{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1774387,0.0002950872,0.0006301436,0.001526305,0.001034844,0.001239383,0.004450934,0.000216377,0.00009794051],"category_scores_gemma":[0.2462799,0.0001895488,0.0001385873,0.006938378,0.0009016287,0.001382144,0.002594382,0.001443274,0.000008045399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002828278,"about_ca_system_score_gemma":0.002187843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006638377,"about_ca_topic_score_gemma":0.00006259336,"domain_scores_codex":[0.9544425,0.03695653,0.001563979,0.001892605,0.004008024,0.001136342],"domain_scores_gemma":[0.7379035,0.2559777,0.0003332327,0.004026067,0.001608003,0.000151523],"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":[0.001339655,0.001418917,0.2046855,0.00006563897,0.00003412304,0.00006830843,0.001132679,0.0268007,0.01779584,0.0006226175,0.001714424,0.7443216],"study_design_scores_gemma":[0.001238412,0.0001025593,0.1363046,0.0001278571,0.00001634622,0.000005124619,0.004390987,0.8380329,0.002523912,0.01588469,0.001146303,0.0002262911],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4453298,0.0001525013,0.5523787,0.000743724,0.0004306395,0.0006700474,0.00004192018,0.00004870925,0.0002039629],"genre_scores_gemma":[0.3593526,0.000004349949,0.6399703,0.0001332543,0.0000439366,0.000202729,0.00001461906,0.00001672135,0.0002614993],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8112322,"threshold_uncertainty_score":0.9997974,"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."}}