{"id":"W4220804800","doi":"10.31234/osf.io/nzmpe","title":"Task-level and Item-level Components of Procedure Speed-up","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; University of Saskatchewan","keywords":"Task (project management); Computer science; Memorization; Arithmetic; Alphabet; Cognition; Transfer (computing); Benchmark (surveying); Natural language processing; Proxy (statistics); Artificial intelligence; Cognitive psychology; Machine learning; Psychology; Mathematics; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005419847,0.0003318872,0.0005174454,0.0002206127,0.0001689469,0.0001720013,0.001289699,0.0001613549,0.0000996785],"category_scores_gemma":[0.00007940534,0.0003062079,0.0001390131,0.000173751,0.00004611202,0.0001498883,0.003870737,0.0007813831,0.00001813938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009080527,"about_ca_system_score_gemma":0.0001595805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006887004,"about_ca_topic_score_gemma":0.000009045916,"domain_scores_codex":[0.9975371,0.0001280143,0.0005435285,0.0008328245,0.0006365856,0.0003218989],"domain_scores_gemma":[0.9984474,0.0001216118,0.0004468095,0.0007029594,0.0001767441,0.0001044487],"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":[0.00006970218,0.0004475068,0.03899364,0.00413145,0.0006620934,0.0001112384,0.01355146,0.007644059,0.01208858,0.9004093,0.006353524,0.01553747],"study_design_scores_gemma":[0.002578317,0.001193711,0.3243943,0.004520801,0.0001665368,0.0003905714,0.003251847,0.1964706,0.01182644,0.01231225,0.4372251,0.005669442],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3894145,0.001321673,0.5769107,0.0009155936,0.008514791,0.001804807,0.0002094115,0.0006050891,0.02030344],"genre_scores_gemma":[0.8958291,0.00003551073,0.01671851,0.0001177553,0.0001661809,0.00002486365,0.00003257297,0.00003139889,0.08704408],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.888097,"threshold_uncertainty_score":0.999939,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1005097252616164,"score_gpt":0.2863828479125659,"score_spread":0.1858731226509495,"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."}}