{"id":"W4402761492","doi":"10.3390/systems12090380","title":"Learning to Score: A Coding System for Constructed Response Items via Interactive Clustering","year":2024,"lang":"en","type":"article","venue":"Systems","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Social Science Fund of China; Fundo para o Desenvolvimento das Ciências e da Tecnologia; China Scholarship Council; Science and Technology Development Fund","keywords":"Cluster analysis; Coding (social sciences); Computer science; Psychology; Natural language processing; Artificial intelligence; Mathematics; Statistics","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":[],"consensus_categories":[],"category_scores_codex":[0.001160385,0.0002166422,0.0003777111,0.0005362662,0.0001879224,0.0007256545,0.0005843599,0.00007965223,0.00000113339],"category_scores_gemma":[0.0002478018,0.0002040577,0.0001328858,0.0009075409,0.00002517132,0.000640398,0.0002882305,0.000219515,0.00005677059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000543861,"about_ca_system_score_gemma":0.00006920009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004326335,"about_ca_topic_score_gemma":0.000007039757,"domain_scores_codex":[0.9979332,0.0002974781,0.0004809606,0.0006570164,0.0002664913,0.0003648305],"domain_scores_gemma":[0.9983774,0.0007001511,0.0001393342,0.0004643451,0.0001928947,0.0001259174],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007886645,0.00003681165,0.0002227115,0.003380288,0.0006660297,0.0004536914,0.01998943,0.01858346,0.8151386,0.03565552,0.001424985,0.1036598],"study_design_scores_gemma":[0.0001479311,0.0002219886,0.00002198743,0.002099331,0.00002038268,0.0002634147,0.001431782,0.9779459,0.008155003,0.0000896786,0.00928668,0.0003159243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01537026,0.0003060909,0.9793368,0.0001179831,0.001539567,0.0008742446,0.000005247967,0.002210601,0.0002392224],"genre_scores_gemma":[0.9697623,0.000001737554,0.02917317,0.00001793448,0.0001110206,0.000351462,0.000002741221,0.00003540367,0.0005441833],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9593624,"threshold_uncertainty_score":0.8321233,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01578249369765576,"score_gpt":0.2975465830359427,"score_spread":0.2817640893382869,"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."}}