{"id":"W4408404791","doi":"10.1080/01621459.2025.2474266","title":"Positive and Unlabeled Data: Model, Estimation, Inference, and Classification","year":2025,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Inference; Estimation; Artificial intelligence; Computer science; Statistics; Econometrics; Mathematics; Pattern recognition (psychology); Machine learning; Data mining; Economics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000810407,0.00006695437,0.0001684466,0.00008074901,0.0001409564,0.0001781325,0.0004096506,0.00002476412,5.623769e-7],"category_scores_gemma":[0.003408154,0.00004781947,0.00001250694,0.0003422864,0.00007957174,0.0004661695,0.0002081774,0.0002056412,0.000001166039],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001162137,"about_ca_system_score_gemma":0.0001383238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002817657,"about_ca_topic_score_gemma":0.000006722823,"domain_scores_codex":[0.9989254,0.0002517553,0.0003006867,0.0001618454,0.0002671469,0.00009319229],"domain_scores_gemma":[0.9975491,0.001056867,0.0008396143,0.0002797283,0.0002311996,0.00004346434],"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":[0.00003530562,0.00008198412,0.06773099,0.00001763027,0.0001002981,8.207485e-7,0.0002643789,0.0007587898,0.0006963185,0.4565068,0.009321543,0.4644851],"study_design_scores_gemma":[0.0001185423,0.00002738071,0.4039524,0.00001484639,0.00003009621,0.000002172956,0.00001611992,0.580351,0.000006398417,0.01522132,0.0002270934,0.00003261343],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01867495,0.00003716515,0.9675252,0.01331894,0.00007583479,0.00005651931,0.00004353088,0.0000116114,0.0002563012],"genre_scores_gemma":[0.897651,0.00007987376,0.101634,0.0004609972,0.00001689971,0.00000113307,0.00001686139,0.000002328255,0.0001369402],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.878976,"threshold_uncertainty_score":0.4080125,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01785442230205226,"score_gpt":0.3301976577369091,"score_spread":0.3123432354348568,"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."}}