{"id":"W4409665275","doi":"10.3758/s13428-025-02658-7","title":"Assessing multiple abilities through process data in computer-based assessments: The multidimensional sequential response model (MSRM)","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Beijing Municipal Social Science Foundation; National Natural Science Foundation of China","keywords":"Computer science; Process (computing); Data mining; Machine learning; Artificial intelligence; 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":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03345891,0.001504328,0.00154134,0.002661581,0.0005281591,0.002990309,0.001292572,0.001278254,0.001643875],"category_scores_gemma":[0.1268557,0.0006139149,0.00178405,0.002482528,0.001332723,0.003636621,0.002260621,0.001911238,0.0005002493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001307001,"about_ca_system_score_gemma":0.003344622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003269728,"about_ca_topic_score_gemma":0.003386293,"domain_scores_codex":[0.9635099,0.02618786,0.00195727,0.002206302,0.005782586,0.0003560082],"domain_scores_gemma":[0.8915884,0.08743748,0.008363213,0.005371884,0.006598308,0.000640676],"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":[0.001434553,0.002656464,0.2399736,0.002260122,0.001593081,0.0001511174,0.005192617,0.08537169,0.00465025,0.03000045,0.001944764,0.6247713],"study_design_scores_gemma":[0.0006730272,0.006913221,0.1983028,0.001723387,0.001009119,0.0005620565,0.003039718,0.6354008,0.009005115,0.136489,0.006279842,0.000601853],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2317968,0.0005170178,0.7590446,0.0004500307,0.0001046493,0.002811183,0.0006002063,0.0006915125,0.003983852],"genre_scores_gemma":[0.6097556,0.0005336435,0.3851506,0.0001775809,0.00003114964,0.003281795,0.0004818331,0.00007570523,0.0005121925],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03345891,"threshold_uncertainty_score":0.1769498,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.920767338243147,"score_gpt":0.759212213405075,"score_spread":0.161555124838072,"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."}}