{"id":"W4414922313","doi":"10.1109/iccv51701.2025.00437","title":"Consensus-Driven Active Model Selection","year":2025,"lang":"en","type":"article","venue":"","topic":"Advanced Control Systems Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Model selection; Selection (genetic algorithm); Inference; Benchmark (surveying); Probabilistic logic; Bayesian inference; Active learning (machine learning); Statistical model","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006810463,0.002674106,0.003311669,0.002169943,0.001432513,0.002889324,0.00732308,0.004020776,0.004792969],"category_scores_gemma":[0.01783703,0.001579033,0.002916026,0.001786359,0.00219254,0.003180552,0.00400578,0.00447792,0.00209708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00153646,"about_ca_system_score_gemma":0.00276243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006855296,"about_ca_topic_score_gemma":0.009122908,"domain_scores_codex":[0.9961002,0.001786751,0.0001734645,0.0008978877,0.0007360393,0.0003055601],"domain_scores_gemma":[0.9839364,0.01168493,0.0005728551,0.001381611,0.001992102,0.0004320059],"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":[0.0003253592,0.0001479882,0.001685314,0.0002275619,0.0002049337,0.0001811448,0.0002265642,0.8572798,0.002327657,0.01303578,0.007153773,0.1172042],"study_design_scores_gemma":[0.00001815465,0.0000179344,0.00004778608,0.000009650205,0.000009081926,0.00001381478,0.00001180715,0.9910076,0.0005299592,0.007892667,0.0004343271,0.000007251025],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00924286,0.0003217248,0.9867155,0.000399457,0.00007423609,0.00009666859,0.0002402925,0.001476527,0.001432717],"genre_scores_gemma":[0.4961071,0.0003895662,0.4891858,0.001333901,0.0003133656,0.001192576,0.003571303,0.00128217,0.006624085],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00732308,"threshold_uncertainty_score":0.0360176,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004662843691046648,"score_gpt":0.21524582263793,"score_spread":0.2105829789468834,"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."}}