{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OLIEKMF57VBKPUXB7DWYA5YFE3","short_pith_number":"pith:OLIEKMF5","schema_version":"1.0","canonical_sha256":"72d04530bdfd42a7d2e1f8ed80770526c66a86618d8f7558347713e97bab2a7a","source":{"kind":"arxiv","id":"2204.08623","version":1},"attestation_state":"computed","paper":{"title":"CorrGAN: Input Transformation Technique Against Natural Corruptions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Christof J. Budnik, Mirazul Haque, Wei Yang","submitted_at":"2022-04-19T02:56:46Z","abstract_excerpt":"Because of the increasing accuracy of Deep Neural Networks (DNNs) on different tasks, a lot of real times systems are utilizing DNNs. These DNNs are vulnerable to adversarial perturbations and corruptions. Specifically, natural corruptions like fog, blur, contrast etc can affect the prediction of DNN in an autonomous vehicle. In real time, these corruptions are needed to be detected and also the corrupted inputs are needed to be de-noised to be predicted correctly. In this work, we propose CorrGAN approach, which can generate benign input when a corrupted input is provided. In this framework, "},"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":"2204.08623","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-19T02:56:46Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2db1b85f137da39d69e7c257d956b6f4f36f5077d18cd2cbb1adb42147cfcbba","abstract_canon_sha256":"959bae990e68631d66278dc623e8b955345a51b1a3a2b6f3a22d3d882ce9d65f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:15:32.184379Z","signature_b64":"7nj9HfMzAXURUPn2f8ZN5g4ZrxFkdkaft2IF90Q2hVNh9M2FAH/15exJukA1XEuiOluRmiqdDzr2rhprSM5YDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72d04530bdfd42a7d2e1f8ed80770526c66a86618d8f7558347713e97bab2a7a","last_reissued_at":"2026-07-05T04:15:32.183968Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:15:32.183968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CorrGAN: Input Transformation Technique Against Natural Corruptions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Christof J. Budnik, Mirazul Haque, Wei Yang","submitted_at":"2022-04-19T02:56:46Z","abstract_excerpt":"Because of the increasing accuracy of Deep Neural Networks (DNNs) on different tasks, a lot of real times systems are utilizing DNNs. These DNNs are vulnerable to adversarial perturbations and corruptions. Specifically, natural corruptions like fog, blur, contrast etc can affect the prediction of DNN in an autonomous vehicle. In real time, these corruptions are needed to be detected and also the corrupted inputs are needed to be de-noised to be predicted correctly. In this work, we propose CorrGAN approach, which can generate benign input when a corrupted input is provided. In this framework, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.08623","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/2204.08623/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":"2204.08623","created_at":"2026-07-05T04:15:32.184030+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.08623v1","created_at":"2026-07-05T04:15:32.184030+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.08623","created_at":"2026-07-05T04:15:32.184030+00:00"},{"alias_kind":"pith_short_12","alias_value":"OLIEKMF57VBK","created_at":"2026-07-05T04:15:32.184030+00:00"},{"alias_kind":"pith_short_16","alias_value":"OLIEKMF57VBKPUXB","created_at":"2026-07-05T04:15:32.184030+00:00"},{"alias_kind":"pith_short_8","alias_value":"OLIEKMF5","created_at":"2026-07-05T04:15:32.184030+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/OLIEKMF57VBKPUXB7DWYA5YFE3","json":"https://pith.science/pith/OLIEKMF57VBKPUXB7DWYA5YFE3.json","graph_json":"https://pith.science/api/pith-number/OLIEKMF57VBKPUXB7DWYA5YFE3/graph.json","events_json":"https://pith.science/api/pith-number/OLIEKMF57VBKPUXB7DWYA5YFE3/events.json","paper":"https://pith.science/paper/OLIEKMF5"},"agent_actions":{"view_html":"https://pith.science/pith/OLIEKMF57VBKPUXB7DWYA5YFE3","download_json":"https://pith.science/pith/OLIEKMF57VBKPUXB7DWYA5YFE3.json","view_paper":"https://pith.science/paper/OLIEKMF5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.08623&json=true","fetch_graph":"https://pith.science/api/pith-number/OLIEKMF57VBKPUXB7DWYA5YFE3/graph.json","fetch_events":"https://pith.science/api/pith-number/OLIEKMF57VBKPUXB7DWYA5YFE3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OLIEKMF57VBKPUXB7DWYA5YFE3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OLIEKMF57VBKPUXB7DWYA5YFE3/action/storage_attestation","attest_author":"https://pith.science/pith/OLIEKMF57VBKPUXB7DWYA5YFE3/action/author_attestation","sign_citation":"https://pith.science/pith/OLIEKMF57VBKPUXB7DWYA5YFE3/action/citation_signature","submit_replication":"https://pith.science/pith/OLIEKMF57VBKPUXB7DWYA5YFE3/action/replication_record"}},"created_at":"2026-07-05T04:15:32.184030+00:00","updated_at":"2026-07-05T04:15:32.184030+00:00"}