{"id":"W2037838730","doi":"10.1177/154193120304700610","title":"Human and Computer-Generated Essay Grades","year":2003,"lang":"en","type":"article","venue":"Proceedings of the Human Factors and Ergonomics Society Annual Meeting","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Grading (engineering); Mathematics education; Latent semantic analysis; Computer science; Psychology; Natural language processing; Engineering","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":[0.006062494,0.0003651089,0.0004376645,0.001715121,0.0003240671,0.002689011,0.000577859,0.0006187924,0.004594974],"category_scores_gemma":[0.084038,0.0001666334,0.0002405793,0.0009478873,0.000501634,0.001170473,0.0008527195,0.0004400478,0.001379045],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004581482,"about_ca_system_score_gemma":0.0002569584,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008614981,"about_ca_topic_score_gemma":0.001244002,"domain_scores_codex":[0.9919317,0.004159642,0.0006440218,0.001395534,0.001710726,0.0001584504],"domain_scores_gemma":[0.9372379,0.04246068,0.007174389,0.004013863,0.007733532,0.001379652],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.01017402,0.001505189,0.4866453,0.0006660222,0.0006320081,0.000389819,0.007720698,0.008251122,0.01716705,0.002624761,0.006947224,0.4572769],"study_design_scores_gemma":[0.000552241,0.004951789,0.9269388,0.0001766175,0.0001919901,0.0007894864,0.002888978,0.0289667,0.01824489,0.003511314,0.01256208,0.0002251019],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9848589,0.0002443069,0.005093325,0.00007387895,0.00008568555,0.0001430959,0.0005754947,0.0003734715,0.008551775],"genre_scores_gemma":[0.9929014,0.00008468761,0.003639994,0.00003930119,0.00002354223,0.00008870972,0.0005574884,0.00003847849,0.002626389],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006062494,"threshold_uncertainty_score":0.03206193,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01983922958457944,"score_gpt":0.2295089546224202,"score_spread":0.2096697250378407,"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."}}