{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04936407,0.002546332,0.003090083,0.00801762,0.004472988,0.0143997,0.004185454,0.00481657,0.005061055],"category_scores_gemma":[0.2953902,0.002553706,0.002543801,0.008039505,0.007752884,0.04909277,0.009436071,0.009671842,0.006035982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00251304,"about_ca_system_score_gemma":0.007793773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01108007,"about_ca_topic_score_gemma":0.01263276,"domain_scores_codex":[0.9454184,0.02486903,0.004557553,0.008594663,0.01488404,0.001676251],"domain_scores_gemma":[0.6489702,0.2168395,0.01633692,0.06015478,0.05302326,0.004675346],"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":[0.001875134,0.0004888852,0.06908237,0.004173402,0.0007685868,0.0005602814,0.009928337,0.01640143,0.01256232,0.04241479,0.07850237,0.7632421],"study_design_scores_gemma":[0.0004660467,0.002130959,0.06434385,0.008643712,0.001184784,0.001865518,0.01777119,0.2054692,0.04248201,0.3215048,0.3329104,0.00122752],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.15081,0.02698183,0.6570436,0.1214503,0.002588342,0.001044841,0.007429525,0.01440601,0.01824571],"genre_scores_gemma":[0.3780777,0.0123315,0.5662274,0.01656225,0.001688558,0.001090253,0.01492663,0.004591248,0.004504514],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04936407,"threshold_uncertainty_score":0.2610653,"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."}}