{"id":"W2784717050","doi":"10.5539/ies.v11n2p106","title":"Designing Cognitively Diagnostic Assessment for Algebraic Content Knowledge and Thinking Skills","year":2018,"lang":"en","type":"article","venue":"International Education Studies","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Bayesian network; Cognition; Variable (mathematics); Domain knowledge; Causal model; Process (computing); Mathematics education; Concept learning; Psychology; Computer science; Artificial intelligence; Natural language processing; Mathematics; Statistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004515361,0.0001140066,0.0001329073,0.0001256151,0.0003457089,0.0001786173,0.0002601529,0.00002304074,0.000005088335],"category_scores_gemma":[0.001336341,0.0001013631,0.00003834504,0.00007791171,0.00006938745,0.0003199661,0.0001656937,0.0000645974,0.0000243344],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001372654,"about_ca_system_score_gemma":0.0001474735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001382918,"about_ca_topic_score_gemma":0.00000509784,"domain_scores_codex":[0.9991051,0.00005074191,0.0002267399,0.0002941731,0.0001802932,0.0001429525],"domain_scores_gemma":[0.9956872,0.00134827,0.0001454535,0.0000895265,0.002691925,0.00003760231],"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":[0.00000680583,0.00033199,0.02415191,0.0000598147,0.0005194075,0.000001290104,0.02617561,0.000008424833,0.0009968583,0.8139604,0.005573573,0.1282139],"study_design_scores_gemma":[0.001853707,0.00107474,0.181129,0.003727065,0.0001217928,0.00010401,0.03051454,0.005285384,0.02105719,0.09540771,0.6583356,0.001389251],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03862768,0.001796,0.9476156,0.001598376,0.007736325,0.0003170645,0.000002779052,0.00007789412,0.002228292],"genre_scores_gemma":[0.9070271,0.00009497449,0.08354027,0.0004553854,0.00113929,0.0002433322,0.000004404505,0.000009610646,0.007485596],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8683994,"threshold_uncertainty_score":0.4133468,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0916243917569757,"score_gpt":0.4011516109462748,"score_spread":0.3095272191892992,"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."}}