{"id":"W1599956645","doi":"10.21427/d7q89w","title":"Off to a Good Start: Using Clustering to Select the Initial Training Set in Active Learning","year":2010,"lang":"en","type":"article","venue":"Arrow - TU Dublin (Technological University Dublin)","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Science Foundation Ireland; Canada Millennium Scholarship Foundation","keywords":"Cluster analysis; Computer science; Artificial intelligence; Set (abstract data type); Selection (genetic algorithm); Task (project management); Machine learning; Process (computing); Nondeterministic algorithm; Sample (material); Data mining; Algorithm; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001035355,0.0003015244,0.0003558459,0.0007790803,0.0006864925,0.0002762102,0.002153036,0.0003447915,0.00006319025],"category_scores_gemma":[0.001013929,0.0002580531,0.0001121939,0.003007722,0.0001645809,0.0006454007,0.001563898,0.002484736,0.00006944108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001492267,"about_ca_system_score_gemma":0.0001582929,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002154936,"about_ca_topic_score_gemma":0.0005088649,"domain_scores_codex":[0.9973863,0.0003071251,0.0002654044,0.0008445539,0.0004006429,0.0007960181],"domain_scores_gemma":[0.9985366,0.0003700586,0.0001313135,0.0005818813,0.000127951,0.0002521855],"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":[0.0003856772,0.0004093532,0.00270098,0.00002668546,0.000112308,0.001222312,0.02250016,0.08855725,0.03099315,0.08815975,0.0002013891,0.764731],"study_design_scores_gemma":[0.001650229,0.0007747879,0.002898045,0.00008522245,0.0000202596,0.0001565223,0.006676255,0.9290894,0.002260044,0.000894981,0.05456957,0.0009246567],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7809493,0.000004523214,0.2105579,0.006288461,0.0002319119,0.0003155147,0.000005852067,0.0006460947,0.001000476],"genre_scores_gemma":[0.9567554,0.00000218779,0.04241782,0.0004629464,0.00008942999,0.000003096115,0.000004511588,0.00001571001,0.0002489202],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8405322,"threshold_uncertainty_score":0.9999872,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03836575112352052,"score_gpt":0.2732255230646223,"score_spread":0.2348597719411018,"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."}}