{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00004381301,0.00006215245,0.00005354893,0.00003848857,0.00008396462,0.0001581325,0.0001964385,0.00004168298,0.0006369492],"category_scores_gemma":[0.00001418743,0.00005099737,0.00002399244,0.000222334,0.000007794218,0.0004245667,0.00004187381,0.00006405447,0.002838828],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002070824,"about_ca_system_score_gemma":0.00001475566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001693395,"about_ca_topic_score_gemma":0.00001064379,"domain_scores_codex":[0.9994166,0.00002695744,0.00008627208,0.0001915363,0.0001295406,0.00014907],"domain_scores_gemma":[0.9996551,0.00002648522,0.0000249201,0.0001572902,0.0000723699,0.00006387587],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000004786794,0.0001438376,0.0008658486,0.000005608709,0.00000812821,0.000001265661,0.00007209191,0.00009793801,0.02583193,0.006844843,0.9229943,0.04312949],"study_design_scores_gemma":[0.001213284,0.0006651201,0.09485196,0.00007202839,0.000008031305,0.00003448055,0.0001104426,0.3308834,0.4809354,0.02433678,0.06604747,0.0008415728],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4827322,0.000005793812,0.4951528,0.004784435,0.0003671281,0.0003423496,0.000007528025,0.0006080804,0.01599975],"genre_scores_gemma":[0.990654,0.000002878286,0.006667191,0.0009514104,0.00003317467,0.00004807786,0.00003208789,0.000003381253,0.00160782],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8569468,"threshold_uncertainty_score":0.9979376,"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."}}