{"id":"W4309467076","doi":"10.1186/s40468-022-00201-5","title":"Lessons from the Chinese imperial examination system","year":2022,"lang":"en","type":"article","venue":"Language Testing in Asia","topic":"Global Educational Reforms and Inequalities","field":"Social Sciences","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Imperial examination; Language assessment; Linguistics; Set (abstract data type); Psychology; Field (mathematics); History; Pedagogy; Computer science; Philosophy; Ancient history","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":[0.000991193,0.00004922734,0.00006389169,0.00002140548,0.0005765511,0.0000580021,0.0002249937,0.00001800108,0.0002365939],"category_scores_gemma":[0.00178924,0.00003400508,0.00001865283,0.0003975803,0.00004095038,0.000077365,0.00005975056,0.0001113706,0.000008436563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002781647,"about_ca_system_score_gemma":0.0001406745,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.07144972,"about_ca_topic_score_gemma":0.003574894,"domain_scores_codex":[0.9990451,0.000287446,0.0001193804,0.0001021094,0.0003011112,0.0001447975],"domain_scores_gemma":[0.9992653,0.0005210587,0.00006343453,0.00009752299,0.00002875753,0.00002396533],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.00001100065,0.0001044083,0.1310181,0.00001558686,0.00001165539,0.00002975802,0.6172789,0.0002693631,0.0009669657,0.2040165,0.000951018,0.0453268],"study_design_scores_gemma":[0.0001495954,0.00001663882,0.5286991,0.00002232146,0.000003536617,0.000002585506,0.4665159,0.0002990234,0.000005308489,0.001393366,0.002800515,0.00009217271],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9350086,0.000179904,0.00000311374,0.001083583,0.00052946,0.0001048386,0.0000390982,0.0000624903,0.06298887],"genre_scores_gemma":[0.9986337,7.020661e-7,0.0002034275,0.0001117463,0.0005432155,0.00005118388,0.00002863673,0.000004743163,0.0004225748],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.397681,"threshold_uncertainty_score":0.9347336,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03157084234721545,"score_gpt":0.3443788321747615,"score_spread":0.312807989827546,"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."}}