{"id":"W152303868","doi":"10.1007/978-3-642-21043-3_19","title":"Instance Selection in Semi-supervised Learning","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Classifier (UML); Artificial intelligence; Machine learning; Labeled data; Training set; Naive Bayes classifier; Pattern recognition (psychology); Bayes classifier; Semi-supervised learning; Co-training; Support vector machine","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001188033,0.0004344155,0.0004177812,0.001122294,0.0002424303,0.0003696214,0.002390362,0.0003347186,0.00003868669],"category_scores_gemma":[0.0001959978,0.0004303424,0.00007425261,0.001067727,0.000269172,0.0008826692,0.0006849077,0.001733855,0.00008822178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003561385,"about_ca_system_score_gemma":0.0004243737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001237567,"about_ca_topic_score_gemma":0.0003575567,"domain_scores_codex":[0.9965343,0.00009618239,0.0005216365,0.001580009,0.0006808391,0.0005870717],"domain_scores_gemma":[0.998381,0.0002519366,0.0003027554,0.0007832443,0.0001573509,0.0001237677],"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":[0.000008702386,0.00003298296,0.002977545,0.00003701338,0.000004329417,0.00002878723,0.001394615,0.03283849,0.0003415353,0.02848859,0.000009350184,0.9338381],"study_design_scores_gemma":[0.0003295971,0.0001761015,0.004667238,0.0004066715,0.000003873646,0.00004698294,2.583407e-7,0.9365692,0.00039914,0.05075849,0.005940908,0.0007016098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003303189,0.0002756844,0.9867071,0.0003542539,0.0005887434,0.0002413509,0.000001129285,0.0002582402,0.01124317],"genre_scores_gemma":[0.7411157,0.0001878177,0.2560344,0.0006670209,0.0003717751,0.00002010995,0.0000200834,0.00005573701,0.001527364],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9331365,"threshold_uncertainty_score":0.9998148,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02088768769147848,"score_gpt":0.2428244471884543,"score_spread":0.2219367594969758,"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."}}