{"id":"W4393772048","doi":"10.5281/zenodo.8309515","title":"Search-based Software Testing Driven by Automatically Generated and Manually Defined Fitness Functions - Dataset and Results","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Software; Software testing; Data mining; Machine learning; Artificial intelligence; Programming language","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":[0.00206608,0.003651952,0.001686187,0.003479362,0.0006603338,0.001724517,0.00304626,0.00295538,0.01578406],"category_scores_gemma":[0.008993356,0.0006497366,0.002208036,0.003752395,0.0004931373,0.0008970714,0.001682794,0.001757692,0.02967074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001749436,"about_ca_system_score_gemma":0.001746724,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01423012,"about_ca_topic_score_gemma":0.02630334,"domain_scores_codex":[0.9969805,0.0006535162,0.0003964403,0.0007909933,0.0009088701,0.0002697094],"domain_scores_gemma":[0.9949976,0.001877512,0.0003625284,0.001527217,0.001005732,0.0002295076],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005531675,0.0002526205,0.004462328,0.002860573,0.0002276797,0.0001154784,0.00004658494,0.007529562,0.0008108404,0.000799961,0.966686,0.01565522],"study_design_scores_gemma":[0.002078634,0.0003771276,0.03124904,0.001285679,0.000382977,0.0005275147,0.0002137398,0.02538601,0.007133895,0.005705487,0.9254497,0.000210276],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.001997976,0.0002339316,0.0005292339,0.00008752879,0.00003822333,0.00004973419,0.9935183,0.002508364,0.001036776],"genre_scores_gemma":[0.001750366,0.00005492652,0.001000125,0.00004749787,0.000004777766,0.0001381727,0.9964662,0.0001552234,0.000382778],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01578406,"threshold_uncertainty_score":0.05280292,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05357661848873221,"score_gpt":0.2681292817312528,"score_spread":0.2145526632425206,"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."}}