{"id":"W1510641421","doi":"","title":"Developing a Taxonomy of Item Model Types to Promote Assessment Engineering","year":2008,"lang":"en","type":"article","venue":"Open Access Journals at BC (Boston College)","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Taxonomy (biology); Context (archaeology); Software; Representation (politics); Artificial intelligence; Information retrieval; Machine learning; 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":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005754453,0.0001919373,0.0003508204,0.0003365374,0.0003789181,0.000306623,0.003845872,0.00008517957,0.00008836069],"category_scores_gemma":[0.00005939413,0.0001806946,0.00006228685,0.0009648566,0.00003640189,0.00184125,0.002873081,0.0002364477,0.00001752304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004158195,"about_ca_system_score_gemma":0.00122213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004426309,"about_ca_topic_score_gemma":0.0000207316,"domain_scores_codex":[0.9983441,0.00003777393,0.000516478,0.0003968611,0.0003850709,0.0003196655],"domain_scores_gemma":[0.9987158,0.00009759038,0.0003019552,0.0004770583,0.0002527147,0.0001548815],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000760632,0.001003688,0.06207456,0.000185752,0.0005465461,0.0002511209,0.001115631,0.1177992,0.01312751,0.7455407,0.03976898,0.01851027],"study_design_scores_gemma":[0.002652886,0.0003980163,0.116175,0.001799309,0.00006644396,0.001060333,0.0002343667,0.5242599,0.1955365,0.0147411,0.1406227,0.002453472],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3215673,0.0001733637,0.6553887,0.01562109,0.0003876844,0.001179779,0.00001228708,0.000079492,0.005590334],"genre_scores_gemma":[0.5858757,0.00007292101,0.4122958,0.0002999195,0.00002674659,0.0001946973,0.000001252906,0.00001186404,0.001220983],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7307996,"threshold_uncertainty_score":0.7368511,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1699692096352127,"score_gpt":0.4206065951274083,"score_spread":0.2506373854921956,"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."}}