{"id":"W4308641647","doi":"10.1145/3540250.3549145","title":"Are we building on the rock? on the importance of data preprocessing for code summarization","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China; Youth Innovation Promotion Association; Chinese Academy of Sciences; National Science Foundation","keywords":"Automatic summarization; Benchmark (surveying); Computer science; Preprocessor; Code (set theory); Data pre-processing; Data mining; Benchmarking; Machine learning; Task (project management); Artificial intelligence; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.001829614,0.000324778,0.0003261048,0.0001744903,0.0006311023,0.0002137395,0.003934858,0.00003946587,0.000007645566],"category_scores_gemma":[0.006012766,0.0002021048,0.0001185771,0.0005694599,0.00006365818,0.000431048,0.001984307,0.0005169825,8.233746e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007271702,"about_ca_system_score_gemma":0.00006707063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003029829,"about_ca_topic_score_gemma":4.185183e-7,"domain_scores_codex":[0.9977878,0.00004214996,0.0006639773,0.0005859931,0.0005954126,0.0003246641],"domain_scores_gemma":[0.9955441,0.001734159,0.0008179124,0.001502776,0.0003470741,0.00005398625],"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":[0.00005684165,0.000168546,0.005435631,0.001241779,0.0002446659,0.000001291359,0.003519189,0.6972132,0.02053155,0.2680684,0.0009967873,0.002522129],"study_design_scores_gemma":[0.0005855053,0.0003360573,0.004640601,0.003136174,0.0001286099,0.00002468321,0.0007463019,0.9577656,0.02500357,0.002958308,0.003859615,0.0008149084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1952023,0.00013178,0.796253,0.00650197,0.0004196658,0.001001751,0.0001280499,0.0003056574,0.00005585298],"genre_scores_gemma":[0.9717696,0.00003976902,0.02772155,0.0001798618,0.00008262226,0.00009237014,0.000008141813,0.00006026621,0.00004582296],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7765673,"threshold_uncertainty_score":0.8241595,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0714784426833877,"score_gpt":0.2534673684029559,"score_spread":0.1819889257195682,"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."}}