{"id":"W6913140415","doi":"10.5281/zenodo.6760333","title":"Aligning Programming Language and Natural Language: Exploring Design Choices in Multi-Modal Transformer-Based Embedding for Bug Localization","year":2024,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Embedding; Natural language; Natural (archaeology); First-generation programming language; Programming domain; Replication (statistics); Natural language programming","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":[0.00477356,0.0006409275,0.0003788289,0.0006057927,0.0004492193,0.001557109,0.001463126,0.0008055243,0.003959475],"category_scores_gemma":[0.01847146,0.0006095382,0.0009610759,0.0004883491,0.001957127,0.005369652,0.003036585,0.001788321,0.0006434384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006912812,"about_ca_system_score_gemma":0.001204634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009080648,"about_ca_topic_score_gemma":0.001631379,"domain_scores_codex":[0.996008,0.002192914,0.0002251772,0.0005272742,0.0008187337,0.0002278572],"domain_scores_gemma":[0.9887454,0.006685704,0.000704144,0.002455892,0.001202822,0.0002060017],"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":[0.001442017,0.0005864258,0.00746737,0.001808487,0.0001880663,0.0006303824,0.0105465,0.06683013,0.1302016,0.2936414,0.005412474,0.4812452],"study_design_scores_gemma":[0.0002091665,0.001074302,0.001880954,0.0002918106,0.0003821188,0.0007982163,0.002998014,0.5552477,0.110676,0.297951,0.02833785,0.000152867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05062595,0.0001128307,0.9438378,0.0003813227,0.00002456293,0.0001210371,0.00009891871,0.002678649,0.002118945],"genre_scores_gemma":[0.5451978,0.0001141802,0.4511735,0.0001688819,0.00001109696,0.0001739041,0.0002586655,0.001157585,0.001744524],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00477356,"threshold_uncertainty_score":0.02524531,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05612344716175682,"score_gpt":0.2987255897735646,"score_spread":0.2426021426118078,"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."}}