{"id":"W2110046526","doi":"10.1179/1743286312y.0000000026","title":"Where do the data come from?","year":2012,"lang":"en","type":"article","venue":"Mining Technology Transactions of the Institutions of Mining and Metallurgy Section A","topic":"Rock Mechanics and Modeling","field":"Engineering","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Margin (machine learning); Computer science; Quality (philosophy); Data quality; Data collection; Risk analysis (engineering); Data science; Mining engineering; Construction engineering; Engineering; Operations management; Business; Machine learning; Statistics; 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":[0.0002669483,0.0001229362,0.0001923874,0.0002025375,0.000372357,0.00001019072,0.0004926412,0.0001709962,0.00003076536],"category_scores_gemma":[0.00004844493,0.00009010666,0.00006408616,0.0004362329,0.0002133487,0.0002128219,0.000067036,0.0002349998,0.000001087313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002141891,"about_ca_system_score_gemma":0.00003598194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006242962,"about_ca_topic_score_gemma":0.0001749648,"domain_scores_codex":[0.9992463,0.00002400893,0.0002976005,0.0001434882,0.0001091393,0.0001794707],"domain_scores_gemma":[0.9989937,0.00007395941,0.00008414077,0.0007721141,0.0000436877,0.00003242946],"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":[0.00008559766,0.000819111,0.003966419,0.0004506322,0.004059702,0.000002262404,0.01210338,0.4983208,0.1889151,0.03698475,0.002187511,0.2521048],"study_design_scores_gemma":[0.002921254,0.0002860088,0.001498378,0.001628633,0.00301664,0.0005206939,0.03582561,0.5393308,0.09486045,0.001568791,0.317093,0.001449702],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7266804,0.00430336,0.2664308,0.0003521966,0.001361585,0.00010129,0.00004967027,0.0001579816,0.0005627244],"genre_scores_gemma":[0.9882896,0.0004435469,0.01111513,0.000007212085,0.00004505612,0.00001876246,0.00000387408,0.00001406059,0.0000627651],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3149055,"threshold_uncertainty_score":0.3674443,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03909131884719256,"score_gpt":0.2493430628401334,"score_spread":0.2102517439929408,"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."}}