{"id":"W2007800125","doi":"10.1007/s10115-014-0801-8","title":"Greedy column subset selection for large-scale data sets","year":2014,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Column (typography); Selection (genetic algorithm); Greedy algorithm; Algorithm; Representation (politics); Matrix (chemical analysis); Big data; Data mining; Artificial intelligence; Frame (networking)","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":[0.0007320938,0.00008673998,0.0001266225,0.0001085761,0.0002348054,0.0003448351,0.000328499,0.00007902023,0.000003709845],"category_scores_gemma":[0.00004847067,0.00007744155,0.00001927135,0.0001844764,0.000007396207,0.004973713,0.0001557144,0.00005134826,0.0002549935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001499206,"about_ca_system_score_gemma":0.00002943726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001627208,"about_ca_topic_score_gemma":0.00003918016,"domain_scores_codex":[0.9992038,0.00005273776,0.0002957737,0.0001589344,0.0001164045,0.0001723701],"domain_scores_gemma":[0.9991722,0.00006418781,0.0001260481,0.0003340843,0.0002315723,0.00007186917],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003391548,0.0001196274,0.002830514,0.001084592,0.00003762953,7.303117e-8,0.008913418,0.00007722973,0.0003689968,0.03764538,0.7684908,0.1803978],"study_design_scores_gemma":[0.0003450435,0.00003966329,0.0002281483,0.00003488137,0.000002941352,0.000006588812,0.0001155451,0.5118001,0.0001191665,0.00005176305,0.4871836,0.00007257593],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006806211,0.0001437134,0.979907,0.0001332299,0.001066995,0.0005097776,0.00009775646,0.0001746528,0.01116068],"genre_scores_gemma":[0.9927744,0.00004809724,0.004756309,0.0003713118,0.0002722622,0.0001466582,0.0009694624,0.000008039655,0.0006534522],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9859682,"threshold_uncertainty_score":0.3605822,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02411245776584549,"score_gpt":0.2674305953687463,"score_spread":0.2433181376029008,"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."}}