{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:W2HCA4HZQBCZW5TL2JZWOKSU4X","short_pith_number":"pith:W2HCA4HZ","schema_version":"1.0","canonical_sha256":"b68e2070f980459b766bd273672a54e5f2ba6e277f2fa8d22317c3d16d23993f","source":{"kind":"arxiv","id":"1906.08988","version":3},"attestation_state":"computed","paper":{"title":"A Fourier Perspective on Model Robustness in Computer Vision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dong Yin, Ekin D. Cubuk, Jonathon Shlens, Justin Gilmer, Raphael Gontijo Lopes","submitted_at":"2019-06-21T07:31:26Z","abstract_excerpt":"Achieving robustness to distributional shift is a longstanding and challenging goal of computer vision. Data augmentation is a commonly used approach for improving robustness, however robustness gains are typically not uniform across corruption types. Indeed increasing performance in the presence of random noise is often met with reduced performance on other corruptions such as contrast change. Understanding when and why these sorts of trade-offs occur is a crucial step towards mitigating them. Towards this end, we investigate recently observed trade-offs caused by Gaussian data augmentation a"},"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":"1906.08988","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-21T07:31:26Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"1113f91581a7fc1c84f3c1302cb2d84f842c25651bdbf404ef0ecc300e3e4c7b","abstract_canon_sha256":"1bbb45b7100a62f98369e8b2cb5f7434674b970d529b0a4bfeca73017b777370"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:35:56.716805Z","signature_b64":"maOw8HcM1qIVSIpusxtuCnkNVilH9gXk0RJ8lUaL3jWQyP/LoV1upvq3iHRIxrZZF3XRpmZPGQQX+yAiaqF1Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b68e2070f980459b766bd273672a54e5f2ba6e277f2fa8d22317c3d16d23993f","last_reissued_at":"2026-07-05T01:35:56.716168Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:35:56.716168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Fourier Perspective on Model Robustness in Computer Vision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dong Yin, Ekin D. Cubuk, Jonathon Shlens, Justin Gilmer, Raphael Gontijo Lopes","submitted_at":"2019-06-21T07:31:26Z","abstract_excerpt":"Achieving robustness to distributional shift is a longstanding and challenging goal of computer vision. Data augmentation is a commonly used approach for improving robustness, however robustness gains are typically not uniform across corruption types. Indeed increasing performance in the presence of random noise is often met with reduced performance on other corruptions such as contrast change. Understanding when and why these sorts of trade-offs occur is a crucial step towards mitigating them. Towards this end, we investigate recently observed trade-offs caused by Gaussian data augmentation a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08988","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/1906.08988/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":"1906.08988","created_at":"2026-07-05T01:35:56.716247+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.08988v3","created_at":"2026-07-05T01:35:56.716247+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08988","created_at":"2026-07-05T01:35:56.716247+00:00"},{"alias_kind":"pith_short_12","alias_value":"W2HCA4HZQBCZ","created_at":"2026-07-05T01:35:56.716247+00:00"},{"alias_kind":"pith_short_16","alias_value":"W2HCA4HZQBCZW5TL","created_at":"2026-07-05T01:35:56.716247+00:00"},{"alias_kind":"pith_short_8","alias_value":"W2HCA4HZ","created_at":"2026-07-05T01:35:56.716247+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20299","citing_title":"Statistical Properties of Training & Generalization","ref_index":300,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20299","citing_title":"Statistical Properties of Training & Generalization","ref_index":300,"is_internal_anchor":false},{"citing_arxiv_id":"1906.11172","citing_title":"Learning Data Augmentation Strategies for Object Detection","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07398","citing_title":"Exposing and Mitigating Temporal Attack in Deepfake Video Detection","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W2HCA4HZQBCZW5TL2JZWOKSU4X","json":"https://pith.science/pith/W2HCA4HZQBCZW5TL2JZWOKSU4X.json","graph_json":"https://pith.science/api/pith-number/W2HCA4HZQBCZW5TL2JZWOKSU4X/graph.json","events_json":"https://pith.science/api/pith-number/W2HCA4HZQBCZW5TL2JZWOKSU4X/events.json","paper":"https://pith.science/paper/W2HCA4HZ"},"agent_actions":{"view_html":"https://pith.science/pith/W2HCA4HZQBCZW5TL2JZWOKSU4X","download_json":"https://pith.science/pith/W2HCA4HZQBCZW5TL2JZWOKSU4X.json","view_paper":"https://pith.science/paper/W2HCA4HZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.08988&json=true","fetch_graph":"https://pith.science/api/pith-number/W2HCA4HZQBCZW5TL2JZWOKSU4X/graph.json","fetch_events":"https://pith.science/api/pith-number/W2HCA4HZQBCZW5TL2JZWOKSU4X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W2HCA4HZQBCZW5TL2JZWOKSU4X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W2HCA4HZQBCZW5TL2JZWOKSU4X/action/storage_attestation","attest_author":"https://pith.science/pith/W2HCA4HZQBCZW5TL2JZWOKSU4X/action/author_attestation","sign_citation":"https://pith.science/pith/W2HCA4HZQBCZW5TL2JZWOKSU4X/action/citation_signature","submit_replication":"https://pith.science/pith/W2HCA4HZQBCZW5TL2JZWOKSU4X/action/replication_record"}},"created_at":"2026-07-05T01:35:56.716247+00:00","updated_at":"2026-07-05T01:35:56.716247+00:00"}