{"id":"W2188911565","doi":"","title":"A Survey of Analysis Models and Methods in Website Verification and Testing Technical Report 2007-532","year":2007,"lang":"en","type":"article","venue":"","topic":"Web Applications and Data Management","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Software; Verification and validation; Data mining; Software engineering; Software testing; Quality (philosophy); Data science; Programming language; Statistics; Mathematics","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":[0.005250352,0.00005117494,0.0001334642,0.0002546065,0.00002629753,0.00004518302,0.0001808475,0.00002853734,0.000001934496],"category_scores_gemma":[0.0001666082,0.00004642002,0.0000111792,0.001657258,0.00002994762,0.000263679,0.0002358604,0.00003922281,3.587321e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001235184,"about_ca_system_score_gemma":0.00001302869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001948276,"about_ca_topic_score_gemma":0.0006459515,"domain_scores_codex":[0.9991011,0.00005673708,0.0003365014,0.0003131035,0.00009737595,0.00009517677],"domain_scores_gemma":[0.9989243,0.0002939444,0.0001092331,0.0005519636,0.00008286251,0.00003774816],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000008839098,0.0002015169,0.5230137,0.00003341194,0.00009229225,0.00002024178,0.0001124767,0.001760143,0.005435645,0.1123672,0.0002529632,0.3567015],"study_design_scores_gemma":[0.00003878837,0.000006445644,0.6727472,0.000001644135,0.0000121939,0.000004300656,0.000005023637,0.3261352,0.0001312821,0.0008025353,0.00007451323,0.00004088135],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02004416,0.00005911572,0.9757627,0.00005532481,0.000005628231,0.0001062322,0.000001515936,0.00002950935,0.003935846],"genre_scores_gemma":[0.4593838,0.000007724023,0.5405494,0.00001494213,0.000001380589,0.000004295586,0.000006198034,0.000001091102,0.00003120182],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4393396,"threshold_uncertainty_score":0.2945223,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08848664537865322,"score_gpt":0.3855443338971711,"score_spread":0.2970576885185179,"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."}}