{"id":"W4319991217","doi":"10.4018/ijdwm.316150","title":"Top-K Pseudo Labeling for Semi-Supervised Image Classification","year":2022,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Computer science; Artificial intelligence; Artificial neural network; Machine learning; Key (lock); Semi-supervised learning; Supervised learning; Set (abstract data type); Pattern recognition (psychology); Labeled data; Training set; Convergence (economics); Data mining","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":[0.001318971,0.00008366915,0.0001218506,0.0002217078,0.0002821009,0.0003246436,0.00168639,0.0000209889,0.00001251281],"category_scores_gemma":[0.0003518401,0.00008301834,0.00003532903,0.0001250388,0.00002152141,0.001288048,0.0007167245,0.0002010018,8.954657e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006435085,"about_ca_system_score_gemma":0.0001244867,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001308978,"about_ca_topic_score_gemma":0.000001359873,"domain_scores_codex":[0.9987031,0.00008991107,0.0003862199,0.0002656074,0.0004336693,0.000121476],"domain_scores_gemma":[0.9986292,0.0002437893,0.0004259292,0.0003701909,0.0002755553,0.00005531214],"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":[0.00009380077,0.0001166461,0.002341828,0.00001924252,0.0001090633,0.00003031364,0.001983756,0.0006510102,0.02037375,0.003729369,0.006655739,0.9638955],"study_design_scores_gemma":[0.00123173,0.0001589141,0.001306744,0.00007083478,0.00003087813,0.0005672933,0.001342789,0.8734962,0.0001802448,0.0004898208,0.1209336,0.0001910168],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08214314,0.0004366539,0.9084452,0.007275275,0.001226975,0.00007846697,0.0001681248,0.00004999646,0.0001761837],"genre_scores_gemma":[0.6478644,0.00007686983,0.351046,0.0003492779,0.0003228361,0.00000489933,0.0002718836,0.0000116223,0.00005225621],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9637045,"threshold_uncertainty_score":0.338539,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07460392936922271,"score_gpt":0.345348009688526,"score_spread":0.2707440803193032,"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."}}