{"id":"W2034878828","doi":"10.1111/j.1745-3992.2002.tb00087.x","title":"Scoring Examinee Responses for Multiple Inferences: Multiple Scoring in Assessments","year":2002,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Scoring system; Inference; Scale (ratio); Computer science; Psychology; Artificial intelligence; Medicine; Geography","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01608875,0.000165765,0.0002617254,0.0004906423,0.0002692019,0.0004104097,0.000357761,0.00005859238,0.0002495822],"category_scores_gemma":[0.585434,0.0001377767,0.00004555586,0.0009185281,0.00004507967,0.00101933,0.00008038079,0.0001639219,0.00002724147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001047855,"about_ca_system_score_gemma":0.00009514834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003411385,"about_ca_topic_score_gemma":0.0000915038,"domain_scores_codex":[0.9960557,0.0009064197,0.0006670631,0.0005724049,0.001485432,0.0003130113],"domain_scores_gemma":[0.8640235,0.1342553,0.0004048414,0.0003451539,0.0008587765,0.0001124156],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002076816,0.0004573162,0.8855349,0.00002856653,0.00003440274,0.000001689805,0.001180058,0.0001254706,0.001200998,0.0008014815,0.003512766,0.1069147],"study_design_scores_gemma":[0.001186625,0.0002325074,0.8225355,0.0001624404,0.00002507749,0.00002027394,0.005178811,0.005266111,0.0002820428,0.007421266,0.1573713,0.0003180987],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9215936,0.01570768,0.0165434,0.02553661,0.004173244,0.001457987,0.00002701806,0.00007369718,0.01488675],"genre_scores_gemma":[0.8953777,0.0003440425,0.1024071,0.0002137453,0.0003259873,0.0001225874,0.000002183409,0.00001020207,0.001196426],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5693452,"threshold_uncertainty_score":0.5618371,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8659566286900213,"score_gpt":0.5782094015970195,"score_spread":0.2877472270930018,"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."}}