{"id":"W2579758603","doi":"","title":"The refinement of a Q-matrix: Assessing methods to validate tasks to skills mapping.","year":2014,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Task (project management); Matrix (chemical analysis); Domain (mathematical analysis); Data mining; Algorithm; Artificial intelligence; Machine learning; Mathematics","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":[0.005012128,0.0003031081,0.000420399,0.0004300124,0.0004931979,0.0006622534,0.001645992,0.0001238968,0.000004748311],"category_scores_gemma":[0.001024429,0.000237146,0.0001751148,0.001002116,0.00003243181,0.000297354,0.0008017155,0.000326756,0.00003539003],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000286456,"about_ca_system_score_gemma":0.0001248224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00246035,"about_ca_topic_score_gemma":0.0001199157,"domain_scores_codex":[0.9966974,0.0006930316,0.0007397518,0.0005697635,0.0005147666,0.0007853015],"domain_scores_gemma":[0.9969766,0.0006280771,0.0003559756,0.001436891,0.0002711595,0.0003313396],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001425673,0.0001441701,0.002623305,0.00004703971,0.00006655099,0.00000897445,0.001913421,0.01504433,0.07266831,0.5646909,0.001722222,0.3410564],"study_design_scores_gemma":[0.0002919633,0.0005031014,0.01643917,0.0004817031,0.0000203422,0.00005732033,0.0003214881,0.135053,0.126626,0.003159472,0.7162384,0.0008080081],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01095245,0.0002249822,0.9811611,0.005393042,0.0004318474,0.0006295846,0.000002560841,0.0003682679,0.0008362225],"genre_scores_gemma":[0.2403422,0.00001063443,0.7538493,0.001269596,0.00014878,0.0002260696,0.000001064168,0.00003307865,0.004119324],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7145162,"threshold_uncertainty_score":0.9670531,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01773638517470293,"score_gpt":0.3055683951158576,"score_spread":0.2878320099411547,"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."}}