{"id":"W2063517468","doi":"10.1109/icdm.2013.155","title":"Distributed Column Subset Selection on MapReduce","year":2013,"lang":"en","type":"article","venue":"","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Benchmark (surveying); Column (typography); Selection (genetic algorithm); Big data; Set (abstract data type); Representation (politics); Preprocessor; Data set; Random projection; External Data Representation; Matrix (chemical analysis); Data mining; Algorithm; Theoretical computer science; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007104456,0.0009875209,0.001168072,0.0006810296,0.0008251498,0.000959059,0.001637955,0.000419278,0.002318955],"category_scores_gemma":[0.001859243,0.0004012006,0.0008021332,0.001198341,0.0003653844,0.001016007,0.001186344,0.0006948735,0.001141149],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004790257,"about_ca_system_score_gemma":0.001551941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005839643,"about_ca_topic_score_gemma":0.008835742,"domain_scores_codex":[0.9993393,0.0001575763,0.00003114583,0.0001579763,0.0002298731,0.00008412983],"domain_scores_gemma":[0.9992495,0.0002088808,0.00003613247,0.0002602638,0.0001808558,0.00006437281],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007493183,0.0003991327,0.002475049,0.0002838998,0.0001807416,0.0004110883,0.0002408406,0.3477544,0.02544202,0.007924133,0.03497676,0.5791626],"study_design_scores_gemma":[0.00007239141,0.00008886871,0.0005339684,0.000005953361,0.00002176408,0.0001531996,0.0001529411,0.9697017,0.01012926,0.01353504,0.005586628,0.00001836649],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02934589,0.0003507638,0.9604458,0.0002831737,0.00008482016,0.0002636913,0.0006123878,0.00657995,0.002033452],"genre_scores_gemma":[0.3430701,0.0002917439,0.6476064,0.0002711798,0.0001032611,0.0005701009,0.003407611,0.0004369031,0.004242631],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005839643,"threshold_uncertainty_score":0.01161128,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01050007881208143,"score_gpt":0.2134554219615589,"score_spread":0.2029553431494775,"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."}}