{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:I2BCLRTFYZ6HSTZK7QE5CV3YTO","short_pith_number":"pith:I2BCLRTF","schema_version":"1.0","canonical_sha256":"468225c665c67c794f2afc09d157789b8056d8fa255c002ecfa5ea2f5ec4fd95","source":{"kind":"arxiv","id":"1903.12261","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Benchmarks for common corruptions show negligible relative robustness gains from AlexNet to ResNet.","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dan Hendrycks, Thomas Dietterich","submitted_at":"2019-03-28T20:56:37Z","abstract_excerpt":"In this paper we establish rigorous benchmarks for image classifier robustness. Our first benchmark, ImageNet-C, standardizes and expands the corruption robustness topic, while showing which classifiers are preferable in safety-critical applications. Then we propose a new dataset called ImageNet-P which enables researchers to benchmark a classifier's robustness to common perturbations. Unlike recent robustness research, this benchmark evaluates performance on common corruptions and perturbations not worst-case adversarial perturbations. We find that there are negligible changes in relative cor"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"1903.12261","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-28T20:56:37Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"23277342ef1585a223722b3849f4825bc5180da3afdc610a297591f55154eba8","abstract_canon_sha256":"80ca9af33ef7b9c092071cdce8a50c5eb7e3132c2263325df4107d2016529076"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:30:50.939724Z","signature_b64":"W6BboKyEu8kOivSJffLvi1PJVdniyDYUEUdr5s5C5b7nwIuGNmXiAqf3r2emOlqaZhltQY2UiV+G2yOYR01sCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"468225c665c67c794f2afc09d157789b8056d8fa255c002ecfa5ea2f5ec4fd95","last_reissued_at":"2026-07-04T23:30:50.939148Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:30:50.939148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Benchmarks for common corruptions show negligible relative robustness gains from AlexNet to ResNet.","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dan Hendrycks, Thomas Dietterich","submitted_at":"2019-03-28T20:56:37Z","abstract_excerpt":"In this paper we establish rigorous benchmarks for image classifier robustness. Our first benchmark, ImageNet-C, standardizes and expands the corruption robustness topic, while showing which classifiers are preferable in safety-critical applications. Then we propose a new dataset called ImageNet-P which enables researchers to benchmark a classifier's robustness to common perturbations. Unlike recent robustness research, this benchmark evaluates performance on common corruptions and perturbations not worst-case adversarial perturbations. We find that there are negligible changes in relative cor"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We find that there are negligible changes in relative corruption robustness from AlexNet classifiers to ResNet classifiers.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the 15 chosen corruptions and the perturbations in ImageNet-P sufficiently represent the common real-world image degradations classifiers will encounter in deployment.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Introduces ImageNet-C and ImageNet-P benchmarks revealing negligible robustness gains from AlexNet to ResNet models on common corruptions and perturbations, plus methods to improve them.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Benchmarks for common corruptions show negligible relative robustness gains from AlexNet to ResNet.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2add343f8cb6aa176e77282b7b65934478f30024412f40ba0b287f94d2e00d28"},"source":{"id":"1903.12261","kind":"arxiv","version":1},"verdict":{"id":"02eddbd9-de5c-46c2-a10f-a550a4419adb","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T04:56:52.450015Z","strongest_claim":"We find that there are negligible changes in relative corruption robustness from AlexNet classifiers to ResNet classifiers.","one_line_summary":"Introduces ImageNet-C and ImageNet-P benchmarks revealing negligible robustness gains from AlexNet to ResNet models on common corruptions and perturbations, plus methods to improve them.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the 15 chosen corruptions and the perturbations in ImageNet-P sufficiently represent the common real-world image degradations classifiers will encounter in deployment.","pith_extraction_headline":"Benchmarks for common corruptions show negligible relative robustness gains from AlexNet to ResNet."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1903.12261/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":62,"sample":[{"doi":"","year":2013,"title":"Applying convolutional neural networks concepts to hybrid nn-hmm model for speech recognition","work_id":"9436cef1-b1e3-41f2-831c-b5680a61be5d","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Why do deep convolutional networks generalize so poorly to small image transformations?","work_id":"3ce65db5-2a7c-48ae-a1c1-26dd55576ac3","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"Measuring neural net robustness with constraints","work_id":"48868be1-0205-4925-9d59-d619235c9923","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2005,"title":"A non-local algorithm for image denoising","work_id":"caeab37b-9ce3-4300-9889-1cb903bc6416","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"Defensive distillation is not robust to adversarial examples","work_id":"a2850dac-02e8-4333-a395-d7b82c936372","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":62,"snapshot_sha256":"1b9f66ac54b27bef1bce4097562af091645b8e072824f97e1744a0a7ab377004","internal_anchors":0},"formal_canon":{"evidence_count":1,"snapshot_sha256":"37c09687df2154df9245b9158884898af498502b8fe540225f3717a3e0d78471"},"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":"1903.12261","created_at":"2026-07-04T23:30:50.939218+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.12261v1","created_at":"2026-07-04T23:30:50.939218+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.12261","created_at":"2026-07-04T23:30:50.939218+00:00"},{"alias_kind":"pith_short_12","alias_value":"I2BCLRTFYZ6H","created_at":"2026-07-04T23:30:50.939218+00:00"},{"alias_kind":"pith_short_16","alias_value":"I2BCLRTFYZ6HSTZK","created_at":"2026-07-04T23:30:50.939218+00:00"},{"alias_kind":"pith_short_8","alias_value":"I2BCLRTF","created_at":"2026-07-04T23:30:50.939218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":72,"internal_anchor_count":72,"sample":[{"citing_arxiv_id":"2606.26041","citing_title":"How Robust is OCR-Reasoning? Evaluating OCR-Reasoning Robustness of Vision-Language Models under Visual Perturbations","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26398","citing_title":"DinoLink: A Token-Centric Representation Compression Framework for Bandwidth-Constrained Collaborative V2X Perception","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22543","citing_title":"MAPS: Multi-Anchor Projection Similarity for Joint Vision-Language Geo-Localization","ref_index":57,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20196","citing_title":"Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2606.12200","citing_title":"Implicit Neural Representations of Individual Behavior","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2606.11319","citing_title":"Learning from almost nothing: How neural networks survive heavy input corruption","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2606.09658","citing_title":"Muon Learns More Robust and Transferable Features than Adam","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2606.08894","citing_title":"Are Reasoning Vision-Language Models Robust to Semantic Visual Distractions?","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2606.08814","citing_title":"STAR: Rethinking MoE Routing as Structure-Aware Subspace Learning","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2607.00259","citing_title":"Multi-Hypothesis Test-Time Adaptation to Mitigate Underspecification","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2606.06140","citing_title":"RedEdit: Agentic Red-Teaming of Image Safety Classifiers via MCTS-Guided Photo-Editing","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2606.07646","citing_title":"DOME: Learning Transferable Domain Variables from Sparse Supervision for Test-Time Adaptation","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2606.02789","citing_title":"Diagnosis of Human Object Interaction Detectors for Real World Educational Applications","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.31187","citing_title":"From Local Geometry to Global Pseudo Labeling for Robust Positive Unlabeled Learning under Covariate Shift","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26398","citing_title":"DinoLink: A Token-Centric Representation Compression Framework for Bandwidth-Constrained Collaborative V2X Perception","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20196","citing_title":"Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20436","citing_title":"Lighting-aware Unified Model for Instance Segmentation","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.24754","citing_title":"Motion-Compensated Weight Compression","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.25651","citing_title":"Hierarchical Consistency Learning for Test-time Adaptation in Camouflage Perception","ref_index":71,"is_internal_anchor":true},{"citing_arxiv_id":"2605.27851","citing_title":"When Context Flips, Safety Breaks: Diagnosing Brittle Safety in Aligned Language Models","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.30734","citing_title":"Beyond Accuracy: Evaluating Efficiency, Robustness and Explainability in Deep Learning for Malaria Diagnosis","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.31226","citing_title":"What changes after deployment? A survey on On-device Learning in TinyML","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2605.31041","citing_title":"Does Visual Information Play a Decisive Role in Vision-Language-Action Model Driving Behavior?","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2606.00828","citing_title":"RoboStressBench: Benchmarking VLM Robustness to Physical Visual Stress in Embodied Scenes","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2606.09881","citing_title":"Toward Calibrated, Fair, and accurate Deepfake Detection","ref_index":299,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I2BCLRTFYZ6HSTZK7QE5CV3YTO","json":"https://pith.science/pith/I2BCLRTFYZ6HSTZK7QE5CV3YTO.json","graph_json":"https://pith.science/api/pith-number/I2BCLRTFYZ6HSTZK7QE5CV3YTO/graph.json","events_json":"https://pith.science/api/pith-number/I2BCLRTFYZ6HSTZK7QE5CV3YTO/events.json","paper":"https://pith.science/paper/I2BCLRTF"},"agent_actions":{"view_html":"https://pith.science/pith/I2BCLRTFYZ6HSTZK7QE5CV3YTO","download_json":"https://pith.science/pith/I2BCLRTFYZ6HSTZK7QE5CV3YTO.json","view_paper":"https://pith.science/paper/I2BCLRTF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.12261&json=true","fetch_graph":"https://pith.science/api/pith-number/I2BCLRTFYZ6HSTZK7QE5CV3YTO/graph.json","fetch_events":"https://pith.science/api/pith-number/I2BCLRTFYZ6HSTZK7QE5CV3YTO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I2BCLRTFYZ6HSTZK7QE5CV3YTO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I2BCLRTFYZ6HSTZK7QE5CV3YTO/action/storage_attestation","attest_author":"https://pith.science/pith/I2BCLRTFYZ6HSTZK7QE5CV3YTO/action/author_attestation","sign_citation":"https://pith.science/pith/I2BCLRTFYZ6HSTZK7QE5CV3YTO/action/citation_signature","submit_replication":"https://pith.science/pith/I2BCLRTFYZ6HSTZK7QE5CV3YTO/action/replication_record"}},"created_at":"2026-07-04T23:30:50.939218+00:00","updated_at":"2026-07-04T23:30:50.939218+00:00"}