{"id":"W1842811255","doi":"","title":"Using the Attribute Hierarchy Method to Make Diagnostic Inferences about Examinees' Cognitive Skills in Algebra on the SAT.","year":2008,"lang":"en","type":"article","venue":"Open Access Journals at BC (Boston College)","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Task (project management); Cognition; Computer science; Hierarchy; Sample (material); Set (abstract data type); Cognitive model; Natural language processing; Think aloud protocol; Test (biology); Salient; Artificial intelligence; Psychology; Human–computer interaction; Usability; Programming language","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":["sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.003989313,0.0004056504,0.0006035861,0.0003867263,0.001904841,0.002407974,0.005428274,0.0001106009,0.0003054474],"category_scores_gemma":[0.001986975,0.0002405044,0.0001497298,0.001969568,0.0001039467,0.001429657,0.003206409,0.0008364883,0.0001465318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000346464,"about_ca_system_score_gemma":0.0003575816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001449485,"about_ca_topic_score_gemma":0.0003989139,"domain_scores_codex":[0.9949213,0.001813909,0.0008461109,0.0007188335,0.0009421072,0.0007577896],"domain_scores_gemma":[0.9901998,0.007946792,0.0005711687,0.0006509158,0.0003982041,0.0002331282],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004484987,0.001396773,0.5424395,0.0000934247,0.0008768533,0.004148818,0.03278947,0.0692484,0.002636759,0.2483254,0.01478796,0.08280819],"study_design_scores_gemma":[0.002499799,0.0007926947,0.8206809,0.006953978,0.00009398715,0.001454174,0.002518089,0.01259931,0.03112239,0.003571112,0.1154581,0.002255523],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7026511,0.0006657275,0.2815662,0.006374957,0.001021454,0.00252065,0.00004597615,0.00004860134,0.005105355],"genre_scores_gemma":[0.9838547,0.0002264337,0.004257267,0.002841259,0.0002736895,0.0001619251,0.000002300655,0.00003518975,0.008347245],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2812036,"threshold_uncertainty_score":0.9999529,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2088888149135274,"score_gpt":0.4387001033503568,"score_spread":0.2298112884368294,"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."}}