{"id":"W4417471048","doi":"10.1109/nss/mic/rtsd57106.2025.11286722","title":"AllMetrics: A Unified Python Library for Standardized Metric Evaluation in Machine Learning","year":2025,"lang":"","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Teck (Canada); University of British Columbia","funders":"","keywords":"Python (programming language); Standardization; Metric (unit); Debugging; Modular design; Modular programming; Product metric; Performance metric","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.007055,0.0004019085,0.0005964548,0.004193504,0.0004108326,0.001072488,0.001218084,0.0002857818,0.0003983745],"category_scores_gemma":[0.006987881,0.0003969446,0.0001981323,0.0120304,0.00005576681,0.00164366,0.0005693947,0.0008180885,0.00003516714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003215997,"about_ca_system_score_gemma":0.00124463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000226529,"about_ca_topic_score_gemma":0.00005605282,"domain_scores_codex":[0.9942572,0.001730008,0.001119985,0.001313663,0.0009517089,0.0006274527],"domain_scores_gemma":[0.9960137,0.002014308,0.0004433992,0.0009997451,0.0003892899,0.0001395561],"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":[0.0003098869,0.0002473858,0.01636008,0.0002176446,0.00007087654,0.000002156629,0.0003417569,0.007384425,0.0001027944,0.06962711,0.002943757,0.9023921],"study_design_scores_gemma":[0.00394302,0.0002510333,0.01172395,0.000126489,0.00009231547,0.000001065388,0.00007794446,0.8367649,0.0003692632,0.003703862,0.1426179,0.0003281845],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001642868,0.006681958,0.9513879,0.007384094,0.0009982955,0.002004446,0.00005478604,0.0004463442,0.02939935],"genre_scores_gemma":[0.8933452,0.001236208,0.0843677,0.0006543641,0.0001070757,0.0002674123,0.0008806355,0.00005197114,0.01908944],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.902064,"threshold_uncertainty_score":0.9999645,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03454321820544654,"score_gpt":0.3235457328130359,"score_spread":0.2890025146075894,"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."}}