{"id":"W4408209334","doi":"10.1007/978-3-031-84460-7_34","title":"Online Performance Estimation with Unlabeled Data: A Bayesian Application of the Hui-Walter Paradigm","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Hewlett-Packard (Canada)","funders":"","keywords":"Bayesian probability; Artificial intelligence; Estimation; Computer science; Machine learning; Pattern recognition (psychology); Statistics; Mathematics; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007940616,0.001271029,0.002946065,0.001626581,0.0008171826,0.002214542,0.003674205,0.00224908,0.00321548],"category_scores_gemma":[0.02357008,0.001339536,0.001425265,0.002692117,0.002090099,0.005493978,0.002777539,0.004264238,0.0008615649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001234507,"about_ca_system_score_gemma":0.001538717,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003542002,"about_ca_topic_score_gemma":0.003526708,"domain_scores_codex":[0.9963946,0.001802896,0.0001143933,0.0006348141,0.0008484554,0.0002049382],"domain_scores_gemma":[0.9901248,0.007881314,0.0004446072,0.0006760794,0.000704145,0.000168939],"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":[0.0001456932,0.0001353059,0.001102941,0.0002275799,0.0001971345,0.0001276966,0.0003073551,0.3259861,0.001630538,0.4799863,0.006264394,0.1838889],"study_design_scores_gemma":[0.000009404912,0.00002087735,0.0001499384,0.000018964,0.00001464213,0.00002951733,0.00001128361,0.8454234,0.0003167661,0.1529397,0.00104935,0.00001619511],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001379167,0.0001990475,0.9968082,0.0001881995,0.00002995705,0.00001547506,0.00003681811,0.00008086066,0.001262145],"genre_scores_gemma":[0.2855675,0.00191715,0.6993325,0.000487654,0.0007972578,0.000341971,0.0004526803,0.0004227564,0.01068049],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007940616,"threshold_uncertainty_score":0.04199451,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0149057140209545,"score_gpt":0.2434079036249069,"score_spread":0.2285021896039524,"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."}}