{"id":"W4221130019","doi":"10.12688/openreseurope.14507.1","title":"An open-source natural language processing toolkit to support software development: addressing automatic bug detection, code summarisation and code search","year":2022,"lang":"en","type":"article","venue":"Open Research Europe","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Horizon 2020 Framework Programme; European Commission","keywords":"Computer science; Software engineering; Codebase; Code review; Source code; Parsing; Code generation; Documentation; Software; Code (set theory); KPI-driven code analysis; TRACE (psycholinguistics); Software development; Programming language; World Wide Web; Static program analysis; Operating system; Key (lock)","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":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.008715915,0.0002425671,0.0002877019,0.0007002455,0.002705025,0.006732304,0.007000346,0.00004884556,0.0001792402],"category_scores_gemma":[0.002413532,0.0002515548,0.00001773499,0.003120277,0.0001098637,0.002488904,0.01491695,0.001345778,0.0001188177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005052629,"about_ca_system_score_gemma":0.001431657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000394993,"about_ca_topic_score_gemma":0.0002607521,"domain_scores_codex":[0.9936425,0.00139008,0.0004190793,0.001189265,0.00223497,0.001124113],"domain_scores_gemma":[0.9968382,0.0007855562,0.00006928684,0.00108564,0.0006945804,0.0005267625],"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":[0.00007911744,0.000181672,0.004506691,0.0001687928,0.00002397809,0.0002511217,0.01335152,0.001767647,0.009342086,0.00005214661,0.0019759,0.9682993],"study_design_scores_gemma":[0.003701825,0.003438033,0.1653235,0.0006092468,0.00001438631,0.0007115716,0.004554754,0.5708191,0.03404998,0.00008387429,0.2142117,0.002481995],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7307892,0.0004551075,0.2616832,0.001083387,0.0002669034,0.003831473,0.00004333033,0.0009874305,0.0008599273],"genre_scores_gemma":[0.9217458,0.000004684277,0.07409607,0.0001979491,0.00005425309,0.0004742369,0.0000519706,0.0000984706,0.003276603],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9658173,"threshold_uncertainty_score":0.9999937,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09172202267189417,"score_gpt":0.3892732159139229,"score_spread":0.2975511932420288,"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."}}