{"id":"W2547865994","doi":"10.5339/qfarc.2016.eepp2827","title":"Machine Learning Techniques for Defect Depth Estimation in Oil and Gas Pipelines","year":2016,"lang":"en","type":"article","venue":"Qatar Foundation Annual Research Conference Proceedings Volume 2016 Issue 1","topic":"Non-Destructive Testing Techniques","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Pipeline transport; Magnetic flux leakage; Pipeline (software); Magnet; Petroleum industry; Petroleum engineering; Leakage (economics); Forensic engineering; Point (geometry); Mechanical engineering; Engineering; Marine 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":[0.002138021,0.0002439872,0.0002571107,0.0006178679,0.0001962966,0.0002452866,0.0002943049,0.0001575362,0.000125473],"category_scores_gemma":[0.004543048,0.0002053257,0.00003693493,0.0003959496,0.0002642234,0.001304339,0.000133492,0.0003918417,0.00009029076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002871304,"about_ca_system_score_gemma":0.0001007009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002198027,"about_ca_topic_score_gemma":0.00009072552,"domain_scores_codex":[0.9981128,0.00005046287,0.0003742512,0.0004547626,0.000433158,0.0005745396],"domain_scores_gemma":[0.9978727,0.0003529418,0.00008184861,0.0001313982,0.001427254,0.0001339176],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009177993,0.00003228496,0.01571527,0.0004655227,0.00001957979,0.000001594667,0.00108203,0.000001851954,0.05144349,0.01094696,0.002441906,0.9177577],"study_design_scores_gemma":[0.002814677,0.002132207,0.008765971,0.004860759,0.00005104675,0.00007877854,0.001563014,0.2202079,0.05373373,0.5022886,0.2012384,0.002264935],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4791524,0.0009279054,0.4510888,0.008927033,0.0003772641,0.003219098,0.000214045,0.008201841,0.04789159],"genre_scores_gemma":[0.7942911,0.001301961,0.2019757,0.00001005511,0.0001316921,0.0005479722,0.00004050551,0.00008323835,0.001617686],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9154928,"threshold_uncertainty_score":0.8372938,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03983976155101109,"score_gpt":0.3420637756150155,"score_spread":0.3022240140640044,"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."}}