{"id":"W4387163691","doi":"10.1109/icalt58122.2023.00103","title":"Innovating Assessment with Conversational Agents: A Technology-Enhanced Approach to Formative Assessments","year":2023,"lang":"en","type":"article","venue":"","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; Concordia University of Edmonton","funders":"","keywords":"Conversation; Formative assessment; Casual; Computer science; Quality (philosophy); Multimedia; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01100707,0.001074486,0.0006455483,0.002347271,0.0005769155,0.003368936,0.002033053,0.001028935,0.001876243],"category_scores_gemma":[0.03847212,0.0004667226,0.0007276408,0.001124176,0.0008571269,0.003943698,0.002180881,0.001471681,0.0008192815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008452389,"about_ca_system_score_gemma":0.001381213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001066597,"about_ca_topic_score_gemma":0.001719636,"domain_scores_codex":[0.9873757,0.00885377,0.0006324814,0.0008841464,0.002043925,0.0002100361],"domain_scores_gemma":[0.9747244,0.01580753,0.001727338,0.002751461,0.004471107,0.000518064],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000455173,0.001291999,0.00924913,0.0007258614,0.0002022227,0.0002827309,0.009270567,0.01271744,0.04547133,0.01994825,0.001950008,0.8984354],"study_design_scores_gemma":[0.0003205056,0.005303203,0.02569547,0.001170836,0.0007492918,0.00244268,0.005745165,0.6383326,0.1380848,0.0673048,0.1140449,0.0008057202],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02976802,0.0001911873,0.9613593,0.0002712172,0.00006693267,0.001215126,0.00007441897,0.002199293,0.004854516],"genre_scores_gemma":[0.1639691,0.0001480602,0.8326458,0.00008491628,0.00004765248,0.0008897309,0.00009080461,0.0001086335,0.002015361],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01100707,"threshold_uncertainty_score":0.05821162,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03761938246569699,"score_gpt":0.3214596459764846,"score_spread":0.2838402635107876,"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."}}