{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:C5XYIFPTEAGBM3FPCFOENGZ5N4","short_pith_number":"pith:C5XYIFPT","schema_version":"1.0","canonical_sha256":"176f8415f3200c166caf115c469b3d6f3b69fef6f5c7b14ae275647f45ccfee3","source":{"kind":"arxiv","id":"2602.07044","version":3},"attestation_state":"computed","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"},"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":"2602.07044","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-04T04:43:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"07a8abf8a845497b27fc08d9e25b0d54403cf899e7e4e85a4b6b87e571e1e08f","abstract_canon_sha256":"e04f60a64ce966b559ab2f34652ffc3774a56026349f46842c92191b7aab5f9c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:14.559167Z","signature_b64":"JGHN7AyAdJCWIoJ8Y6dq4GCnWTQ7WBiFaPZoosaake6N15UaZT9wZ6V29jXV/i5xZuoIrJGDQ76vE3oGhuXyCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"176f8415f3200c166caf115c469b3d6f3b69fef6f5c7b14ae275647f45ccfee3","last_reissued_at":"2026-05-25T02:01:14.558399Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:14.558399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2602.07044","created_at":"2026-05-25T02:01:14.558503+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.07044v3","created_at":"2026-05-25T02:01:14.558503+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.07044","created_at":"2026-05-25T02:01:14.558503+00:00"},{"alias_kind":"pith_short_12","alias_value":"C5XYIFPTEAGB","created_at":"2026-05-25T02:01:14.558503+00:00"},{"alias_kind":"pith_short_16","alias_value":"C5XYIFPTEAGBM3FP","created_at":"2026-05-25T02:01:14.558503+00:00"},{"alias_kind":"pith_short_8","alias_value":"C5XYIFPT","created_at":"2026-05-25T02:01:14.558503+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/C5XYIFPTEAGBM3FPCFOENGZ5N4","json":"https://pith.science/pith/C5XYIFPTEAGBM3FPCFOENGZ5N4.json","graph_json":"https://pith.science/api/pith-number/C5XYIFPTEAGBM3FPCFOENGZ5N4/graph.json","events_json":"https://pith.science/api/pith-number/C5XYIFPTEAGBM3FPCFOENGZ5N4/events.json","paper":"https://pith.science/paper/C5XYIFPT"},"agent_actions":{"view_html":"https://pith.science/pith/C5XYIFPTEAGBM3FPCFOENGZ5N4","download_json":"https://pith.science/pith/C5XYIFPTEAGBM3FPCFOENGZ5N4.json","view_paper":"https://pith.science/paper/C5XYIFPT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.07044&json=true","fetch_graph":"https://pith.science/api/pith-number/C5XYIFPTEAGBM3FPCFOENGZ5N4/graph.json","fetch_events":"https://pith.science/api/pith-number/C5XYIFPTEAGBM3FPCFOENGZ5N4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C5XYIFPTEAGBM3FPCFOENGZ5N4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C5XYIFPTEAGBM3FPCFOENGZ5N4/action/storage_attestation","attest_author":"https://pith.science/pith/C5XYIFPTEAGBM3FPCFOENGZ5N4/action/author_attestation","sign_citation":"https://pith.science/pith/C5XYIFPTEAGBM3FPCFOENGZ5N4/action/citation_signature","submit_replication":"https://pith.science/pith/C5XYIFPTEAGBM3FPCFOENGZ5N4/action/replication_record"}},"created_at":"2026-05-25T02:01:14.558503+00:00","updated_at":"2026-05-25T02:01:14.558503+00:00"}