{"id":"W3022049020","doi":"10.1007/s11004-017-9695-9","title":"Optimizing Infill Drilling Decisions Using Multi-Armed Bandits: Application in a Long-Term, Multi-Element Stockpile","year":2017,"lang":"en","type":"article","venue":"Mathematical Geosciences","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; AngloGold Ashanti; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Newmont Corporation; Barrick Gold Corporation","keywords":"Stockpile; Infill; Drilling; Drill; Computer science; Term (time); Sequence (biology); Data mining; Mining engineering; Petroleum engineering; Geology; Operations research; Civil engineering; Engineering; Mechanical engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000865933,0.0001814517,0.0002693226,0.0001777151,0.0003437419,0.0002740246,0.0005248602,0.00008583969,0.00004177851],"category_scores_gemma":[0.0007220199,0.0001566985,0.00006106259,0.0001898569,0.0001053645,0.0003648185,0.0001062463,0.0001683537,0.00002104453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008010487,"about_ca_system_score_gemma":0.00001786269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003077521,"about_ca_topic_score_gemma":0.00004124989,"domain_scores_codex":[0.9985456,0.00003216285,0.0004501628,0.0002749662,0.0003144892,0.0003826004],"domain_scores_gemma":[0.9989735,0.0002589982,0.00008452709,0.0005100212,0.00004008642,0.0001327998],"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":[0.000001618463,0.00006043409,0.005705043,0.00006288542,0.000006421795,0.000003613708,0.0005343265,0.9872125,0.002431456,0.000141503,0.000001480138,0.003838753],"study_design_scores_gemma":[0.00047431,0.000008899779,0.02043073,0.0001972254,0.000007433431,0.000002884264,0.00006341687,0.9777355,0.000582231,0.0002706541,0.0000331427,0.0001935922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3989648,0.00006044933,0.6004355,0.00001113031,0.0001311409,0.0002113518,0.000003154752,0.00008514756,0.0000973192],"genre_scores_gemma":[0.5957929,0.00002012812,0.4040608,0.000004126098,0.00002763582,0.00003477207,0.000002043749,0.00001515315,0.00004247457],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.1968281,"threshold_uncertainty_score":0.6389978,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08718930538874528,"score_gpt":0.3697845879833213,"score_spread":0.282595282594576,"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."}}