{"id":"W4392681534","doi":"10.22318/icls2023.530792","title":"Design and Evaluation of a Conversational Agent for Formative Assessment in Higher Education","year":2023,"lang":"en","type":"article","venue":"Proceedings.","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; Concordia University of Edmonton","funders":"","keywords":"Formative assessment; Conversation; Software walkthrough; Computer science; Psychology; Mathematics education","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":[0.001414505,0.0000454707,0.00006563622,0.0001255934,0.00003818039,0.00004044237,0.00007847975,0.00002040866,0.000005536083],"category_scores_gemma":[0.00003341732,0.0000426774,0.00001234166,0.0002072748,0.000007160784,0.0003182756,0.00002980807,0.00003760092,0.000002715917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009866893,"about_ca_system_score_gemma":0.0001344781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005402363,"about_ca_topic_score_gemma":9.151486e-8,"domain_scores_codex":[0.9993916,0.0000161375,0.000141022,0.0001248584,0.0002414715,0.00008491283],"domain_scores_gemma":[0.9994411,0.00004589891,0.000101532,0.00002726034,0.000370688,0.00001344654],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006567168,0.0000437549,0.003070969,0.0001428621,0.00001526702,5.426765e-8,0.008746906,0.001817255,0.002190005,0.9535196,0.0009484797,0.02949823],"study_design_scores_gemma":[0.0004612365,0.0001172373,0.0694552,0.0001600616,0.00001008213,9.818338e-7,0.001035931,0.9065871,0.002622906,0.0141407,0.005297889,0.0001106715],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3351707,0.0001455376,0.6533679,0.001905434,0.001367894,0.002482034,0.000001375185,0.0001386636,0.005420445],"genre_scores_gemma":[0.9786882,0.000003370578,0.02028688,0.00002604755,0.00003750597,0.0002116871,0.00000203174,0.000002983553,0.0007412734],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9393789,"threshold_uncertainty_score":0.1740334,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1453634086173477,"score_gpt":0.3622131756128345,"score_spread":0.2168497669954868,"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."}}