{"id":"W2132864254","doi":"10.1007/s00138-005-0012-0","title":"Morphological segmentation and classification of underground pipe images","year":2006,"lang":"en","type":"article","venue":"Machine Vision and Applications","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":48,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Pipeline (software); Segmentation; Artificial intelligence; Image segmentation; Computer science; Visual inspection; Pipeline transport; Computer vision; Pattern recognition (psychology); Geology; Engineering; Mechanical 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":[0.00004059494,0.00006514444,0.00006856241,0.00004216885,0.00006455297,0.00001984916,0.00002824125,0.0000330339,0.000007001214],"category_scores_gemma":[0.000001770928,0.00005300908,0.00001109387,0.00007750535,0.0000448551,0.00005586337,0.0000130719,0.00005077763,0.000001822521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001070186,"about_ca_system_score_gemma":0.000001684706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000236026,"about_ca_topic_score_gemma":0.000006087225,"domain_scores_codex":[0.9996611,0.000004947712,0.000124711,0.00009578467,0.00004933958,0.00006408214],"domain_scores_gemma":[0.9998369,0.00002134303,0.00002567685,0.00007828436,0.00001781626,0.00001995131],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00000417935,0.00002899544,0.008752042,0.00005559779,0.000006481707,4.380423e-7,0.0000290953,0.0006390403,0.8568471,0.01829961,0.0008093633,0.1145281],"study_design_scores_gemma":[0.0006560739,0.00005847937,0.9048437,0.00002613085,0.00003479407,0.0000315875,0.0002673236,0.02524973,0.03884929,0.01667174,0.0130412,0.0002699649],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7089352,0.0006213869,0.2850378,0.0001616817,0.00004457623,0.00024775,0.00002186505,0.0001170164,0.004812752],"genre_scores_gemma":[0.9965563,0.0001347875,0.003101323,0.00001016816,0.00005678874,0.00003727049,0.00003853393,0.000006975412,0.00005781488],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8960916,"threshold_uncertainty_score":0.2161647,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005870507811560283,"score_gpt":0.2463795253771771,"score_spread":0.2405090175656169,"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."}}