{"id":"W2945689285","doi":"10.1016/j.autcon.2019.04.014","title":"Segment-based pavement crack quantification","year":2019,"lang":"en","type":"article","venue":"Automation in Construction","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":77,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Wuhan University; National Natural Science Foundation of China","keywords":"Enhanced Data Rates for GSM Evolution; Segmentation; Pixel; Edge detection; Grayscale; Fracture mechanics; Structural engineering; Computer science; Materials science; Image processing; Artificial intelligence; Image (mathematics); Engineering","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":[0.00009998744,0.00008614371,0.00008321473,0.000152069,0.00002475859,0.00002924147,0.00004584698,0.00006067314,0.0001264797],"category_scores_gemma":[0.000006480435,0.00009317426,0.00002261982,0.0001728531,0.00001458967,0.0001991655,0.000004327444,0.0000826984,0.0001408176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001706797,"about_ca_system_score_gemma":0.00001534634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009320529,"about_ca_topic_score_gemma":0.000004759003,"domain_scores_codex":[0.999389,0.00001442485,0.0002257192,0.0001184502,0.0001191346,0.0001332575],"domain_scores_gemma":[0.9997345,0.0000173756,0.00004436401,0.0001519199,0.00003440704,0.0000174364],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001175517,0.00001981183,0.1234389,0.0002718774,0.00002477655,0.000001496469,0.0003479689,0.5602044,0.168811,0.01025766,0.0004297603,0.1361806],"study_design_scores_gemma":[0.0009848701,0.00002720002,0.1298318,0.0001497408,0.000008701409,0.000008200468,0.0004658081,0.7144167,0.1502793,0.0009279024,0.002600156,0.0002995503],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9503022,0.00001669999,0.04482277,0.00004768145,0.002476861,0.0002450463,0.000002068704,0.0003398176,0.001746879],"genre_scores_gemma":[0.9929365,0.00000543156,0.006886405,0.00002018189,0.0000617212,0.00002720653,0.0000269502,0.00001233239,0.00002330618],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1542123,"threshold_uncertainty_score":0.3799536,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005903485132817769,"score_gpt":0.210669961577554,"score_spread":0.2047664764447363,"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."}}