{"id":"W4210294742","doi":"10.1109/ase51524.2021.9678520","title":"Subtle Bugs Everywhere: Generating Documentation for Data Wrangling Code","year":2021,"lang":"en","type":"article","venue":"2021 36th IEEE/ACM International Conference on Automated Software Engineering (ASE)","topic":"Software Engineering Research","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Documentation; Code (set theory); Programming language; Reuse; Plug-in; Software bug; Database; Software engineering; Software; Engineering; Set (abstract data type)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.004737252,0.001555875,0.0005639002,0.002839777,0.0007894303,0.001831752,0.002091566,0.001297279,0.007066806],"category_scores_gemma":[0.03725714,0.001385562,0.0009914874,0.001398122,0.001010242,0.002981326,0.003048274,0.001900553,0.003398976],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005400458,"about_ca_system_score_gemma":0.001528988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009069199,"about_ca_topic_score_gemma":0.001584968,"domain_scores_codex":[0.9964803,0.0008949452,0.0003945734,0.0006477146,0.001415122,0.0001673214],"domain_scores_gemma":[0.9633649,0.01695174,0.00287752,0.01175532,0.004397837,0.0006526492],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008525086,0.0008759429,0.0181716,0.001645414,0.0001511066,0.002125724,0.007643867,0.01778179,0.06844699,0.01407025,0.08685815,0.7813765],"study_design_scores_gemma":[0.0006822046,0.001340452,0.01190691,0.001176003,0.000246298,0.003550001,0.001509689,0.3994898,0.2912216,0.03177271,0.2566788,0.0004255109],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04873287,0.0002277585,0.7281107,0.0006325449,0.0001762971,0.0006041682,0.00271605,0.2133293,0.005470246],"genre_scores_gemma":[0.1759035,0.0002449866,0.7641879,0.0003582699,0.00006428248,0.0007065772,0.006920453,0.04444754,0.00716644],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007066806,"threshold_uncertainty_score":0.02505332,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07020492043842771,"score_gpt":0.3442052189351064,"score_spread":0.2740002984966787,"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."}}