{"id":"W2914080670","doi":"","title":"Proceedings of the 4th International Haifa Verification Conference on Hardware and Software: Verification and Testing","year":2009,"lang":"en","type":"article","venue":"","topic":"Safety Systems Engineering in Autonomy","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Software verification; Software engineering; Verification; Software; Intelligent verification; Programming language; Software construction; Software system","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":[],"consensus_categories":[],"category_scores_codex":[0.0000808753,0.0000862759,0.00007851483,0.00004309825,0.00002805616,0.00003651089,0.0001069704,0.00004179,0.000004155194],"category_scores_gemma":[0.0001089807,0.00007187205,0.00001047239,0.00009679232,0.00002138204,0.0001203184,0.00001163664,0.00007562428,0.000001741373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003753654,"about_ca_system_score_gemma":0.000007234285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004999953,"about_ca_topic_score_gemma":3.207591e-7,"domain_scores_codex":[0.9995437,0.00000204169,0.0001559557,0.0001212576,0.0001037442,0.00007333494],"domain_scores_gemma":[0.9997311,0.00003014042,0.00004065855,0.00008742598,0.00008718225,0.00002354932],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.000033193,0.00008468421,0.05190475,0.0006240461,0.0001186399,6.582037e-7,0.002738846,0.01924773,0.5810699,0.1454749,0.00238825,0.1963144],"study_design_scores_gemma":[0.0003716926,0.00006227077,0.7400581,0.0003183014,0.00001381964,0.00002140424,0.000144217,0.220057,0.03477551,0.0005069677,0.003406282,0.0002643502],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9436713,0.0001342649,0.01913401,0.0008942784,0.0005827448,0.0005628081,0.00001250254,0.0007920007,0.0342161],"genre_scores_gemma":[0.9937966,0.0000128248,0.005995601,0.00002047673,0.00003360137,0.00000980291,0.00000201989,0.000009433927,0.0001196763],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6881534,"threshold_uncertainty_score":0.2930857,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01780360263690948,"score_gpt":0.201220993659039,"score_spread":0.1834173910221295,"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."}}