{"id":"W4401172336","doi":"10.1007/978-3-031-47821-5_15","title":"Model Acceptance Testing","year":2024,"lang":"en","type":"book-chapter","venue":"CIGRE green books","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Opal-Rt Technologies (Canada)","funders":"","keywords":"Acceptance testing; Psychology; Computer science; Software engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002537637,0.000545739,0.0004421514,0.000284679,0.0001566356,0.000319356,0.001805817,0.0003988508,0.00001960329],"category_scores_gemma":[0.00008493027,0.0005397348,0.0002056058,0.00006973989,0.0001141085,0.000204389,0.001013495,0.0008483757,0.0005324885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001223431,"about_ca_system_score_gemma":0.0002284245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004666371,"about_ca_topic_score_gemma":0.00001186135,"domain_scores_codex":[0.9976252,0.000007772853,0.0004250791,0.001047785,0.0004730735,0.0004211141],"domain_scores_gemma":[0.9976248,0.0002830941,0.0002189526,0.001521245,0.0001970957,0.0001548151],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000001813518,0.000006328891,0.00003231648,0.0001930055,0.00005134087,0.0003297623,0.0002220967,0.00004487652,0.00001424298,0.6521341,0.06792434,0.2790458],"study_design_scores_gemma":[0.00004164715,0.00004582599,0.000004397382,0.0008888592,0.00003113537,0.00008828842,1.787069e-7,0.1709966,0.00001554848,0.8008808,0.02645076,0.0005560039],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.000002712087,0.001430591,0.1707623,0.0002082292,0.0003436205,0.0002128054,0.00001754199,0.02486889,0.8021533],"genre_scores_gemma":[0.001473289,0.00001156502,0.2339331,0.0005594873,0.0003381352,0.00002363652,0.00000538834,0.0001178354,0.7635376],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.2784898,"threshold_uncertainty_score":0.9997054,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07991491499171106,"score_gpt":0.2671525657356494,"score_spread":0.1872376507439384,"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."}}