{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009435239,0.001240298,0.0008770834,0.001405627,0.0008541067,0.003268565,0.001614532,0.001363224,0.06474935],"category_scores_gemma":[0.004821496,0.0008068859,0.0006720108,0.001338266,0.001075697,0.003464161,0.001323578,0.00250279,0.02683774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001017373,"about_ca_system_score_gemma":0.001187484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002983294,"about_ca_topic_score_gemma":0.004830929,"domain_scores_codex":[0.9984846,0.0002814251,0.00003501902,0.0001470431,0.0009698546,0.00008216669],"domain_scores_gemma":[0.998047,0.0008400819,0.00004901264,0.0004115477,0.0005976944,0.00005462434],"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":[0.00004142663,0.0001497682,0.0003935484,0.0001703711,0.00001755468,0.0001316966,0.0003485266,0.003243862,0.001219206,0.266598,0.2264117,0.5012743],"study_design_scores_gemma":[0.00002212437,0.00008817507,0.0006627963,0.0003652821,0.00003291395,0.000533356,0.0002788663,0.02217769,0.003177425,0.317977,0.6546433,0.00004124398],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.002831596,0.004317975,0.1609432,0.001973966,0.0007777957,0.0001113554,0.0003487373,0.003500143,0.8251953],"genre_scores_gemma":[0.09292151,0.005697888,0.07281788,0.001864903,0.0003257514,0.0002753969,0.001547752,0.002602431,0.8219464],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.06474935,"threshold_uncertainty_score":0.2166082,"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."}}