{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005866491,0.0002031863,0.0002519581,0.00002954767,0.0009533381,0.0002834237,0.0003731159,0.00008895875,9.060957e-7],"category_scores_gemma":[0.00003002919,0.0001511829,0.0001250063,0.0001219485,0.0001209801,0.0003812545,0.0003063954,0.0002296218,2.648281e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004820993,"about_ca_system_score_gemma":0.00001760033,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008132792,"about_ca_topic_score_gemma":0.000001713955,"domain_scores_codex":[0.9989053,0.00001972703,0.0003134276,0.0003582356,0.0001300078,0.0002733047],"domain_scores_gemma":[0.9993245,0.00003968299,0.0003139691,0.0000931403,0.000156011,0.00007271269],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.000001668225,0.00004445066,0.137774,0.0001758839,0.00009947892,1.398829e-7,0.02980642,0.0001181234,0.03402773,0.7972041,0.0004992065,0.000248756],"study_design_scores_gemma":[0.003420919,0.001477963,0.427532,0.002892824,0.0002421143,0.0001001499,0.06208036,0.02719438,0.3979473,0.02216433,0.05013477,0.004812888],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.998357,0.0001333307,0.0006488932,0.00003026514,0.0001884376,0.0001121992,0.000002289672,0.0000567298,0.0004708397],"genre_scores_gemma":[0.9953195,0.00001283471,0.003925405,0.00004129136,0.00009613979,0.000002617518,4.076141e-7,0.00001443693,0.0005873827],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7750398,"threshold_uncertainty_score":0.7332402,"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."}}