{"id":"W2015688842","doi":"10.1080/09528130903010295","title":"Warning: statistical benchmarking is addictive. Kicking the habit in machine learning","year":2009,"lang":"en","type":"article","venue":"Journal of Experimental & Theoretical Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; National Research Council Canada","funders":"","keywords":"Benchmarking; Computer science; Addiction; Set (abstract data type); Habit; Machine learning; Test (biology); Artificial intelligence; Measure (data warehouse); Psychology; Data mining; Social psychology; Psychiatry; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001677868,0.0002003828,0.0002806414,0.0001724031,0.0002648459,0.0002981327,0.001013515,0.00008272116,0.0004273102],"category_scores_gemma":[0.0006561424,0.0001389889,0.0001121732,0.0004407742,0.0003522598,0.0004225407,0.0001559327,0.001131993,0.00004108958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001105614,"about_ca_system_score_gemma":0.00006359275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001848711,"about_ca_topic_score_gemma":0.000001968152,"domain_scores_codex":[0.9973153,0.0004706288,0.0008691084,0.0003293922,0.0006490539,0.0003665079],"domain_scores_gemma":[0.9983812,0.0006913312,0.0003639679,0.0002948119,0.0001161405,0.0001525546],"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":[0.00009188477,0.0001849358,0.000313997,0.000001549976,0.000008653268,0.00005499535,0.002990052,0.0004102418,0.009732835,0.8472567,0.00003398388,0.1389202],"study_design_scores_gemma":[0.0001153658,0.001597889,0.001405316,0.0001314313,0.00001487034,0.0002116793,0.001315134,0.6883076,0.1017802,0.2036632,0.001137713,0.0003195994],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04075523,0.0006506664,0.9502326,0.005781055,0.0003580335,0.0001339672,0.000002673893,0.00004226702,0.002043497],"genre_scores_gemma":[0.984014,0.000034142,0.01513745,0.0005791128,0.0002104492,0.000002420632,0.000003488336,0.00000899907,0.000009881352],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9432588,"threshold_uncertainty_score":0.5667804,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02424670070729992,"score_gpt":0.3166015831447657,"score_spread":0.2923548824374658,"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."}}