{"id":"W4417184697","doi":"10.1111/capa.70043","title":"Escaping the Tunnel: How Formative Evaluation Complements Performance Audit to Improve Decision Navigation","year":2025,"lang":"en","type":"article","venue":"Canadian Public Administration","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Formative assessment; Audit; Performance audit; Evaluation methods; Reliability (semiconductor)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1406911,0.001178172,0.001356214,0.006719004,0.005367383,0.02029007,0.003069681,0.002840449,0.004468437],"category_scores_gemma":[0.2429769,0.0007115144,0.00064798,0.004772361,0.008218418,0.01497759,0.006992811,0.004351512,0.0008317045],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01208046,"about_ca_system_score_gemma":0.02457763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02448748,"about_ca_topic_score_gemma":0.04035099,"domain_scores_codex":[0.8260756,0.1474064,0.00342275,0.00302443,0.01578883,0.004282028],"domain_scores_gemma":[0.7188417,0.2015236,0.01479792,0.01924848,0.04144594,0.004142411],"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":[0.0009554279,0.001579126,0.01915774,0.0008548428,0.000177881,0.0007800453,0.04421536,0.0224181,0.002577546,0.1452943,0.01434022,0.7476494],"study_design_scores_gemma":[0.001012022,0.004224928,0.0385863,0.007226042,0.0005283351,0.0008134583,0.08130223,0.1634895,0.01873841,0.561666,0.1210997,0.001313253],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3535649,0.002207767,0.3601355,0.05054292,0.0008463027,0.002551085,0.0002775661,0.002525466,0.2273486],"genre_scores_gemma":[0.8609928,0.0004006613,0.1341977,0.001052003,0.00007971792,0.0003610801,0.00006135482,0.0001298133,0.002724994],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1406911,"threshold_uncertainty_score":0.7440547,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1439210505811699,"score_gpt":0.4574227160440045,"score_spread":0.3135016654628345,"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."}}