{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006500835,0.0004072759,0.0003461693,0.0003347637,0.0001799536,0.001003048,0.003015441,0.0001776904,0.0003897441],"category_scores_gemma":[0.007174456,0.0004701357,0.0001132076,0.0006143586,0.00002656815,0.001141042,0.0007834036,0.0004463325,0.0001454487],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003492563,"about_ca_system_score_gemma":0.0004978822,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000364665,"about_ca_topic_score_gemma":0.000014426,"domain_scores_codex":[0.9965522,0.00006931693,0.0005892811,0.001159043,0.0009913463,0.0006388228],"domain_scores_gemma":[0.9952556,0.001610262,0.0001472965,0.001841136,0.0009242279,0.0002214442],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001207111,0.0007286948,0.005788925,0.000860457,0.001569799,0.001130918,0.001768138,0.7149779,0.1282697,0.0323603,0.05310091,0.05932352],"study_design_scores_gemma":[0.000774849,0.00005804659,0.0007263186,0.0002917017,0.00001566646,0.0000466082,0.00003058562,0.9784154,0.01526713,0.0001371189,0.003736735,0.000499825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03265987,0.0001569979,0.9594128,0.0008267656,0.003833212,0.0003480737,0.0004094295,0.002297162,0.00005574821],"genre_scores_gemma":[0.402738,0.0001085883,0.5927011,0.0002636091,0.0006972066,0.0002049899,0.00202064,0.0001230179,0.001142801],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3700781,"threshold_uncertainty_score":0.9997751,"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."}}