{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QQI5UXYY2OCIZ7S7A4FUCMVKFX","short_pith_number":"pith:QQI5UXYY","schema_version":"1.0","canonical_sha256":"8411da5f18d3848cfe5f070b4132aa2df9aaca5cba5b2ac481aea633d078aa08","source":{"kind":"arxiv","id":"1904.03936","version":3},"attestation_state":"computed","paper":{"title":"Wasserstein Adversarial Regularization (WAR) on label noise","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bharath Bhushan Damodaran, Devis Tuia, Kilian Fatras, Nicolas Courty, R\\'emi Flamary, Sylvain Lobry","submitted_at":"2019-04-08T10:28:12Z","abstract_excerpt":"Noisy labels often occur in vision datasets, especially when they are obtained from crowdsourcing or Web scraping. We propose a new regularization method, which enables learning robust classifiers in presence of noisy data. To achieve this goal, we propose a new adversarial regularization scheme based on the Wasserstein distance. Using this distance allows taking into account specific relations between classes by leveraging the geometric properties of the labels space. Our Wasserstein Adversarial Regularization (WAR) encodes a selective regularization, which promotes smoothness of the classifi"},"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":"1904.03936","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-04-08T10:28:12Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"d2002c56297212c213ea2cbfe2f2e39b883ad6fed86579fe57ab201fb3d036b3","abstract_canon_sha256":"2790f281e3f1376cb55df1386ecc099aae1ef729d89cf86c3d7f225fae7016eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:55.840665Z","signature_b64":"Vau0ko/Ih2m5xfJ4MR/36SsWMRokJHyV/hplZgX2ngGYRqlcJH1VueTrnYjwq2NGZBWUPDGmgjTxiKJsYZ/3Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8411da5f18d3848cfe5f070b4132aa2df9aaca5cba5b2ac481aea633d078aa08","last_reissued_at":"2026-07-05T02:52:55.840227Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:55.840227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Wasserstein Adversarial Regularization (WAR) on label noise","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bharath Bhushan Damodaran, Devis Tuia, Kilian Fatras, Nicolas Courty, R\\'emi Flamary, Sylvain Lobry","submitted_at":"2019-04-08T10:28:12Z","abstract_excerpt":"Noisy labels often occur in vision datasets, especially when they are obtained from crowdsourcing or Web scraping. We propose a new regularization method, which enables learning robust classifiers in presence of noisy data. To achieve this goal, we propose a new adversarial regularization scheme based on the Wasserstein distance. Using this distance allows taking into account specific relations between classes by leveraging the geometric properties of the labels space. Our Wasserstein Adversarial Regularization (WAR) encodes a selective regularization, which promotes smoothness of the classifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03936","kind":"arxiv","version":3},"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/1904.03936/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":"1904.03936","created_at":"2026-07-05T02:52:55.840282+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.03936v3","created_at":"2026-07-05T02:52:55.840282+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03936","created_at":"2026-07-05T02:52:55.840282+00:00"},{"alias_kind":"pith_short_12","alias_value":"QQI5UXYY2OCI","created_at":"2026-07-05T02:52:55.840282+00:00"},{"alias_kind":"pith_short_16","alias_value":"QQI5UXYY2OCIZ7S7","created_at":"2026-07-05T02:52:55.840282+00:00"},{"alias_kind":"pith_short_8","alias_value":"QQI5UXYY","created_at":"2026-07-05T02:52:55.840282+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QQI5UXYY2OCIZ7S7A4FUCMVKFX","json":"https://pith.science/pith/QQI5UXYY2OCIZ7S7A4FUCMVKFX.json","graph_json":"https://pith.science/api/pith-number/QQI5UXYY2OCIZ7S7A4FUCMVKFX/graph.json","events_json":"https://pith.science/api/pith-number/QQI5UXYY2OCIZ7S7A4FUCMVKFX/events.json","paper":"https://pith.science/paper/QQI5UXYY"},"agent_actions":{"view_html":"https://pith.science/pith/QQI5UXYY2OCIZ7S7A4FUCMVKFX","download_json":"https://pith.science/pith/QQI5UXYY2OCIZ7S7A4FUCMVKFX.json","view_paper":"https://pith.science/paper/QQI5UXYY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.03936&json=true","fetch_graph":"https://pith.science/api/pith-number/QQI5UXYY2OCIZ7S7A4FUCMVKFX/graph.json","fetch_events":"https://pith.science/api/pith-number/QQI5UXYY2OCIZ7S7A4FUCMVKFX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QQI5UXYY2OCIZ7S7A4FUCMVKFX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QQI5UXYY2OCIZ7S7A4FUCMVKFX/action/storage_attestation","attest_author":"https://pith.science/pith/QQI5UXYY2OCIZ7S7A4FUCMVKFX/action/author_attestation","sign_citation":"https://pith.science/pith/QQI5UXYY2OCIZ7S7A4FUCMVKFX/action/citation_signature","submit_replication":"https://pith.science/pith/QQI5UXYY2OCIZ7S7A4FUCMVKFX/action/replication_record"}},"created_at":"2026-07-05T02:52:55.840282+00:00","updated_at":"2026-07-05T02:52:55.840282+00:00"}