{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002789707,0.0001407689,0.0001905525,0.0002187812,0.0007512874,0.001238235,0.002558281,0.00003036293,0.000001799433],"category_scores_gemma":[0.00801029,0.0001126967,0.00009363823,0.003896159,0.0003413264,0.0006576708,0.0006480117,0.0002421294,0.00001130315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009662545,"about_ca_system_score_gemma":0.0003112619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009528972,"about_ca_topic_score_gemma":0.000002308863,"domain_scores_codex":[0.9975417,0.00003342312,0.0002995761,0.000764237,0.0006812151,0.0006798017],"domain_scores_gemma":[0.997147,0.00181851,0.00005723183,0.0005669846,0.0002341533,0.000176158],"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":[0.000003380208,0.00002798296,0.007739831,0.00008838269,0.000006462523,0.00002104594,0.002793362,0.9226847,0.009878607,0.009980674,0.0001673135,0.04660828],"study_design_scores_gemma":[0.0001179935,0.00002604613,0.004287351,0.00006586967,0.000001692883,0.000009762298,0.0000289006,0.9902359,0.002579838,0.0001598,0.002332001,0.0001548873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1883506,0.0002136127,0.8091589,0.001494199,0.0003587565,0.0001867421,9.876817e-7,0.0002261611,0.00001008802],"genre_scores_gemma":[0.9254303,0.000002256969,0.07430765,0.0001425322,0.00009559845,0.000008506994,5.084517e-7,0.00000774479,0.0000048861],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7370797,"threshold_uncertainty_score":0.9997986,"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."}}