{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001345159,0.0005842076,0.0004660275,0.0007992058,0.0001239083,0.0008016542,0.0005291912,0.0005787972,0.002845782],"category_scores_gemma":[0.01425442,0.0003410376,0.0003523988,0.0003975167,0.0005645776,0.00125066,0.001146592,0.0009605894,0.0004931166],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003002477,"about_ca_system_score_gemma":0.0003344217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005077094,"about_ca_topic_score_gemma":0.0004969661,"domain_scores_codex":[0.9986221,0.0002148895,0.0001379489,0.0004943431,0.0004270092,0.0001037706],"domain_scores_gemma":[0.9878448,0.005146184,0.002782669,0.002867191,0.0008146547,0.0005445164],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.002251212,0.001177976,0.1406444,0.0005117757,0.000336319,0.0001248956,0.001199997,0.00553369,0.6522803,0.002055887,0.0002580258,0.1936255],"study_design_scores_gemma":[0.00003357415,0.002332894,0.8737291,0.00002799666,0.0001302023,0.0003100303,0.0001078831,0.01018635,0.1103952,0.001828908,0.0008723821,0.00004536989],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9843004,0.0001580697,0.01222233,0.00002067708,0.00001020669,0.0001081659,0.0002414197,0.0001488406,0.002789843],"genre_scores_gemma":[0.9924947,0.00005027051,0.005419164,0.00001554422,0.00000625902,0.0001051297,0.0003251758,0.00005514126,0.001528602],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002845782,"threshold_uncertainty_score":0.009520113,"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."}}