{"id":"W2056960254","doi":"10.1145/1390334.1390354","title":"A boosting algorithm for learning bipartite ranking functions with partially labeled data","year":2008,"lang":"en","type":"preprint","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Boosting (machine learning); Computer science; Ranking (information retrieval); Machine learning; Artificial intelligence; Learning to rank; Bipartite graph; Labeled data; Algorithm; Training set; Semi-supervised learning; Ranking SVM; Data mining; Theoretical computer science; Graph","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":[0.0007765089,0.0003354989,0.0003852133,0.000207364,0.0004970378,0.0005201616,0.003091066,0.0002028842,0.00001056426],"category_scores_gemma":[0.000264458,0.000298181,0.00006343524,0.0003691389,0.00007993983,0.0008792066,0.0035311,0.0007129078,0.00002647307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007852957,"about_ca_system_score_gemma":0.000476405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007019047,"about_ca_topic_score_gemma":0.00003971206,"domain_scores_codex":[0.9970489,0.0001116779,0.0005020683,0.00145122,0.0004139896,0.0004721658],"domain_scores_gemma":[0.9956051,0.0002862072,0.0004861765,0.003162224,0.0003609806,0.00009928658],"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":[0.00002550175,0.0001725902,0.0006527868,0.0001523842,0.0002540964,0.00002592554,0.0004813622,0.003487464,0.0008993493,0.005103515,0.0290204,0.9597246],"study_design_scores_gemma":[0.000368019,0.00008083178,0.0001066519,0.0001584989,0.00003245263,0.00003107433,0.00001636194,0.924244,0.001582035,0.0004401063,0.07248819,0.0004517196],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00006522394,0.0000786563,0.9944504,0.0006264331,0.0002909936,0.0009104213,0.0001619079,0.002293192,0.001122719],"genre_scores_gemma":[0.004756547,0.0001222079,0.9905991,0.0002053144,0.0002220734,0.0005011755,0.001921652,0.00004427042,0.001627666],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9592729,"threshold_uncertainty_score":0.999947,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08191461973988243,"score_gpt":0.304749296064842,"score_spread":0.2228346763249596,"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."}}