{"id":"W4412496678","doi":"10.1007/978-3-031-98462-4_33","title":"Modeling Intrinsic Load: Can Item Difficulty Be a Reasonable Proxy?","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Visual and Cognitive Learning Processes","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Proxy (statistics); Machine learning","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004273099,0.0004850958,0.0005030646,0.0004353544,0.0002728764,0.0002039024,0.0009823728,0.0003942472,0.0001793597],"category_scores_gemma":[0.000302014,0.0004201503,0.0001063726,0.000528401,0.0004114407,0.0001046409,0.0004027744,0.00117576,0.00005378938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002837737,"about_ca_system_score_gemma":0.0008413834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002624076,"about_ca_topic_score_gemma":0.0003378063,"domain_scores_codex":[0.9968241,0.00004405757,0.0003885454,0.001431112,0.0006567615,0.000655364],"domain_scores_gemma":[0.9982479,0.0003624115,0.0001474276,0.0005502643,0.0005696826,0.0001222769],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007479302,0.0001052762,0.0002345562,0.0001931756,0.00005712671,0.0001613879,0.004269506,0.01710896,0.00002774489,0.009597546,0.0001643719,0.9680055],"study_design_scores_gemma":[0.002964428,0.001497049,0.0008448664,0.00741197,0.0002337004,0.0003383026,0.00003346434,0.8043956,0.0007771485,0.141254,0.03561909,0.004630376],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002618747,0.001407488,0.9357592,0.001506612,0.00182665,0.0006388358,0.00002580138,0.0002426529,0.05597396],"genre_scores_gemma":[0.9412496,0.00004451428,0.0117933,0.007120119,0.001092856,0.00008477769,0.00004253581,0.00008123079,0.03849106],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9633752,"threshold_uncertainty_score":0.9998251,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02826331486639794,"score_gpt":0.304518845690122,"score_spread":0.2762555308237241,"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."}}