{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BTUQRQWSHPUN263Z76D4LF7QJP","short_pith_number":"pith:BTUQRQWS","schema_version":"1.0","canonical_sha256":"0ce908c2d23be8dd7b79ff87c597f04be8dc77d9ff76c071b0694ef0dac0f249","source":{"kind":"arxiv","id":"1907.07484","version":2},"attestation_state":"computed","paper":{"title":"Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Alexander S. Ecker, Benjamin Mitzkus, Claudio Michaelis, Evgenia Rusak, Matthias Bethge, Oliver Bringmann, Robert Geirhos, Wieland Brendel","submitted_at":"2019-07-17T12:51:10Z","abstract_excerpt":"The ability to detect objects regardless of image distortions or weather conditions is crucial for real-world applications of deep learning like autonomous driving. We here provide an easy-to-use benchmark to assess how object detection models perform when image quality degrades. The three resulting benchmark datasets, termed Pascal-C, Coco-C and Cityscapes-C, contain a large variety of image corruptions. We show that a range of standard object detection models suffer a severe performance loss on corrupted images (down to 30--60\\% of the original performance). However, a simple data augmentati"},"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":"1907.07484","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-17T12:51:10Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"dfb642d4e01f6cc4a979cbb76ba647ec9d091455b1d8fd4e536ab9391d7628eb","abstract_canon_sha256":"4cd9f63945b1ce9f1d09bac9b540f7e6fb3c1e01b5ee5f96d2f1334ea7158ac4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:51:29.468628Z","signature_b64":"G49gTCv9K5BMJH5mh7Oxqn0uAe1wsclLaZ/eYyqKiQ999jH2RRt3GrxVjF21mtMH1lpFRa63AAwH7VHTYUdDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ce908c2d23be8dd7b79ff87c597f04be8dc77d9ff76c071b0694ef0dac0f249","last_reissued_at":"2026-07-05T00:51:29.468143Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:51:29.468143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Alexander S. Ecker, Benjamin Mitzkus, Claudio Michaelis, Evgenia Rusak, Matthias Bethge, Oliver Bringmann, Robert Geirhos, Wieland Brendel","submitted_at":"2019-07-17T12:51:10Z","abstract_excerpt":"The ability to detect objects regardless of image distortions or weather conditions is crucial for real-world applications of deep learning like autonomous driving. We here provide an easy-to-use benchmark to assess how object detection models perform when image quality degrades. The three resulting benchmark datasets, termed Pascal-C, Coco-C and Cityscapes-C, contain a large variety of image corruptions. We show that a range of standard object detection models suffer a severe performance loss on corrupted images (down to 30--60\\% of the original performance). However, a simple data augmentati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.07484","kind":"arxiv","version":2},"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/1907.07484/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":"1907.07484","created_at":"2026-07-05T00:51:29.468201+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.07484v2","created_at":"2026-07-05T00:51:29.468201+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.07484","created_at":"2026-07-05T00:51:29.468201+00:00"},{"alias_kind":"pith_short_12","alias_value":"BTUQRQWSHPUN","created_at":"2026-07-05T00:51:29.468201+00:00"},{"alias_kind":"pith_short_16","alias_value":"BTUQRQWSHPUN263Z","created_at":"2026-07-05T00:51:29.468201+00:00"},{"alias_kind":"pith_short_8","alias_value":"BTUQRQWS","created_at":"2026-07-05T00:51:29.468201+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21446","citing_title":"Lost in Fog: Sensor Perturbations Expose Reasoning Fragility in Driving VLAs","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02603","citing_title":"COD10K-C: Benchmarking Robustness of Camouflaged Object Detection Under Natural Image Corruptions","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27155","citing_title":"Semantic Robustness Probing via Inpainting: An Interactive Tool for Safety-Critical Object Detection","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00828","citing_title":"RoboStressBench: Benchmarking VLM Robustness to Physical Visual Stress in Embodied Scenes","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2501.07360","citing_title":"TimberVision: A Multi-Task Dataset and Framework for Log-Component Segmentation and Tracking in Autonomous Forestry Operations","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2505.09971","citing_title":"APCoTTA: Continual Test-Time Adaptation for Semantic Segmentation of Airborne LiDAR Point Clouds","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2506.16950","citing_title":"LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21446","citing_title":"Lost in Fog: Sensor Perturbations Expose Reasoning Fragility in Driving VLAs","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18287","citing_title":"StableVLA: Towards Robust Vision-Language-Action Models without Extra Data","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18059","citing_title":"Bench2Drive-Robust: Benchmarking Closed-Loop Autonomous Driving under Deployment Perturbations","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2512.18599","citing_title":"Restore-R1: Efficient Image Restoration Agents via Reinforcement Learning with Multimodal LLM Perceptual Feedback","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2312.17090","citing_title":"Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10822","citing_title":"Benchmarking Sensor-Fault Robustness in Forecasting","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05439","citing_title":"Safety-Critical Camera Reliability Monitoring for ADAS via Degradation-Aware Uncertainty Pattern Analysis","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04531","citing_title":"Reward-Guided Semantic Evolution for Test-time Adaptive Object Detection","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23342","citing_title":"Empirical Insights of Test Selection Metrics under Multiple Testing Objectives and Distribution Shifts","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BTUQRQWSHPUN263Z76D4LF7QJP","json":"https://pith.science/pith/BTUQRQWSHPUN263Z76D4LF7QJP.json","graph_json":"https://pith.science/api/pith-number/BTUQRQWSHPUN263Z76D4LF7QJP/graph.json","events_json":"https://pith.science/api/pith-number/BTUQRQWSHPUN263Z76D4LF7QJP/events.json","paper":"https://pith.science/paper/BTUQRQWS"},"agent_actions":{"view_html":"https://pith.science/pith/BTUQRQWSHPUN263Z76D4LF7QJP","download_json":"https://pith.science/pith/BTUQRQWSHPUN263Z76D4LF7QJP.json","view_paper":"https://pith.science/paper/BTUQRQWS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.07484&json=true","fetch_graph":"https://pith.science/api/pith-number/BTUQRQWSHPUN263Z76D4LF7QJP/graph.json","fetch_events":"https://pith.science/api/pith-number/BTUQRQWSHPUN263Z76D4LF7QJP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BTUQRQWSHPUN263Z76D4LF7QJP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BTUQRQWSHPUN263Z76D4LF7QJP/action/storage_attestation","attest_author":"https://pith.science/pith/BTUQRQWSHPUN263Z76D4LF7QJP/action/author_attestation","sign_citation":"https://pith.science/pith/BTUQRQWSHPUN263Z76D4LF7QJP/action/citation_signature","submit_replication":"https://pith.science/pith/BTUQRQWSHPUN263Z76D4LF7QJP/action/replication_record"}},"created_at":"2026-07-05T00:51:29.468201+00:00","updated_at":"2026-07-05T00:51:29.468201+00:00"}