{"id":"W4393732781","doi":"10.5281/zenodo.8122618","title":"Dataset for Automatic Refactoring Candidate Identification Leveraging Effective Code Representation","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Code refactoring; Computer science; Code (set theory); Identification (biology); Representation (politics); Programming language; Software; Biology","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":[0.001721075,0.003284811,0.001168799,0.005986541,0.001084412,0.001656519,0.003553169,0.002598175,0.008828558],"category_scores_gemma":[0.006377431,0.0005861349,0.001668523,0.005597232,0.0006146471,0.001258502,0.001935319,0.00186964,0.0193773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002219785,"about_ca_system_score_gemma":0.00266457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02506958,"about_ca_topic_score_gemma":0.05453433,"domain_scores_codex":[0.9976752,0.0004040856,0.0002926279,0.000615287,0.0007926213,0.0002202989],"domain_scores_gemma":[0.9962399,0.001050435,0.0003161345,0.0009569402,0.001163583,0.0002729599],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002927032,0.0003095742,0.003853178,0.002215185,0.0001250726,0.0002563869,0.00009060173,0.003129262,0.002083743,0.00126153,0.9647514,0.0216313],"study_design_scores_gemma":[0.0006618541,0.0001854768,0.01653369,0.0006124761,0.0001833441,0.0006793991,0.0002794715,0.01433675,0.007187658,0.003033852,0.9561854,0.0001205487],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.005315326,0.0007163926,0.001466206,0.0002570848,0.00009461592,0.0001111887,0.9853356,0.004369454,0.002334266],"genre_scores_gemma":[0.001639058,0.00009310519,0.001916678,0.00005284751,0.00000694775,0.00009854466,0.9954269,0.0000953413,0.0006705959],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02506958,"threshold_uncertainty_score":0.04984736,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04331755302203935,"score_gpt":0.3214804849110235,"score_spread":0.2781629318889841,"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."}}