{"id":"W4393617534","doi":"10.5281/zenodo.5732299","title":"Bash in the Wild: Language Usage, Code Smells, and Bugs - Dataset","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Code (set theory); Computer science; Programming language; Code smell; Software; Software quality; Set (abstract data type)","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":[0.0008077156,0.002559613,0.00139736,0.002509582,0.0009129167,0.001277141,0.002278181,0.002470264,0.01033194],"category_scores_gemma":[0.002687006,0.0004876779,0.001253285,0.002651706,0.0005415285,0.0009084174,0.001710386,0.001859635,0.02239933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009690107,"about_ca_system_score_gemma":0.001476351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02540389,"about_ca_topic_score_gemma":0.05613097,"domain_scores_codex":[0.9987208,0.0001898777,0.0001229514,0.0003294476,0.000407036,0.0002297781],"domain_scores_gemma":[0.9984072,0.0002783584,0.0001640009,0.0003890898,0.000467171,0.0002942768],"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":[0.0003342082,0.0002188059,0.00628071,0.0005449341,0.00008343103,0.0001322591,0.00007896289,0.0006014494,0.0008270869,0.0003191784,0.9823888,0.008190179],"study_design_scores_gemma":[0.0009826659,0.0003495046,0.08798432,0.000444114,0.0001976755,0.0009711739,0.0007000256,0.007546954,0.00464795,0.002027628,0.8939188,0.0002292881],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.005914772,0.0002163673,0.0002731276,0.0001775291,0.0001077318,0.00005538587,0.9911225,0.0009115303,0.001220942],"genre_scores_gemma":[0.002735119,0.00003732662,0.0004118822,0.00005857022,0.00001576175,0.0000851312,0.9958962,0.00004714789,0.0007128519],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02540389,"threshold_uncertainty_score":0.05051202,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02404359875268159,"score_gpt":0.2531799358686012,"score_spread":0.2291363371159196,"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."}}