{"id":"W4323305347","doi":"10.2118/212503-ms","title":"Automatic Classification of PDC Cutter Damage Using a Single Deep Learning Neural Network Model","year":2023,"lang":"en","type":"article","venue":"SPE/IADC International Drilling Conference and Exhibition","topic":"Drilling and Well Engineering","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Artificial intelligence; Computer science; Artificial neural network; Drill; Deep learning; Pattern recognition (psychology); Convolutional neural network; Machine learning; Computer vision; 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":[0.0001808936,0.0001630118,0.0001755286,0.0002043966,0.00008596956,0.00008671451,0.0001060123,0.00009080025,0.0000363152],"category_scores_gemma":[0.00003257999,0.0001818907,0.00005605265,0.0002181689,0.00003912653,0.0002790321,0.00003503451,0.0001997163,0.00001553476],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006086138,"about_ca_system_score_gemma":0.00001092811,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000979061,"about_ca_topic_score_gemma":0.00000655696,"domain_scores_codex":[0.9989816,0.00001900894,0.0003286264,0.0001983277,0.0002224432,0.0002500282],"domain_scores_gemma":[0.9995989,0.00005702602,0.00007641956,0.0001051536,0.0001085558,0.00005389764],"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":[0.000003846448,0.000006441216,0.0003828898,0.00007090849,0.00002639865,0.000002284826,0.0003628469,0.9346294,0.05627858,0.001412038,0.00003629913,0.00678802],"study_design_scores_gemma":[0.0001762078,0.00001807034,0.0009857723,0.0002611907,0.00001854838,0.000005913875,0.0001285465,0.9944711,0.001861422,0.001813558,0.00007819199,0.0001814192],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7623076,0.00004670504,0.2350058,0.00005541444,0.0004428737,0.00007443206,0.000005720553,0.0004000802,0.001661353],"genre_scores_gemma":[0.9961557,0.0001519808,0.003197024,0.00001452232,0.0002310641,0.000007521416,0.0001334113,0.00003587027,0.00007287879],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2338481,"threshold_uncertainty_score":0.741729,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03630901826136377,"score_gpt":0.2446779657011177,"score_spread":0.2083689474397539,"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."}}