{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:I2BCLRTFYZ6HSTZK7QE5CV3YTO","short_pith_number":"pith:I2BCLRTF","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"},"canonical_sha256":"468225c665c67c794f2afc09d157789b8056d8fa255c002ecfa5ea2f5ec4fd95","source":{"kind":"arxiv","id":"1903.12261","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.12261","created_at":"2026-07-04T23:30:50Z"},{"alias_kind":"arxiv_version","alias_value":"1903.12261v1","created_at":"2026-07-04T23:30:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.12261","created_at":"2026-07-04T23:30:50Z"},{"alias_kind":"pith_short_12","alias_value":"I2BCLRTFYZ6H","created_at":"2026-07-04T23:30:50Z"},{"alias_kind":"pith_short_16","alias_value":"I2BCLRTFYZ6HSTZK","created_at":"2026-07-04T23:30:50Z"},{"alias_kind":"pith_short_8","alias_value":"I2BCLRTF","created_at":"2026-07-04T23:30:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:I2BCLRTFYZ6HSTZK7QE5CV3YTO","target":"record","payload":{"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"},"canonical_sha256":"468225c665c67c794f2afc09d157789b8056d8fa255c002ecfa5ea2f5ec4fd95","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"},"source_kind":"arxiv","source_id":"1903.12261","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T23:30:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZqhdIhFeGMka0e+rDYeMbUEAEzFCIx2kH6mOVKQCvgKfniEjEGKM3oNG/YivO8z35Sqct4zg3or/zVNL8GlEDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:04:04.375819Z"},"content_sha256":"5a41b4cd7146a11db1786b27d905123767d16a9ea6832c3f19208c55670bc590","schema_version":"1.0","event_id":"sha256:5a41b4cd7146a11db1786b27d905123767d16a9ea6832c3f19208c55670bc590"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:I2BCLRTFYZ6HSTZK7QE5CV3YTO","target":"graph","payload":{"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"},"verdict_id":"02eddbd9-de5c-46c2-a10f-a550a4419adb"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T23:30:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9wzqnyPxJBOrL2WWnOxScKncJiRkkhlGkPcR9VSiptkd3wzZOAD3FRpidyi713Eq7aqktc82MmQ9tqavG+tUBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:04:04.376359Z"},"content_sha256":"30247d3ec65262396a7cfff57a9d340bf7a546f920a1bd821b9fb34ae0ce843a","schema_version":"1.0","event_id":"sha256:30247d3ec65262396a7cfff57a9d340bf7a546f920a1bd821b9fb34ae0ce843a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I2BCLRTFYZ6HSTZK7QE5CV3YTO/bundle.json","state_url":"https://pith.science/pith/I2BCLRTFYZ6HSTZK7QE5CV3YTO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I2BCLRTFYZ6HSTZK7QE5CV3YTO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T11:04:04Z","links":{"resolver":"https://pith.science/pith/I2BCLRTFYZ6HSTZK7QE5CV3YTO","bundle":"https://pith.science/pith/I2BCLRTFYZ6HSTZK7QE5CV3YTO/bundle.json","state":"https://pith.science/pith/I2BCLRTFYZ6HSTZK7QE5CV3YTO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I2BCLRTFYZ6HSTZK7QE5CV3YTO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:I2BCLRTFYZ6HSTZK7QE5CV3YTO","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"80ca9af33ef7b9c092071cdce8a50c5eb7e3132c2263325df4107d2016529076","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-28T20:56:37Z","title_canon_sha256":"23277342ef1585a223722b3849f4825bc5180da3afdc610a297591f55154eba8"},"schema_version":"1.0","source":{"id":"1903.12261","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.12261","created_at":"2026-07-04T23:30:50Z"},{"alias_kind":"arxiv_version","alias_value":"1903.12261v1","created_at":"2026-07-04T23:30:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.12261","created_at":"2026-07-04T23:30:50Z"},{"alias_kind":"pith_short_12","alias_value":"I2BCLRTFYZ6H","created_at":"2026-07-04T23:30:50Z"},{"alias_kind":"pith_short_16","alias_value":"I2BCLRTFYZ6HSTZK","created_at":"2026-07-04T23:30:50Z"},{"alias_kind":"pith_short_8","alias_value":"I2BCLRTF","created_at":"2026-07-04T23:30:50Z"}],"graph_snapshots":[{"event_id":"sha256:30247d3ec65262396a7cfff57a9d340bf7a546f920a1bd821b9fb34ae0ce843a","target":"graph","created_at":"2026-07-04T23:30:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We find that there are negligible changes in relative corruption robustness from AlexNet classifiers to ResNet classifiers."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Benchmarks for common corruptions show negligible relative robustness gains from AlexNet to ResNet."}],"snapshot_sha256":"2add343f8cb6aa176e77282b7b65934478f30024412f40ba0b287f94d2e00d28"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"37c09687df2154df9245b9158884898af498502b8fe540225f3717a3e0d78471"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1903.12261/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dan Hendrycks, Thomas Dietterich","cross_cats":["cs.CV","stat.ML"],"headline":"Benchmarks for common corruptions show negligible relative robustness gains from AlexNet to ResNet.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-28T20:56:37Z","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations"},"references":{"count":62,"internal_anchors":0,"resolved_work":62,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Applying convolutional neural networks concepts to hybrid nn-hmm model for speech recognition","work_id":"9436cef1-b1e3-41f2-831c-b5680a61be5d","year":2013},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Why do deep convolutional networks generalize so poorly to small image transformations?","work_id":"3ce65db5-2a7c-48ae-a1c1-26dd55576ac3","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Measuring neural net robustness with constraints","work_id":"48868be1-0205-4925-9d59-d619235c9923","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"A non-local algorithm for image denoising","work_id":"caeab37b-9ce3-4300-9889-1cb903bc6416","year":2005},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Defensive distillation is not robust to adversarial examples","work_id":"a2850dac-02e8-4333-a395-d7b82c936372","year":2016}],"snapshot_sha256":"1b9f66ac54b27bef1bce4097562af091645b8e072824f97e1744a0a7ab377004"},"source":{"id":"1903.12261","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-13T04:56:52.450015Z","id":"02eddbd9-de5c-46c2-a10f-a550a4419adb","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Benchmarks for common corruptions show negligible relative robustness gains from AlexNet to ResNet.","strongest_claim":"We find that there are negligible changes in relative corruption robustness from AlexNet classifiers to ResNet classifiers.","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."}},"verdict_id":"02eddbd9-de5c-46c2-a10f-a550a4419adb"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5a41b4cd7146a11db1786b27d905123767d16a9ea6832c3f19208c55670bc590","target":"record","created_at":"2026-07-04T23:30:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"80ca9af33ef7b9c092071cdce8a50c5eb7e3132c2263325df4107d2016529076","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-28T20:56:37Z","title_canon_sha256":"23277342ef1585a223722b3849f4825bc5180da3afdc610a297591f55154eba8"},"schema_version":"1.0","source":{"id":"1903.12261","kind":"arxiv","version":1}},"canonical_sha256":"468225c665c67c794f2afc09d157789b8056d8fa255c002ecfa5ea2f5ec4fd95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"468225c665c67c794f2afc09d157789b8056d8fa255c002ecfa5ea2f5ec4fd95","first_computed_at":"2026-07-04T23:30:50.939148Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:30:50.939148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W6BboKyEu8kOivSJffLvi1PJVdniyDYUEUdr5s5C5b7nwIuGNmXiAqf3r2emOlqaZhltQY2UiV+G2yOYR01sCQ==","signature_status":"signed_v1","signed_at":"2026-07-04T23:30:50.939724Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.12261","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a41b4cd7146a11db1786b27d905123767d16a9ea6832c3f19208c55670bc590","sha256:30247d3ec65262396a7cfff57a9d340bf7a546f920a1bd821b9fb34ae0ce843a"],"state_sha256":"ad9d14ee1c2b16d875abbecfa0ba8a61a70276528c86cc0f044881dad45be1c8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SnF8ED01FjgOd9MYO4TJX5fMuvPsD4eHVXTg1O21ZDn/DPUhTJaf2zG6E6BT1trcCLC1ApxBQzI1mS7IJ8RpBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:04:04.378948Z","bundle_sha256":"e2591d4adcf8964c968e3720e60ab67c55d111b7c65383754e3385426e6011ba"}}