{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004007799,0.001641552,0.0007910184,0.001834536,0.0006394354,0.003541359,0.002438758,0.002163099,0.04088413],"category_scores_gemma":[0.01358933,0.001316918,0.001494874,0.001097743,0.001652144,0.004793151,0.002419818,0.003868436,0.01361852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008700088,"about_ca_system_score_gemma":0.001399232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001141375,"about_ca_topic_score_gemma":0.001398604,"domain_scores_codex":[0.9965215,0.001126198,0.000697796,0.0004558697,0.001011251,0.0001873441],"domain_scores_gemma":[0.9916266,0.005848956,0.0004907729,0.0007814093,0.001098266,0.0001538793],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002191265,0.000139948,0.001073405,0.001500656,0.00007228286,0.0009802543,0.001421646,0.01587529,0.006849059,0.512317,0.1832368,0.2763146],"study_design_scores_gemma":[0.0001166061,0.00009477831,0.0005185017,0.0007956572,0.00005910787,0.002232362,0.0002614724,0.1378018,0.01676649,0.2728491,0.5683921,0.0001121218],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0009680081,0.0001019236,0.9625502,0.0003094953,0.0001216184,0.0001829177,0.001956735,0.02475866,0.009050418],"genre_scores_gemma":[0.05164194,0.0003800333,0.9114289,0.0008003217,0.0002217472,0.0009434875,0.008554229,0.01138272,0.01464667],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04088413,"threshold_uncertainty_score":0.1367711,"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."}}