{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002455962,0.001102914,0.001336711,0.001604271,0.001528371,0.001627731,0.002760504,0.001895491,0.002383179],"category_scores_gemma":[0.007215152,0.0005985104,0.001143005,0.001501067,0.001745242,0.003020918,0.001386247,0.002066164,0.001793425],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00136975,"about_ca_system_score_gemma":0.001514478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002101978,"about_ca_topic_score_gemma":0.002696263,"domain_scores_codex":[0.9955714,0.001615983,0.0002819479,0.001091468,0.001189796,0.0002493222],"domain_scores_gemma":[0.9939873,0.00170031,0.0005779076,0.00181444,0.001759658,0.0001603878],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005924343,0.0003320366,0.002772875,0.0005351981,0.000163219,0.0002583414,0.0006384652,0.1437617,0.03471228,0.03007113,0.015593,0.7705693],"study_design_scores_gemma":[0.00002001808,0.00009422765,0.0004397944,0.000029116,0.00002496694,0.0001742421,0.0000547119,0.9612135,0.01510146,0.01867506,0.004133437,0.00003956849],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006161376,0.000203315,0.9905242,0.0001012217,0.00004918287,0.00008597988,0.0000857398,0.001808724,0.0009802757],"genre_scores_gemma":[0.2876224,0.0002532038,0.7068141,0.0003834145,0.0001316032,0.000480233,0.00116332,0.0005503447,0.00260128],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002760504,"threshold_uncertainty_score":0.01298857,"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."}}