{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005562633,0.000274969,0.0003843625,0.000469454,0.0006401323,0.0001419652,0.002295006,0.0002033833,0.00002785561],"category_scores_gemma":[0.001294055,0.0002285999,0.00006371037,0.002657939,0.0002661206,0.0008014884,0.002152268,0.0009913555,0.00007408447],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006125493,"about_ca_system_score_gemma":0.0002845266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000148314,"about_ca_topic_score_gemma":0.00004973774,"domain_scores_codex":[0.997752,0.0001120611,0.0004403702,0.0007829189,0.0003943252,0.0005183737],"domain_scores_gemma":[0.9976895,0.0001011061,0.0002845503,0.001620577,0.0001942947,0.0001099635],"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":[0.00007447581,0.0007139107,0.001397022,0.0001488673,0.000655351,0.00132041,0.001758917,0.05133095,0.1295281,0.1411381,0.03379196,0.6381419],"study_design_scores_gemma":[0.001421086,0.0002241622,0.0001329146,0.0002436238,0.00006928739,0.0003410819,0.0005119235,0.1724644,0.06912727,0.001966694,0.7528372,0.0006603493],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6193299,0.0009176049,0.3360859,0.03605065,0.003414094,0.0007319869,0.001194453,0.00142807,0.000847299],"genre_scores_gemma":[0.5817611,0.00005855606,0.4149506,0.001085109,0.0002348984,0.00004304073,0.001502678,0.00004657627,0.0003174984],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7190452,"threshold_uncertainty_score":0.9322034,"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."}}