{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01407555,0.001563181,0.0005393686,0.002214682,0.0007045691,0.001356485,0.001577046,0.001406306,0.001599513],"category_scores_gemma":[0.1369561,0.0005583363,0.0006667745,0.001278315,0.001647435,0.002405012,0.002241756,0.001869943,0.0006999796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008914656,"about_ca_system_score_gemma":0.002071238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00562903,"about_ca_topic_score_gemma":0.005160066,"domain_scores_codex":[0.9904478,0.005363734,0.000530658,0.001407782,0.002090435,0.000159655],"domain_scores_gemma":[0.9077498,0.06617906,0.006517984,0.009108251,0.009639484,0.0008054432],"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":[0.001264743,0.0007482515,0.0384025,0.001387009,0.0006194867,0.0001557648,0.00190149,0.2169283,0.03291552,0.01281909,0.006612649,0.6862451],"study_design_scores_gemma":[0.0002502341,0.000919253,0.02199851,0.0001969361,0.00007005774,0.0003132617,0.0004528481,0.9177688,0.03021304,0.02192582,0.005746931,0.0001442958],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04839064,0.0003336417,0.9478205,0.0002396992,0.00009105108,0.0003857898,0.0003676334,0.001330046,0.001040977],"genre_scores_gemma":[0.3574357,0.0001221189,0.6398956,0.0001376464,0.000022749,0.0005362267,0.0008455305,0.0002400227,0.0007644233],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01407555,"threshold_uncertainty_score":0.07443953,"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."}}