{"id":"W4400484631","doi":"10.1145/3663533.3664042","title":"Graph Neural Network vs. Large Language Model: A Comparative Analysis for Bug Report Priority and Severity Prediction","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Graph; Artificial neural network; Artificial intelligence; Natural language processing; Theoretical computer science","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":[0.003256663,0.001911919,0.001045447,0.003411271,0.0003762946,0.0009733234,0.001198913,0.001081459,0.00113816],"category_scores_gemma":[0.009404653,0.0003154345,0.0009942874,0.00216073,0.0003715393,0.002288118,0.0005696613,0.001396343,0.0004944067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001678235,"about_ca_system_score_gemma":0.001387056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03694808,"about_ca_topic_score_gemma":0.0324913,"domain_scores_codex":[0.9988158,0.0004664649,0.00008744053,0.0002652545,0.0002616062,0.0001035457],"domain_scores_gemma":[0.9943408,0.004119555,0.0002921704,0.0003304835,0.0007652147,0.0001517111],"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":[0.001481139,0.0006896278,0.03692631,0.0008060383,0.0007337432,0.0002657822,0.0001780342,0.6014425,0.001797175,0.002929721,0.01472632,0.3380236],"study_design_scores_gemma":[0.0000166088,0.0001186418,0.002725252,0.00002438602,0.00006815444,0.00002571848,0.00003964861,0.9946714,0.0003829458,0.001315729,0.000596545,0.0000149823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.764657,0.03162237,0.1719377,0.004687621,0.0009015226,0.000298717,0.006520347,0.009902881,0.009471838],"genre_scores_gemma":[0.9551934,0.003646092,0.03192865,0.0002949459,0.0001452244,0.00009578322,0.006237645,0.0002206204,0.002237702],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03694808,"threshold_uncertainty_score":0.07346606,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02254936607785773,"score_gpt":0.3139234305496094,"score_spread":0.2913740644717517,"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."}}