{"id":"W1589919686","doi":"","title":"Does Unlabeled Data Provably Help? Worst-case Analysis of the Sample Complexity of Semi-Supervised Learning.","year":2008,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Sample complexity; Computer science; Semi-supervised learning; Homogeneous; Distribution (mathematics); Artificial intelligence; Conjecture; Sample (material); Class (philosophy); Labeled data; Supervised learning; Machine learning; Pattern recognition (psychology); Mathematics; Artificial neural network; Discrete mathematics; Combinatorics","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":[0.002033402,0.0002366982,0.0005220857,0.0003124982,0.0005521429,0.00006801938,0.00258896,0.000101692,0.0002350741],"category_scores_gemma":[0.003443418,0.0001421227,0.0001543339,0.001610324,0.0006481658,0.00033174,0.0009704476,0.0007906125,0.00001529721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002694965,"about_ca_system_score_gemma":0.0002225597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003713163,"about_ca_topic_score_gemma":0.00006921801,"domain_scores_codex":[0.9962797,0.001651878,0.0005228202,0.000748156,0.0004997643,0.0002976503],"domain_scores_gemma":[0.9950982,0.001306794,0.0006724973,0.002539643,0.0002916398,0.00009123523],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002844102,0.0006297041,0.2683807,0.0001671712,0.001054528,0.00005502323,0.009647001,0.01821464,0.005431186,0.6018642,0.0002038829,0.09406758],"study_design_scores_gemma":[0.0005343439,0.0002254615,0.06798401,0.0001015096,0.0002736543,0.00003210279,0.0008228603,0.9206918,0.0008382852,0.005651091,0.002489695,0.0003551994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6035352,0.00006233552,0.3912469,0.001324412,0.0002269512,0.0003558729,0.0001155962,0.0003044562,0.002828205],"genre_scores_gemma":[0.9932922,0.00005684969,0.005183752,0.0000630356,0.00002581341,0.000008339051,0.0002292578,0.00001469927,0.001126092],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9024771,"threshold_uncertainty_score":0.5795596,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1094726326608954,"score_gpt":0.3005835196592879,"score_spread":0.1911108869983926,"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."}}