{"id":"W2893182464","doi":"","title":"A Comparison of Features for the Automatic Labeling of Student Answers to Open-Ended Questions.","year":2018,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa; Polytechnique Montréal","funders":"","keywords":"Computer science; Closed-ended question; Information retrieval; Artificial intelligence; Natural language processing; Mathematics; Statistics","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":[0.004330089,0.0009922941,0.001038346,0.004656268,0.0006673164,0.002050864,0.00162863,0.001909625,0.004282482],"category_scores_gemma":[0.01687192,0.0003250402,0.0008016113,0.00224164,0.0002444546,0.002716897,0.001861616,0.001047038,0.0027617],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009211123,"about_ca_system_score_gemma":0.0008537206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005720664,"about_ca_topic_score_gemma":0.01093902,"domain_scores_codex":[0.9967538,0.0009829385,0.0003044773,0.0006940074,0.0009844358,0.0002804597],"domain_scores_gemma":[0.978493,0.01558115,0.0008492926,0.000932992,0.003196956,0.0009466335],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.007965378,0.001257793,0.02924096,0.00111932,0.0004696856,0.0002036377,0.0005239961,0.00273507,0.02201046,0.0007219377,0.02758796,0.9061639],"study_design_scores_gemma":[0.001905431,0.005463675,0.3814246,0.0007551176,0.001363096,0.001497437,0.002459313,0.4626087,0.08561231,0.00589062,0.05063345,0.0003862734],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7178839,0.009326729,0.1947534,0.001158537,0.0009132771,0.001238808,0.02022966,0.03856235,0.01593334],"genre_scores_gemma":[0.8018737,0.001005975,0.1502697,0.0003436983,0.0002244393,0.0008838212,0.03696042,0.0009983052,0.007439987],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005720664,"threshold_uncertainty_score":0.02289993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03268743239961167,"score_gpt":0.3338391229926817,"score_spread":0.30115169059307,"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."}}