{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02189335,0.001756831,0.002794225,0.002146411,0.001333768,0.003879654,0.005490818,0.003817958,0.002851109],"category_scores_gemma":[0.06913269,0.001445139,0.00173766,0.003344746,0.005011727,0.007461074,0.004901636,0.008376365,0.0009965237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002019707,"about_ca_system_score_gemma":0.002922544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003542143,"about_ca_topic_score_gemma":0.003178076,"domain_scores_codex":[0.9882866,0.006515898,0.000450584,0.002550367,0.001728679,0.000467873],"domain_scores_gemma":[0.9561771,0.03082053,0.003203972,0.007033489,0.002193964,0.0005710026],"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":[0.0002645499,0.0002768972,0.01293407,0.0004986926,0.0002340722,0.0004669869,0.0006301258,0.1771182,0.001769721,0.6182149,0.007664214,0.1799276],"study_design_scores_gemma":[0.00002430195,0.00004612518,0.001016376,0.00008308711,0.00003600124,0.0001769036,0.00007661471,0.5899429,0.0006407641,0.404535,0.003382564,0.0000394134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005203225,0.0004135951,0.9920682,0.001011369,0.00008470585,0.00007554261,0.0002239215,0.0001265411,0.0007929742],"genre_scores_gemma":[0.4237641,0.001886597,0.5627898,0.001838044,0.00139315,0.001281059,0.002358149,0.000225834,0.004463294],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02189335,"threshold_uncertainty_score":0.1157845,"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."}}