{"id":"W1596584299","doi":"10.21427/9w8z-hc83","title":"Sweetening the Dataset : Using Active Learning to Label Unlabelled Datasets","year":2021,"lang":"en","type":"article","venue":"Arrow@dit (Dublin Institute of Technology)","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Science Foundation Ireland; Canada Millennium Scholarship Foundation","keywords":"Computer science; Machine learning; Artificial intelligence; Active learning (machine learning); Set (abstract data type); Focus (optics); Supervised learning; Expert system; Training set; Artificial neural network","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":[0.0146689,0.002200813,0.001744877,0.006131118,0.002112161,0.006237699,0.006943865,0.005771848,0.00282456],"category_scores_gemma":[0.03396606,0.001197629,0.002073054,0.004672386,0.00220797,0.007303455,0.006567272,0.006631726,0.003306201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001809096,"about_ca_system_score_gemma":0.001485186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002414922,"about_ca_topic_score_gemma":0.007461219,"domain_scores_codex":[0.9872602,0.00576328,0.000788126,0.002602397,0.003131372,0.0004545642],"domain_scores_gemma":[0.9643289,0.01689806,0.002155072,0.01162853,0.00395519,0.001034128],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001146607,0.0015385,0.00772241,0.0009532011,0.0003599837,0.0004546065,0.001028815,0.06186679,0.01349788,0.02175221,0.09439973,0.7952793],"study_design_scores_gemma":[0.0002994501,0.0004569569,0.003123125,0.0003066208,0.0001377126,0.0004253426,0.0005500471,0.7929457,0.02990235,0.07529261,0.09634205,0.0002179868],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03156393,0.001078793,0.9352165,0.001949089,0.0009360993,0.0009817537,0.006749487,0.01219053,0.009333689],"genre_scores_gemma":[0.08491795,0.0003784854,0.8877905,0.001296649,0.0002940697,0.001068882,0.02016944,0.0008615865,0.003222407],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0146689,"threshold_uncertainty_score":0.07757747,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02440303009430266,"score_gpt":0.2971462182489404,"score_spread":0.2727431881546377,"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."}}