{"id":"W4416940015","doi":"10.1007/s41060-025-00885-x","title":"Sequential Bayesian estimation of the F1 score using the Dirichlet-multinomial model","year":2025,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University; University of Manitoba","funders":"","keywords":"Benchmark (surveying); Metric (unit); Bayesian probability; Sample (material); Point estimation; Sample size determination; Bayesian inference; Prior probability; Class (philosophy)","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":[0.001345326,0.00006034591,0.00008920796,0.0002210985,0.0001639889,0.0002985689,0.005112322,0.0000212716,8.938595e-7],"category_scores_gemma":[0.000529138,0.00003516991,0.00003052485,0.0006140284,0.0004593029,0.002279053,0.001238432,0.0001315897,1.398461e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009048893,"about_ca_system_score_gemma":0.0008571147,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001680259,"about_ca_topic_score_gemma":0.000003436624,"domain_scores_codex":[0.9985131,0.00002869056,0.0003734988,0.0001687349,0.0008238802,0.00009206664],"domain_scores_gemma":[0.9980291,0.00006625673,0.0004499058,0.0006145455,0.0008124092,0.00002776375],"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":[0.00005759231,0.0003008887,0.008895353,0.00003909379,0.0002569002,0.00001364405,0.001031861,0.1359005,0.1141678,0.4787115,0.007291285,0.2533336],"study_design_scores_gemma":[0.0001042734,0.000006354243,0.0009801657,0.0000644358,0.00001692318,0.00002514321,0.00002513477,0.9864206,0.00774842,0.004370196,0.0002033753,0.00003492231],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01384,0.00002472846,0.9815343,0.004035373,0.0003492076,0.00005013507,0.00004151595,0.00000591308,0.0001188541],"genre_scores_gemma":[0.8990269,0.00003298972,0.1005598,0.0003168555,0.00004137453,2.313166e-7,0.000002765982,0.000001403404,0.00001771148],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8851869,"threshold_uncertainty_score":0.9500051,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0841653532904757,"score_gpt":0.3783429684597155,"score_spread":0.2941776151692398,"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."}}