{"id":"W3093570631","doi":"10.2118/201664-ms","title":"Drill Bit Damage Assessment Using Image Analysis and Deep Learning as an Alternative to Traditional IADC Dull Grading","year":2020,"lang":"en","type":"article","venue":"SPE Annual Technical Conference and Exhibition","topic":"Drilling and Well Engineering","field":"Engineering","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Apache (Canada)","funders":"","keywords":"Computer science; Drill bit; Drill; Artificial intelligence; Grading (engineering); Convolutional neural network; Drilling; Image processing; Computer vision; Machine learning; Pattern recognition (psychology); 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":[0.0001420942,0.0001919471,0.0002610113,0.0001839788,0.0001164918,0.000144748,0.0000796142,0.00008646013,0.00006253045],"category_scores_gemma":[0.00003968255,0.000206064,0.00005669368,0.0004022029,0.00004883319,0.0004653791,0.00004547147,0.000329322,0.000006859761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004729782,"about_ca_system_score_gemma":0.00001113962,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004836794,"about_ca_topic_score_gemma":0.00001674864,"domain_scores_codex":[0.9989889,0.00003132007,0.0002184665,0.0003351219,0.000189992,0.0002361588],"domain_scores_gemma":[0.9994861,0.00003654634,0.00002947956,0.00008833372,0.00006886484,0.0002906017],"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":[0.00006050182,0.00009084284,0.002512586,0.0002364869,0.000353593,0.0001333367,0.004007318,0.4921184,0.4602236,0.01955217,0.0001332083,0.02057802],"study_design_scores_gemma":[0.0002468718,0.0002930053,0.007149768,0.00006855815,0.0001509151,0.0000111429,0.0004760783,0.9848701,0.004130274,0.002030285,0.0001898124,0.0003831969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6014584,0.00002883019,0.3967504,0.0001984837,0.00003151183,0.00009950779,0.0000310411,0.0002952857,0.001106546],"genre_scores_gemma":[0.9890854,0.000114812,0.01041235,0.0001198221,0.0001441695,0.000008565964,0.00008577001,0.0000242354,0.000004876184],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4927517,"threshold_uncertainty_score":0.8403048,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02847940979912192,"score_gpt":0.2731702515408439,"score_spread":0.244690841741722,"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."}}