{"id":"W1565883978","doi":"10.1002/9781118411360.wbcla022","title":"Large‐Scale Assessment","year":2013,"lang":"en","type":"other","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Accountability; Scale (ratio); Bureaucracy; Politics; Test (biology); Quality (philosophy); Language assessment; Political science; Public relations; Psychology; Computer science; Mathematics education; Epistemology; Geography; Law","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002459376,0.0001533653,0.0002096263,0.0001007333,0.0001591232,0.0001412454,0.0003536571,0.0002765754,0.2488165],"category_scores_gemma":[0.000005554345,0.0001312421,0.00008492907,0.0001276101,0.00008612337,0.00005542549,0.00008063504,0.0001377665,0.004674953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007556793,"about_ca_system_score_gemma":0.0001357755,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003258996,"about_ca_topic_score_gemma":0.009639765,"domain_scores_codex":[0.9986337,0.00008230919,0.0001111422,0.0002382192,0.0005544118,0.0003802459],"domain_scores_gemma":[0.9995444,0.00002661086,0.00009323007,0.0002003649,0.0000237446,0.0001116556],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[1.334435e-7,0.00005115789,0.002658071,0.0000043895,0.00002779928,7.05027e-7,0.0009449822,4.697061e-9,9.729819e-7,0.05044774,0.9455913,0.0002727674],"study_design_scores_gemma":[0.0001466162,0.000007774326,0.0008136892,0.00001988701,0.00001633078,2.62031e-8,0.008737306,0.000004744504,1.884301e-7,0.0001126444,0.9899511,0.0001897231],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00001938682,0.0001206606,0.0005072238,0.0006470364,0.0009913035,0.0004480161,0.000007611787,0.0004147116,0.9968441],"genre_scores_gemma":[0.0002560305,0.000403734,0.002788585,0.0002625326,0.001164105,0.0000453684,0.00001991227,0.0001575425,0.9949022],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.2441416,"threshold_uncertainty_score":0.9961,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01975342632826853,"score_gpt":0.3682010653148333,"score_spread":0.3484476389865648,"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."}}