{"id":"W4391759979","doi":"10.1016/j.ijer.2024.102323","title":"Running a double-blind true social experiment with a goal oriented adaptive AI-based conversational agent in educational research","year":2024,"lang":"en","type":"article","venue":"International Journal of Educational Research","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Psychology; Mathematics education; Cognitive psychology; Computer science; Applied psychology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02590438,0.001017823,0.000911544,0.0006324574,0.001838575,0.002118049,0.001610974,0.001722987,0.004056335],"category_scores_gemma":[0.05313149,0.0007720393,0.0005293062,0.0004469233,0.002584583,0.002200613,0.002637419,0.001745511,0.001262908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008618433,"about_ca_system_score_gemma":0.002462038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005137601,"about_ca_topic_score_gemma":0.0006933487,"domain_scores_codex":[0.9697614,0.02339856,0.001336781,0.003096964,0.001397061,0.001009253],"domain_scores_gemma":[0.9046987,0.07159221,0.004842434,0.01091935,0.004545829,0.003401529],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"randomized_trial","study_design_scores_codex":[0.05981651,0.07676661,0.07157159,0.00509835,0.0006462801,0.0009929783,0.08963078,0.02221046,0.2952989,0.01925096,0.004997144,0.3537194],"study_design_scores_gemma":[0.0340629,0.2686448,0.1324059,0.0009340156,0.001123534,0.001168491,0.03246636,0.1440997,0.2278103,0.05822452,0.09775841,0.001301087],"study_design_candidate":"randomized_trial","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8773134,0.00006854007,0.09911587,0.0003296052,0.0002304982,0.01795731,0.0002982172,0.0006361215,0.004050314],"genre_scores_gemma":[0.7539731,0.00006467457,0.1887542,0.0005979626,0.0001290716,0.05382229,0.0001959043,0.00009872619,0.002364042],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02590438,"threshold_uncertainty_score":0.136997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1791202511191977,"score_gpt":0.5047955688891547,"score_spread":0.325675317769957,"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."}}