{"id":"W4247379461","doi":"10.1002/0470013192.bsa670","title":"Test Construction","year":2005,"lang":"en","type":"other","venue":"Encyclopedia of Statistics in Behavioral Science","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Test (biology); Function (biology); Construct (python library); Computer science; Item bank; Computerized adaptive testing; Key (lock); Item response theory; Process (computing); Information retrieval; Data mining; Artificial intelligence; Statistics; Mathematics; Psychometrics; 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":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004309739,0.0002413795,0.0005673984,0.002314104,0.00007895318,0.0001012355,0.001768874,0.000187377,0.005600159],"category_scores_gemma":[0.04868558,0.000195648,0.00004650689,0.004809966,0.001855205,0.0001613472,0.0002825817,0.0003341851,0.0001026236],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001032228,"about_ca_system_score_gemma":0.0003836918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000684545,"about_ca_topic_score_gemma":0.00042142,"domain_scores_codex":[0.9951398,0.0001142937,0.001023697,0.0008283549,0.002427521,0.000466294],"domain_scores_gemma":[0.9909371,0.006783932,0.001073051,0.0007708849,0.000277878,0.0001571305],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002209526,0.0001321037,0.1517374,0.000007163183,7.952731e-7,0.00001671217,0.00008919308,0.000006472607,0.00004486149,0.00289009,0.1104634,0.7346095],"study_design_scores_gemma":[0.0005886693,0.0003317229,0.2399202,0.0002407019,0.000037905,0.00003241554,0.000692888,0.0002820443,0.00005341311,0.01997715,0.736991,0.0008518594],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.001744638,0.000270341,0.01608488,0.00002869257,0.002673841,0.0002975188,0.0007764439,0.00006736059,0.9780563],"genre_scores_gemma":[0.003116447,0.0007326991,0.7721904,0.00001482979,0.0002719738,0.0000117632,0.000007612923,0.00008402456,0.2235703],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.7561055,"threshold_uncertainty_score":0.9953089,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1959902382496173,"score_gpt":0.4684073038429675,"score_spread":0.2724170655933502,"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."}}