{"id":"W2125592902","doi":"10.1613/jair.1509","title":"Learning From Labeled And Unlabeled Data: An Empirical Study Across Techniques And Domains","year":2005,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":97,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Labeled data; Semi-supervised learning; Relevance (law); Independence (probability theory); Selection (genetic algorithm); Empirical research; Bivariate analysis; Process (computing); Selection bias","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07462388,0.001142854,0.001248782,0.006404977,0.002042362,0.003164663,0.002321455,0.002626695,0.001118234],"category_scores_gemma":[0.3005234,0.0006709936,0.001561848,0.007555592,0.004770027,0.007988516,0.003250567,0.003153588,0.0006037896],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001657993,"about_ca_system_score_gemma":0.001018512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001996029,"about_ca_topic_score_gemma":0.003070139,"domain_scores_codex":[0.9021531,0.07004455,0.004660438,0.007672345,0.01459388,0.0008755882],"domain_scores_gemma":[0.3241137,0.6103453,0.01903173,0.02687059,0.01784821,0.0017905],"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":[0.002064988,0.002729457,0.4093144,0.003875118,0.002519568,0.0004555163,0.006322849,0.05768108,0.00202441,0.01907527,0.01400519,0.4799322],"study_design_scores_gemma":[0.0006475797,0.005757357,0.4448055,0.006130484,0.002020629,0.006773097,0.02326671,0.3372336,0.01271522,0.08543523,0.07455759,0.0006569715],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8431463,0.02452665,0.1109241,0.003438853,0.0002914163,0.0008704404,0.001518103,0.0003439657,0.01494016],"genre_scores_gemma":[0.9196181,0.006358972,0.06752194,0.0008059692,0.0002885,0.0004767551,0.003426344,0.0002463437,0.001257105],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07462388,"threshold_uncertainty_score":0.3946535,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2839496994906822,"score_gpt":0.524008033142466,"score_spread":0.2400583336517838,"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."}}