{"id":"W4220779482","doi":"10.1145/3490395","title":"Identifying the Big Shots—A Quantile-Matching Way in the Big Data Context","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Management Information Systems","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Quantile; Operationalization; Multivariate statistics; Statistic; Matching (statistics); Econometrics; Context (archaeology); Sample size determination; Statistics; Big data; Computer science; Sample (material); Multivariate analysis; Quantile regression; Variable (mathematics); Mathematics; Data mining; Geography","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":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002551772,0.0002301803,0.0001911218,0.0007032446,0.001493967,0.001731193,0.003404436,0.00003962129,0.0001730605],"category_scores_gemma":[0.00003129812,0.0001572482,0.00007308168,0.001706608,0.00004775597,0.004186786,0.000338697,0.0004490896,0.0006105566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007306642,"about_ca_system_score_gemma":0.00001565584,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002367259,"about_ca_topic_score_gemma":0.000373709,"domain_scores_codex":[0.9975269,0.0000897037,0.0007793317,0.0002833494,0.0009917488,0.0003289677],"domain_scores_gemma":[0.9973632,0.0001668598,0.0003899391,0.001995412,0.00007575947,0.000008892223],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001298961,0.0002852716,0.00036187,0.001279203,0.0002084499,0.00001650579,0.003497393,0.05466818,0.000008859848,0.06332733,0.02004255,0.8561745],"study_design_scores_gemma":[0.0004361808,0.000008990645,0.001181201,0.0001202881,0.00009647413,0.00001384977,0.07255983,0.01678549,0.000002729732,0.0006417593,0.9078699,0.0002833216],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01601455,0.0003759071,0.9259416,0.008282329,0.01387114,0.004083749,0.0003299036,0.0004232584,0.03067754],"genre_scores_gemma":[0.9944417,0.00007394384,0.00003621509,0.003843894,0.0003163214,0.0004338351,0.0005267037,0.00001627955,0.0003111323],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9784271,"threshold_uncertainty_score":0.9998059,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1927878425864501,"score_gpt":0.3058364880874943,"score_spread":0.1130486455010442,"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."}}