{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00133533,0.0003248012,0.000297525,0.000443569,0.002386396,0.002378386,0.001903673,0.0001959993,0.00008541332],"category_scores_gemma":[0.008598714,0.0003397288,0.0000284126,0.001122293,0.0003012752,0.0002897317,0.003634002,0.0005816547,0.001752262],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009443935,"about_ca_system_score_gemma":0.00002904062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002399646,"about_ca_topic_score_gemma":0.000002000921,"domain_scores_codex":[0.9968657,0.0005091184,0.0004983615,0.001042686,0.0005687957,0.0005152614],"domain_scores_gemma":[0.9970267,0.000602397,0.0002203577,0.001230521,0.0006102799,0.0003097084],"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":[0.00001648964,0.00005993268,0.000002010618,0.0001672884,0.00002535723,0.00004697917,0.00003664945,0.00005419693,0.0000446028,0.0000151319,0.9800938,0.01943756],"study_design_scores_gemma":[0.0005585785,0.0003893196,0.0001749832,0.0002299311,0.00003179353,0.0001425378,0.00000590137,0.02338616,0.00001947096,0.0001717854,0.9744658,0.0004236811],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00009173348,0.00004561559,0.05324019,0.0006331991,0.00008282686,0.0004130598,0.9327517,0.01266433,0.00007731164],"genre_scores_gemma":[0.00008705009,0.00003682615,0.03366233,0.0002223815,0.00006107909,3.335414e-7,0.9652705,0.0005612969,0.00009818618],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.03251878,"threshold_uncertainty_score":0.9999055,"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."}}