{"id":"W4251182982","doi":"10.2118/174784-ms","title":"Machine Learning as a Reliable Technology for Evaluating Time-Rate Performance of Unconventional Wells","year":2015,"lang":"en","type":"article","venue":"SPE Annual Technical Conference and Exhibition","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Apache (Canada)","funders":"","keywords":"Computer science; Markov chain Monte Carlo; Production (economics); Expression (computer science); Probabilistic logic; Monte Carlo method; Calibration; Econometrics; Artificial intelligence; Machine learning; Data mining; Algorithm; Statistics; Bayesian probability; 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":[],"consensus_categories":[],"category_scores_codex":[0.0007393269,0.000106569,0.0001811993,0.0001258044,0.00004379302,0.00001570362,0.00007114519,0.0001376775,0.00004545763],"category_scores_gemma":[0.000276947,0.0001047867,0.00003343207,0.0001854387,0.00004924237,0.0001639072,0.00003036339,0.0001895493,0.0000189886],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002500798,"about_ca_system_score_gemma":0.0000326878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006582129,"about_ca_topic_score_gemma":6.342401e-7,"domain_scores_codex":[0.9992985,0.0000243895,0.0002434848,0.0001427405,0.0001297087,0.0001611934],"domain_scores_gemma":[0.999478,0.00007233671,0.00004238779,0.00009991392,0.0002453155,0.00006201398],"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":[0.0001661153,0.00003514353,0.001419595,0.00029829,0.0000279508,0.000001344663,0.0001261559,0.9104038,0.06927788,0.007686794,0.0008331266,0.009723788],"study_design_scores_gemma":[0.0006827323,0.0006821954,0.0001709191,0.0001225075,0.00001481872,0.00000658921,0.00006138144,0.9697551,0.01318427,0.01279402,0.002372786,0.0001527253],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9373366,0.0002820775,0.0585722,0.0001934038,0.00007202884,0.0002395281,0.00002143223,0.000385712,0.002896984],"genre_scores_gemma":[0.9782947,0.00009774305,0.0209985,0.000009908624,0.00002979233,0.00002877114,0.00004923926,0.000015676,0.0004757125],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05935124,"threshold_uncertainty_score":0.4273076,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03720973490735065,"score_gpt":0.3105457868435996,"score_spread":0.2733360519362489,"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."}}