{"id":"W2104268806","doi":"10.1007/978-3-642-35795-4_5","title":"Software Testing is Necessary But Not Sufficient for Software Trustworthiness","year":2013,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Software Reliability and Analysis Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Trustworthiness; Software reliability testing; Software construction; Software quality; Verification and validation; Software engineering; Software; Software quality analyst; Software development; Software verification; Software quality assurance; Software metric; Reliability engineering; 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":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.001861766,0.0003217052,0.0004226692,0.001166367,0.001073533,0.001480439,0.005527319,0.000205288,0.00002205145],"category_scores_gemma":[0.0008454543,0.0003058142,0.0001206819,0.001007568,0.001015083,0.006804359,0.003836146,0.0005889855,0.0001035717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002014409,"about_ca_system_score_gemma":0.0006879499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005656018,"about_ca_topic_score_gemma":0.000005488881,"domain_scores_codex":[0.9970732,0.00004142306,0.0009864161,0.0005632811,0.0008773092,0.0004584085],"domain_scores_gemma":[0.9926351,0.001832503,0.0004384727,0.003016175,0.001882482,0.0001952786],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003698807,0.00004743165,0.0005241602,0.0001921487,0.00001632297,4.285051e-7,0.001721722,0.001160747,0.000002301967,0.09262095,0.001241531,0.9024686],"study_design_scores_gemma":[0.0003635956,0.00009644144,0.002274848,0.0003459679,0.00001226736,0.00001667769,0.00003519444,0.9229171,0.00002644484,0.0121617,0.06117707,0.0005726479],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002720613,0.0003330621,0.9893803,0.00130981,0.0002286081,0.0008163945,0.0000560255,0.0002396167,0.007364135],"genre_scores_gemma":[0.01298592,0.0009898236,0.9799307,0.002816602,0.00007810497,0.0002122459,0.0001141467,0.00002207288,0.002850377],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9217564,"threshold_uncertainty_score":0.9999394,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0683685272162676,"score_gpt":0.3153826507900473,"score_spread":0.2470141235737797,"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."}}