{"id":"W4412128547","doi":"10.1109/cism64958.2025.11060864","title":"Defining and Benchmarking a Symmetric Kappa+ Prequential Error Metric on Shifting Imbalanced Streaming Data with Label Budgets","year":2025,"lang":"en","type":"article","venue":"","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Benchmarking; Kappa; Metric (unit); Computer science; Streaming data; Data mining; Mathematics; Economics; Operations management","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":[0.01581415,0.001102877,0.001278424,0.001929546,0.0008797403,0.00218342,0.002453864,0.002162261,0.0008201607],"category_scores_gemma":[0.07338665,0.0002890633,0.0006291692,0.001879365,0.001668601,0.00344766,0.002288972,0.001950133,0.0005496418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001994063,"about_ca_system_score_gemma":0.002770228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004597679,"about_ca_topic_score_gemma":0.004552735,"domain_scores_codex":[0.9911747,0.002839543,0.0008730783,0.001810451,0.002804904,0.0004973412],"domain_scores_gemma":[0.9590364,0.02121926,0.003620216,0.006642081,0.008015181,0.001466868],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001556927,0.0006086141,0.0312665,0.0006024085,0.0002985725,0.0002671086,0.0004976415,0.6108159,0.01451711,0.02144973,0.01256739,0.3055522],"study_design_scores_gemma":[0.0000398281,0.0005489866,0.004974814,0.0000515528,0.00002103374,0.0002021633,0.0001882424,0.968978,0.007302857,0.01579943,0.001848482,0.00004468813],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3887574,0.001985875,0.5967536,0.001365592,0.0006417194,0.0003665857,0.001528711,0.003200656,0.005399786],"genre_scores_gemma":[0.8138165,0.0003026334,0.1813308,0.0002614408,0.0002046281,0.0002209005,0.002007274,0.0003784405,0.001477357],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01581415,"threshold_uncertainty_score":0.0836342,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02296950921326816,"score_gpt":0.2983363388782921,"score_spread":0.2753668296650239,"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."}}