{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008206872,0.000121466,0.0002443503,0.0002469594,0.0005251443,0.0008792608,0.00139676,0.00008331259,0.0000133933],"category_scores_gemma":[0.001129798,0.00009840656,0.00001966051,0.000552252,0.0002145713,0.001691398,0.0009282492,0.001243916,0.00001533494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005180987,"about_ca_system_score_gemma":0.0001243438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002181821,"about_ca_topic_score_gemma":0.0003532617,"domain_scores_codex":[0.9965844,0.001104177,0.000601707,0.0004972544,0.0008395939,0.000372914],"domain_scores_gemma":[0.9976065,0.00076932,0.0002122691,0.0006976732,0.000463475,0.0002507427],"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":[0.0000959222,0.0004789958,0.01767422,0.000004650558,0.00002506583,0.00005771682,0.007070971,0.00004868398,0.004432799,0.0008270133,0.00009016633,0.9691938],"study_design_scores_gemma":[0.0005838975,0.009978671,0.03807912,0.0001810655,0.00004647127,0.0004018891,0.03539537,0.828493,0.02771812,0.01682809,0.04146965,0.0008246821],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9187421,0.0003125917,0.07779205,0.002840231,0.00004998219,0.0001687351,0.000004450316,0.00004600145,0.00004390362],"genre_scores_gemma":[0.9709637,0.0003237753,0.02813894,0.0000260184,0.0004920706,0.000003074904,0.000006676139,0.000009830418,0.00003593014],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9683691,"threshold_uncertainty_score":0.8478733,"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."}}