{"id":"W4385638295","doi":"10.1016/j.jocs.2023.102119","title":"A framework for the comparison of errors in agent-based models using machine learning","year":2023,"lang":"en","type":"article","venue":"Journal of Computational Science","topic":"Opinion Dynamics and Social Influence","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"University at Buffalo; Thompson Rivers University; George Mason University","keywords":"Soar; Computer science; Artificial intelligence; Machine learning; Classifier (UML); Perception; Decision tree; Psychology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007160596,0.00004060038,0.000113487,0.0001160337,0.0001904546,0.00003320909,0.0002085821,0.00001097444,0.00000560254],"category_scores_gemma":[0.00004436439,0.00003014146,0.00006611588,0.0006209759,0.0001272322,0.0001363497,0.00002348816,0.0001435868,3.131113e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002680078,"about_ca_system_score_gemma":0.0002679061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005797197,"about_ca_topic_score_gemma":0.000001494882,"domain_scores_codex":[0.999249,0.00002093518,0.0002783696,0.00005749058,0.0002866656,0.0001075416],"domain_scores_gemma":[0.9989001,0.0004893049,0.0003254325,0.00003136054,0.0002236864,0.00003012153],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007008866,0.00002255025,0.02727663,0.000002326751,0.000004323101,9.409319e-8,0.0004551059,0.9215137,0.0000915825,0.04960017,0.000002485087,0.001023971],"study_design_scores_gemma":[0.0001337725,0.00002647477,0.007256666,0.00003644056,0.000003212472,1.347836e-7,0.0003934397,0.8681478,0.00003892354,0.1239195,0.00001562799,0.00002804148],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4998094,0.00001679674,0.4997996,0.0002223258,0.00009535364,0.00003890418,0.000004101445,0.000001339756,0.00001216473],"genre_scores_gemma":[0.9724978,5.485368e-7,0.02742922,0.00001981208,0.00004527307,8.958512e-7,0.000001420388,0.000002661636,0.000002367721],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4726884,"threshold_uncertainty_score":0.1464842,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0837010296547493,"score_gpt":0.4056319968579816,"score_spread":0.3219309672032323,"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."}}