{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002770429,0.0002574282,0.0003939792,0.0001054034,0.00006929786,0.0001014792,0.001282039,0.0002705168,4.909516e-7],"category_scores_gemma":[0.00001938568,0.0001654292,0.00002287362,0.0001756384,0.00008114168,0.0001880726,0.0004752599,0.0003892096,2.19648e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004191156,"about_ca_system_score_gemma":0.00007010979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009621216,"about_ca_topic_score_gemma":0.0001790663,"domain_scores_codex":[0.9986217,0.00004139407,0.0004045828,0.0005428331,0.0002237328,0.000165731],"domain_scores_gemma":[0.9974754,0.0002022058,0.0003957788,0.001853517,0.00004679191,0.00002625093],"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":[0.00004023144,0.00006196038,0.003396277,0.0009596972,0.000127913,0.000006138021,0.0002269977,0.1331206,0.000004449219,0.07453033,0.000956415,0.786569],"study_design_scores_gemma":[0.0001226366,0.00004712686,0.0002540023,0.001723351,0.00002713728,0.00001906871,3.467528e-7,0.9929839,0.000006709704,0.001993567,0.0026483,0.0001738134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00005136327,0.001358864,0.9962398,0.0002001204,0.0001744662,0.0006663096,0.00006405608,0.00007698061,0.00116807],"genre_scores_gemma":[0.9490982,0.0003885646,0.04827106,0.0001831691,0.0002695011,0.00006675481,0.0007290453,0.00003808316,0.0009556597],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9490468,"threshold_uncertainty_score":0.6746008,"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."}}