{"paper":{"title":"PipeMFL-240K: A Large-scale Dataset and Benchmark for Object Detection in Pipeline Magnetic Flux Leakage Imaging","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"PipeMFL-240K provides the first large-scale public dataset and benchmark for detecting defects in pipeline magnetic flux leakage images.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guanlin Liu, Haolin Wang, Honghe Chen, Huadong Song, Songxiao Yang, Tianyi Qu, Wenguang Hu, Xiaoting Guo, Yafei Ou","submitted_at":"2026-02-04T04:43:32Z","abstract_excerpt":"Pipeline integrity is critical to industrial safety and environmental protection, with Magnetic Flux Leakage (MFL) detection being a primary non-destructive testing technology. Despite the promise of deep learning for automating MFL interpretation, progress toward reliable models has been constrained by the absence of a large-scale public dataset and benchmark, making fair comparison and reproducible evaluation difficult. We introduce \\textbf{PipeMFL-240K}, a large-scale, meticulously annotated dataset and benchmark for complex object detection in pipeline MFL pseudo-color images. PipeMFL-240K"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"As the first public dataset and the first benchmark of this scale and scope for pipeline MFL inspection, it provides a critical foundation for efficient pipeline diagnostics as well as maintenance planning and is expected to accelerate algorithmic innovation and reproducible research in MFL-based pipeline integrity assessment.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The collected images and annotations from the 12 pipelines are representative of real-world MFL inspection complexity and that the bounding-box labels are consistently high-quality across the entire dataset.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PipeMFL-240K is the first large public dataset and benchmark for object detection in pipeline MFL imaging, with 249k images across 12 long-tailed categories featuring tiny objects and high intra-class variability.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"PipeMFL-240K provides the first large-scale public dataset and benchmark for detecting defects in pipeline magnetic flux leakage images.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"7e9e04700ad6ba9826d89361cfc74350855b75e535fbe9a0536f0a9dc14db004"},"source":{"id":"2602.07044","kind":"arxiv","version":3},"verdict":{"id":"d6fa1ae0-c385-4226-8c4b-f444e7de7f86","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T08:12:42.743443Z","strongest_claim":"As the first public dataset and the first benchmark of this scale and scope for pipeline MFL inspection, it provides a critical foundation for efficient pipeline diagnostics as well as maintenance planning and is expected to accelerate algorithmic innovation and reproducible research in MFL-based pipeline integrity assessment.","one_line_summary":"PipeMFL-240K is the first large public dataset and benchmark for object detection in pipeline MFL imaging, with 249k images across 12 long-tailed categories featuring tiny objects and high intra-class variability.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The collected images and annotations from the 12 pipelines are representative of real-world MFL inspection complexity and that the bounding-box labels are consistently high-quality across the entire dataset.","pith_extraction_headline":"PipeMFL-240K provides the first large-scale public dataset and benchmark for detecting defects in pipeline magnetic flux leakage images."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.07044/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"}