{"id":"W4388306673","doi":"10.1002/ev.20564","title":"Artificial intelligence and the future of evaluation education: Possibilities and prototypes","year":2023,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Fraser Health","funders":"","keywords":"Chatbot; Evaluation methods; Engineering ethics; Literacy; Computer science; Program evaluation; Management science; Psychology; Pedagogy; Artificial intelligence; Political science; Engineering","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":[0.01728557,0.00009295601,0.0001587205,0.0003258435,0.0003833795,0.0001679127,0.0001099248,0.00005694804,0.0004731944],"category_scores_gemma":[0.003221796,0.00006000196,0.00005839018,0.001034678,0.0001632111,0.0003777951,0.00003314192,0.00006323629,0.00002652376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005495895,"about_ca_system_score_gemma":0.001091945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006165556,"about_ca_topic_score_gemma":0.0003979991,"domain_scores_codex":[0.9969491,0.000518244,0.0005869541,0.0003046232,0.001532963,0.0001080899],"domain_scores_gemma":[0.99639,0.001250022,0.0002604376,0.0002989531,0.001753137,0.00004739401],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009152033,0.00002359094,0.0005221862,0.000009302708,0.0000109287,3.423711e-9,0.002727089,0.0007941752,0.00003930739,0.03605647,0.001988458,0.957737],"study_design_scores_gemma":[0.0004153337,0.00008834241,0.02025618,0.0000169729,0.0001054219,0.000002574249,0.00967973,0.3223081,0.0005779981,0.6381781,0.008294486,0.00007680805],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9249324,0.005009631,0.008771664,0.0379023,0.004190451,0.01217176,0.0000299394,0.0001242143,0.006867656],"genre_scores_gemma":[0.9944193,0.0002849851,0.001026437,0.00009483676,0.0005414897,0.001588974,0.0000429196,0.000008171827,0.001992887],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9576601,"threshold_uncertainty_score":0.5990867,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2331504610129478,"score_gpt":0.5285796286386468,"score_spread":0.295429167625699,"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."}}