{"id":"W2525234853","doi":"","title":"Estimating the required test volume and effort for software verification and validation","year":2005,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Software verification; Verification and validation; Volume (thermodynamics); Model validation; Software; Reliability engineering; Test (biology); Data mining; Software development; Statistics; Engineering; Software construction; Programming language; Mathematics; Data science","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":[0.004672051,0.001447564,0.001126899,0.004578852,0.0003660902,0.001499733,0.001782076,0.001191935,0.001282047],"category_scores_gemma":[0.05006033,0.0007665005,0.001070193,0.001606751,0.0004416557,0.003350792,0.001053142,0.0007789799,0.0006891221],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00117182,"about_ca_system_score_gemma":0.001515636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002385438,"about_ca_topic_score_gemma":0.004026937,"domain_scores_codex":[0.9910642,0.002778325,0.0005681064,0.0006077885,0.00457232,0.000409244],"domain_scores_gemma":[0.9444529,0.03727853,0.00581354,0.004741924,0.007207424,0.0005056434],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000456076,0.000286923,0.03413839,0.0005197214,0.0001910361,0.0002802695,0.0002497625,0.5330913,0.03476488,0.01005062,0.001343393,0.3846276],"study_design_scores_gemma":[0.00007284737,0.0006831897,0.02583818,0.0001208902,0.0001324409,0.0004266856,0.0001379487,0.9161986,0.04181895,0.01016217,0.004317223,0.00009088466],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1188301,0.000508349,0.8756006,0.0002109882,0.0000298347,0.0001537646,0.0003780569,0.00134443,0.002943749],"genre_scores_gemma":[0.6135191,0.0004940497,0.3819171,0.00007093783,0.00008246908,0.0004326937,0.001659509,0.0004207204,0.001403418],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004672051,"threshold_uncertainty_score":0.02470845,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02170947310393653,"score_gpt":0.276159024302778,"score_spread":0.2544495511988415,"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."}}