{"id":"W2964327378","doi":"","title":"Analysis of semi-supervised learning with the Yarowsky algorithm","year":2007,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Weighted Majority Algorithm; Computer science; Algorithm; Semi-supervised learning; Supervised learning; Graph; Bootstrapping (finance); Artificial intelligence; Entropy (arrow of time); Machine learning; Unsupervised learning; Wake-sleep algorithm; Mathematics; Theoretical computer science; Generalization error; Artificial neural network","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005232621,0.00009966554,0.0001379769,0.00008312894,0.00007125317,0.00001216423,0.0001797215,0.00007303624,0.00008885781],"category_scores_gemma":[0.00004843375,0.00005816105,0.00009511369,0.0004243726,0.00007792648,0.000002022768,0.00006770971,0.0001313018,0.000003736786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004563579,"about_ca_system_score_gemma":0.00002003147,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003866653,"about_ca_topic_score_gemma":0.00009979052,"domain_scores_codex":[0.9993188,0.00003353595,0.0001858037,0.0001227051,0.0001650127,0.0001740758],"domain_scores_gemma":[0.9994449,0.00003647357,0.0001068752,0.0002831588,0.00008857516,0.0000400285],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003722881,0.0002169861,0.4977961,0.00009547695,0.007998645,0.00001044749,0.002803414,0.08643746,0.1871784,0.0006513777,0.003176691,0.2132627],"study_design_scores_gemma":[0.001870147,0.001788509,0.1542773,0.00002246443,0.002145506,0.0000382273,0.005613187,0.4688791,0.2011157,0.00000833278,0.163269,0.0009725885],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6149768,0.00007141908,0.3607761,0.0001276051,0.00001814957,0.00009021689,0.000002922682,0.00001884343,0.02391798],"genre_scores_gemma":[0.981465,0.00001501215,0.01531282,0.0002774741,0.00004606066,0.000001939821,0.0001030932,0.000011263,0.00276727],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3824416,"threshold_uncertainty_score":0.2371739,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00397787480399339,"score_gpt":0.2359396683324911,"score_spread":0.2319617935284977,"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."}}