{"id":"W4413373109","doi":"10.1007/978-3-032-02018-5_16","title":"Certus: A Domain Specific Language for Confidence Assessment in Assurance Cases","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Safety Systems Engineering in Autonomy","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Critical Systems Labs; University of Victoria","funders":"","keywords":"Computer science; Domain (mathematical analysis); Domain-specific language; Natural language processing; Artificial intelligence; Software engineering; Mathematics","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":[0.0005650031,0.000466655,0.0005820439,0.0007366792,0.00005428059,0.0001388873,0.0008878019,0.0002584738,0.00001780373],"category_scores_gemma":[0.00005242947,0.000495659,0.0001004384,0.0003734932,0.0001717381,0.0001500689,0.0001378139,0.0006383852,0.000007634999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008838777,"about_ca_system_score_gemma":0.0003111652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002845624,"about_ca_topic_score_gemma":0.0001858761,"domain_scores_codex":[0.997781,0.00001374783,0.00054932,0.0007430252,0.0003754312,0.0005374579],"domain_scores_gemma":[0.9977472,0.001311929,0.00007914359,0.0007221752,0.00006767697,0.00007187508],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007350638,0.00001332703,0.00007633483,0.0007706794,0.00002565414,0.0002931139,0.0008887321,0.8886455,0.000954699,0.01472086,0.0001951453,0.09340858],"study_design_scores_gemma":[0.001145385,0.0001336361,0.0009617269,0.006432305,0.00001494937,0.0001723943,0.000005244924,0.9160358,0.002076892,0.01527615,0.05585423,0.001891327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001778804,0.00226981,0.9890748,0.0001154931,0.002516584,0.0008346409,0.00004222565,0.0002465119,0.004722018],"genre_scores_gemma":[0.5266351,0.0001408651,0.4714947,0.0001975523,0.0006683397,0.0001707319,0.00002250539,0.000111759,0.0005585029],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5264572,"threshold_uncertainty_score":0.9997495,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01154912985296156,"score_gpt":0.2458385963605707,"score_spread":0.2342894665076092,"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."}}