{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008088598,0.0007712873,0.001065801,0.001129431,0.001319078,0.002148249,0.002362572,0.002511701,0.001167175],"category_scores_gemma":[0.02152982,0.0008559296,0.0006554879,0.001377747,0.002434036,0.003658242,0.002291541,0.002279282,0.0008843396],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001251348,"about_ca_system_score_gemma":0.001032054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002039845,"about_ca_topic_score_gemma":0.003430243,"domain_scores_codex":[0.9957098,0.00220699,0.0002411821,0.0007306656,0.0009047387,0.0002066299],"domain_scores_gemma":[0.9829764,0.01068071,0.001075636,0.003105625,0.001897669,0.0002640061],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008523669,0.0003631096,0.004847033,0.0002718089,0.0001570461,0.0001777052,0.001006056,0.5362195,0.01889899,0.04144867,0.002744184,0.3930136],"study_design_scores_gemma":[0.00005060834,0.0001519911,0.0005850111,0.00004028109,0.00002057757,0.00007790432,0.0001044123,0.950217,0.01530314,0.03160395,0.001797413,0.00004777224],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02788655,0.0003113543,0.9696615,0.0003145792,0.00003406033,0.00007969009,0.00002419772,0.0005221413,0.001165936],"genre_scores_gemma":[0.5213808,0.0001947376,0.4759372,0.0003279208,0.00004094152,0.000229821,0.0001470791,0.0002048752,0.001536631],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008088598,"threshold_uncertainty_score":0.04277712,"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."}}