{"id":"W4205761947","doi":"10.1145/3508017.3495533","title":"Conversation-Based Assessments: Real-Time Assessment and Feedback","year":2021,"lang":"en","type":"article","venue":"eLearn","topic":"Innovative Teaching and Learning Methods","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Conversation; Computer science; Test (biology); Conversation analysis; Human–computer interaction; Multimedia; Psychology; Communication","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001343208,0.0001301072,0.0001935737,0.00007277617,0.0001429551,0.00005821558,0.00007424135,0.0001000602,0.006987339],"category_scores_gemma":[0.000111354,0.0001327764,0.0000397849,0.0002453755,0.00006734268,0.00004870412,0.00002993798,0.000442631,0.0003811925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007557395,"about_ca_system_score_gemma":0.0001605146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001021743,"about_ca_topic_score_gemma":0.000001683748,"domain_scores_codex":[0.9974487,0.001582717,0.0001960008,0.0003575855,0.0001728552,0.0002421205],"domain_scores_gemma":[0.9989306,0.0004617066,0.0001087992,0.0003008955,0.0001400077,0.00005793562],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001870242,0.001033324,0.562387,0.00009622247,0.0006991189,0.0003343937,0.006980489,0.0002240164,0.0617016,0.05095524,0.03666727,0.2787342],"study_design_scores_gemma":[0.001588339,0.0001993345,0.9525502,0.00003272254,0.0000356471,0.00001592533,0.001362367,0.001734004,0.0003549128,0.000354062,0.04149752,0.0002749268],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7398568,0.00007019868,0.02722093,0.002073169,0.0006318371,0.0001318441,0.000006199581,0.0002166125,0.2297924],"genre_scores_gemma":[0.9067394,0.00000590333,0.05696665,0.0009024161,0.0001571818,0.00002051159,0.0000929921,0.00003849714,0.03507649],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3901632,"threshold_uncertainty_score":0.9939204,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03762148700075259,"score_gpt":0.4244944663750185,"score_spread":0.386872979374266,"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."}}