{"id":"W4408159444","doi":"10.1007/s11042-025-20700-w","title":"EGY_PDD: a comprehensive multi-sensor benchmark dataset for accurate pavement distress detection and classification","year":2025,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Benchmark (surveying); Distress; Artificial intelligence; Data mining; Machine learning; Pattern recognition (psychology); Geology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00003360358,0.0001189489,0.0001114536,0.00004850573,0.0001858225,0.00006917575,0.00005667126,0.00006065178,0.000002018606],"category_scores_gemma":[0.00001353874,0.0001135083,0.00001763976,0.00008620851,0.00004750979,0.00009624603,0.00002640846,0.00007846389,0.000002256745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003041729,"about_ca_system_score_gemma":0.000005329949,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008766068,"about_ca_topic_score_gemma":0.00002205678,"domain_scores_codex":[0.9994409,0.00000629656,0.0001652765,0.0001999869,0.00003984777,0.000147687],"domain_scores_gemma":[0.9995781,0.000120075,0.00003135621,0.0001722738,0.00005164107,0.00004653973],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001606415,0.00004091411,0.0006222015,0.0003626141,0.0000914943,3.605111e-7,0.000242932,0.001114248,0.1986928,0.0008401926,0.001999925,0.7959763],"study_design_scores_gemma":[0.001638915,0.00002435196,0.1176449,0.0000714714,0.0001094773,0.000002746266,0.0009438464,0.4299245,0.02104341,0.0003223273,0.4278902,0.0003838694],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05575998,0.0006814225,0.9339086,0.0002071191,0.0004216838,0.002451222,0.00624151,0.0001822944,0.000146144],"genre_scores_gemma":[0.9781787,0.0003955055,0.01654799,0.00006587477,0.0001660068,0.002099154,0.002475359,0.00001657031,0.00005479987],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9224188,"threshold_uncertainty_score":0.4628735,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03000237342829242,"score_gpt":0.2878734253600178,"score_spread":0.2578710519317253,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}