{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001184844,0.0001856021,0.0003972688,0.000227385,0.0003159071,0.000239082,0.002041476,0.00009173244,0.000004141956],"category_scores_gemma":[0.0002654808,0.0001423515,0.0001143703,0.0005069522,0.00007220173,0.0002452955,0.0005857002,0.0001810728,0.000003993523],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001407437,"about_ca_system_score_gemma":0.0001516596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004157473,"about_ca_topic_score_gemma":0.0008958222,"domain_scores_codex":[0.9982452,0.0001258186,0.0005788227,0.0003224392,0.0003558368,0.0003718315],"domain_scores_gemma":[0.9979025,0.0003662617,0.0003879356,0.0008314984,0.0004064696,0.000105297],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006393393,0.0004530763,0.02736752,0.0001216745,0.0001916949,0.000002476228,0.01071736,0.01186617,0.04005758,0.8529661,0.004368918,0.05182354],"study_design_scores_gemma":[0.0008960004,0.002251265,0.1258584,0.00101256,0.00009258389,0.00002975062,0.002598552,0.6336214,0.2139714,0.002342936,0.01660739,0.00071777],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04086866,0.0005987241,0.95465,0.001789185,0.0002977531,0.001420098,0.000007896457,0.0001811676,0.0001864981],"genre_scores_gemma":[0.7453173,0.00000558611,0.2533207,0.0002960915,0.00007684233,0.0002752506,8.992616e-7,0.00001575075,0.0006915866],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8506231,"threshold_uncertainty_score":0.6284883,"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."}}