{"id":"W3082189468","doi":"10.1109/mcse.2020.3019770","title":"Raising the Bar: Assurance Cases for Scientific Software","year":2020,"lang":"en","type":"article","venue":"Computing in Science & Engineering","topic":"Software Reliability and Analysis Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Documentation; Software engineering; Correctness; Software; Software quality analyst; Software system; Software construction; Programming language","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1084217,0.001816126,0.001449203,0.005049495,0.009428324,0.01559353,0.005751078,0.01830069,0.009902611],"category_scores_gemma":[0.3589502,0.002343189,0.002585524,0.002003469,0.02644559,0.03389674,0.01332771,0.01833983,0.003127718],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004306268,"about_ca_system_score_gemma":0.006824546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003012213,"about_ca_topic_score_gemma":0.001707466,"domain_scores_codex":[0.8655034,0.06720986,0.00908515,0.007243167,0.04701121,0.003947156],"domain_scores_gemma":[0.5606033,0.3223838,0.01672739,0.06116836,0.03527524,0.003842027],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001013717,0.0000721271,0.001470532,0.000219129,0.00002861463,0.002554095,0.00535588,0.002139007,0.001360158,0.9419269,0.01301725,0.03175505],"study_design_scores_gemma":[0.0001204888,0.0001268451,0.0005050423,0.0007456741,0.00005522463,0.002623768,0.001097787,0.01321767,0.004681094,0.8321561,0.1445076,0.0001626866],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01724255,0.0008207533,0.8877679,0.04906983,0.001037159,0.0004637847,0.0001293384,0.003741862,0.0397269],"genre_scores_gemma":[0.3657115,0.0007610683,0.6045681,0.01137055,0.001219706,0.001144706,0.000243859,0.002341719,0.01263879],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8915783,"threshold_uncertainty_score":0.5733958,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05799632067226392,"score_gpt":0.3051431806933281,"score_spread":0.2471468600210642,"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."}}