{"id":"W2101700102","doi":"10.1109/secse.2009.5069163","title":"Testing for trustworthiness in scientific software","year":2009,"lang":"en","type":"article","venue":"","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal Military College of Canada; Queen's University","funders":"","keywords":"Computer science; Software engineering; Correctness; Software construction; Software reliability testing; Trustworthiness; Software; Software testing; Verification and validation; Code (set theory); Software bug; Software quality; Software development; Programming language; Computer security; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.008726312,0.00008982136,0.0001569094,0.0005307095,0.0003034513,0.001435751,0.001009043,0.0000251772,0.0001085137],"category_scores_gemma":[0.01426927,0.00006364929,0.00005519482,0.002877071,0.00005866792,0.0003329454,0.0001530319,0.00005184925,0.0001483352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002239083,"about_ca_system_score_gemma":0.00005052361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001751618,"about_ca_topic_score_gemma":0.00006780947,"domain_scores_codex":[0.9974077,0.00004016632,0.0005092384,0.0008528651,0.0008699879,0.0003199818],"domain_scores_gemma":[0.9970602,0.001499817,0.0001028517,0.0009426436,0.0003232228,0.00007130994],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000006645343,0.00005923019,0.01837792,0.000001740047,7.35724e-7,0.000003084414,0.0001025475,0.001303631,0.00008723503,0.00391822,0.07122338,0.9049156],"study_design_scores_gemma":[0.0009022798,0.0001325824,0.3840852,0.00004479564,0.000005704136,0.000004689502,0.0005796872,0.134534,0.0001498347,0.3434304,0.1357503,0.000380505],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.566647,0.00005628189,0.4054615,0.002879801,0.00385452,0.0007358716,0.0000215545,0.0003333915,0.02001006],"genre_scores_gemma":[0.9076735,3.82982e-8,0.07934792,0.0004046482,0.00006493133,0.000006187119,0.00001017427,0.000003572205,0.01248906],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9045351,"threshold_uncertainty_score":0.9996008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2322874908001109,"score_gpt":0.4142692574484899,"score_spread":0.1819817666483789,"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."}}