{"id":"W4402524684","doi":"10.1145/3696009","title":"Artificial Intelligence and the Future of Evaluation: From Augmented to Automated Evaluation","year":2024,"lang":"en","type":"article","venue":"Digital Government Research and Practice","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Artificial intelligence; Computer science","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.008671964,0.0001145463,0.0001241641,0.00007430212,0.0001951259,0.001765012,0.0003593676,0.00004865835,0.00005371488],"category_scores_gemma":[0.004582989,0.00008141436,0.0000271009,0.0008772119,0.0002259152,0.002270017,0.000477184,0.0002430845,0.00008602482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002131109,"about_ca_system_score_gemma":0.0002202089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001433328,"about_ca_topic_score_gemma":0.00003898143,"domain_scores_codex":[0.995066,0.0007196756,0.0003332151,0.0004791129,0.003124646,0.0002773155],"domain_scores_gemma":[0.9940358,0.004705044,0.00007100615,0.0004053025,0.0006511929,0.0001315876],"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":[0.0004136293,0.0001013236,0.00001156639,0.00001804291,0.00006323012,0.00001427853,0.003202456,0.0001630418,0.0005447846,0.2146303,0.001240838,0.7795965],"study_design_scores_gemma":[0.0001013953,0.0003840991,0.0001397978,0.00008083322,0.00003377579,0.00002179914,0.008354261,0.8374634,0.009143619,0.1238484,0.0202911,0.0001374257],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2645188,0.03383702,0.3786055,0.2178137,0.002475846,0.009306395,0.0002883322,0.000735185,0.09241915],"genre_scores_gemma":[0.9978853,0.000255831,0.001354385,0.0001411378,0.0001491641,0.0001100119,0.000008126879,0.000007362894,0.00008863152],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8373004,"threshold_uncertainty_score":0.9992713,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1213552028661894,"score_gpt":0.4269703605473044,"score_spread":0.305615157681115,"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."}}