{"id":"W1862540101","doi":"10.19173/irrodl.v15i5.1857","title":"Evaluating the validity and applicability of automated essay scoring in two massive open online courses","year":2014,"lang":"en","type":"article","venue":"The International Review of Research in Open and Distributed Learning","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Bill and Melinda Gates Foundation","keywords":"Rubric; Grading (engineering); Massive open online course; Higher education; Computer science; Mathematics education; Open education; Distance education; Psychology; Multimedia; Medical education; World Wide Web; Engineering; Medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01865322,0.00008276411,0.0002890234,0.0000759673,0.0001435348,0.0002582001,0.002400777,0.00001904357,0.00001023064],"category_scores_gemma":[0.006918816,0.00005026059,0.00002586146,0.0005963061,0.0002187571,0.0002451396,0.002852481,0.0006063137,0.000001040703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006036355,"about_ca_system_score_gemma":0.0002099582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008161746,"about_ca_topic_score_gemma":0.00007175294,"domain_scores_codex":[0.9967276,0.001756804,0.0004398526,0.0002818669,0.0006068381,0.0001870798],"domain_scores_gemma":[0.996218,0.00277656,0.0002499812,0.0003329127,0.0003792271,0.00004329432],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001686402,0.0007695609,0.5345839,0.00322724,0.00009093915,0.00001154946,0.001101452,0.03749586,0.0008078322,0.09982894,0.0003431487,0.321571],"study_design_scores_gemma":[0.0007029037,0.0001408604,0.03844682,0.005420407,0.000005977431,0.00000533073,0.0005869786,0.9479195,0.00006010429,0.00568956,0.000944819,0.00007675891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9500105,0.002441497,0.004733186,0.03973245,0.00006319938,0.001325305,0.00003629532,0.0000309063,0.001626704],"genre_scores_gemma":[0.9960508,0.001770357,0.001973496,0.00007487328,0.0000223406,0.0000265861,0.00003080184,0.000003947896,0.00004675675],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9104236,"threshold_uncertainty_score":0.8282969,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1986828325979672,"score_gpt":0.5550126832509729,"score_spread":0.3563298506530057,"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."}}