{"id":"W3203897244","doi":"10.1007/978-3-030-76004-5_14","title":"Hybrid Concrete Crack Segmentation and Quantification Across Complex Backgrounds Without a Large Training Dataset","year":2021,"lang":"en","type":"book-chapter","venue":"Conference proceedings of the Society for Experimental Mechanics","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Segmentation; Artificial intelligence; Convolutional neural network; Computer science; Deep learning; Pixel; Artificial neural network; Image segmentation; Training (meteorology); Pattern recognition (psychology); Field (mathematics); Computer vision; Machine learning; Geography; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002012319,0.0003612076,0.0004202726,0.00001619281,0.0002738645,0.0001596882,0.0002926544,0.0002036918,0.00003300763],"category_scores_gemma":[0.0000122689,0.0003365225,0.0003211856,0.00002619546,0.00008820345,0.0002376909,0.0002057852,0.0002827792,7.137118e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001529074,"about_ca_system_score_gemma":0.00003621473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001423813,"about_ca_topic_score_gemma":8.325517e-7,"domain_scores_codex":[0.9986823,0.000001600241,0.0003740821,0.0003654826,0.0002422388,0.000334248],"domain_scores_gemma":[0.999252,0.00001915822,0.0002759162,0.000157954,0.0002348786,0.00006010488],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002949964,0.000005721866,0.00000591352,0.000782565,0.0004180985,2.364778e-7,0.01014757,0.000006714946,0.851847,0.1310323,0.004909859,0.0008145007],"study_design_scores_gemma":[0.001934465,0.0001824983,0.000006313667,0.001311163,0.0003250211,0.00004931987,0.06037047,0.0536664,0.8328562,0.008195671,0.03992478,0.001177732],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7497103,0.01168404,0.1259463,0.0005341665,0.01312141,0.01445252,0.05919452,0.001557519,0.02379928],"genre_scores_gemma":[0.987767,0.0002751759,0.007957914,0.0000853982,0.0002130223,0.00009975322,0.001513225,0.0001151986,0.001973269],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2380567,"threshold_uncertainty_score":0.9999087,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05176000648262609,"score_gpt":0.2927860593352413,"score_spread":0.2410260528526152,"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."}}