instability of their dual optimization s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.05862","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2010.05862/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":"2010.05862","created_at":"2026-07-05T01:42:11.186266+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.05862v1","created_at":"2026-07-05T01:42:11.186266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.05862","created_at":"2026-07-05T01:42:11.186266+00:00"},{"alias_kind":"pith_short_12","alias_value":"G5IW5KLCIY6H","created_at":"2026-07-05T01:42:11.186266+00:00"},{"alias_kind":"pith_short_16","alias_value":"G5IW5KLCIY6HJTFM","created_at":"2026-07-05T01:42:11.186266+00:00"},{"alias_kind":"pith_short_8","alias_value":"G5IW5KLC","created_at":"2026-07-05T01:42:11.186266+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09471","citing_title":"The Statistical Cost of Adaptation in Multi-Source Transfer Learning","ref_index":271,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G5IW5KLCIY6HJTFM67ULFPRG3U","json":"https://pith.science/pith/G5IW5KLCIY6HJTFM67ULFPRG3U.json","graph_json":"https://pith.science/api/pith-number/G5IW5KLCIY6HJTFM67ULFPRG3U/graph.json","events_json":"https://pith.science/api/pith-number/G5IW5KLCIY6HJTFM67ULFPRG3U/events.json","paper":"https://pith.science/paper/G5IW5KLC"},"agent_actions":{"view_html":"https://pith.science/pith/G5IW5KLCIY6HJTFM67ULFPRG3U","download_json":"https://pith.science/pith/G5IW5KLCIY6HJTFM67ULFPRG3U.json","view_paper":"https://pith.science/paper/G5IW5KLC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.05862&json=true","fetch_graph":"https://pith.science/api/pith-number/G5IW5KLCIY6HJTFM67ULFPRG3U/graph.json","fetch_events":"https://pith.science/api/pith-number/G5IW5KLCIY6HJTFM67ULFPRG3U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G5IW5KLCIY6HJTFM67ULFPRG3U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G5IW5KLCIY6HJTFM67ULFPRG3U/action/storage_attestation","attest_author":"https://pith.science/pith/G5IW5KLCIY6HJTFM67ULFPRG3U/action/author_attestation","sign_citation":"https://pith.science/pith/G5IW5KLCIY6HJTFM67ULFPRG3U/action/citation_signature","submit_replication":"https://pith.science/pith/G5IW5KLCIY6HJTFM67ULFPRG3U/action/replication_record"}},"created_at":"2026-07-05T01:42:11.186266+00:00","updated_at":"2026-07-05T01:42:11.186266+00:00"}