{"id":"W2593712670","doi":"10.24908/pceea.v0i0.6465","title":"Testing Inter-Rater Reliability in Rubrics for Large Scale Undergraduate Independent Projects","year":2017,"lang":"en","type":"article","venue":"Proceedings of the Canadian Engineering Education Association (CEEA)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Rubric; Deliverable; Reliability (semiconductor); Peer assessment; Consistency (knowledge bases); Supervisor; Inter-rater reliability; Psychology; Computer science; Work (physics); Mathematics education; Engineering; Rating scale; Political science; Systems engineering; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001616312,0.00009777019,0.0001332899,0.0001550472,0.0007046426,0.0003571584,0.000503298,0.0001309753,0.000006422193],"category_scores_gemma":[0.005566831,0.00009846439,0.00006042872,0.0002457126,0.00002518688,0.0004074905,0.00004842726,0.0001634168,0.000002783431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002701858,"about_ca_system_score_gemma":0.0009965551,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.03513374,"about_ca_topic_score_gemma":0.1634684,"domain_scores_codex":[0.9988786,0.00001025464,0.0002271426,0.000188195,0.0003190767,0.0003767586],"domain_scores_gemma":[0.9986012,0.00009281977,0.0004125709,0.0001148574,0.0006606717,0.0001179066],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000001310653,0.00004958868,0.9864773,0.00005302403,0.0000101203,1.399514e-8,0.004944955,0.00001313912,0.0001228739,0.005139172,0.002954476,0.0002340233],"study_design_scores_gemma":[0.000263813,0.00001209517,0.9768862,0.0001267994,0.00001915498,1.014142e-7,0.003047802,0.0008508119,0.0001366334,0.001178514,0.01731946,0.0001586849],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9609917,0.00001240532,0.00001889023,0.01586469,0.00187299,0.001000769,0.00001742369,0.00004371203,0.02017736],"genre_scores_gemma":[0.9950668,0.000003665163,0.001024453,0.00008106647,0.0002179078,0.00009920762,0.000002795231,0.00001494608,0.003489171],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1283346,"threshold_uncertainty_score":0.9712914,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02201015964286919,"score_gpt":0.2958311354151263,"score_spread":0.2738209757722572,"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."}}