{"id":"W6997367243","doi":"","title":"Using Repository Level Embeddings to Generate Code Using Large Language Models","year":2024,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Code (set theory); Source code; Natural language; Key (lock); Set (abstract data type)","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":[0.0007772586,0.0009961046,0.0005131256,0.001332143,0.0004877409,0.001082334,0.00104706,0.001048072,0.003765988],"category_scores_gemma":[0.007089075,0.0007287199,0.001230355,0.0009165835,0.0004837665,0.002998487,0.001494149,0.00178983,0.00335234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006588842,"about_ca_system_score_gemma":0.001005189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002257936,"about_ca_topic_score_gemma":0.005201836,"domain_scores_codex":[0.9992114,0.0002654388,0.00005186876,0.0002210762,0.0001851533,0.00006510355],"domain_scores_gemma":[0.9959086,0.002233024,0.0002131606,0.0007548694,0.0007843518,0.0001060501],"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":[0.0005379091,0.0005671832,0.00950924,0.0004496585,0.000142789,0.000674637,0.0006369628,0.250623,0.02322143,0.02292951,0.03493074,0.655777],"study_design_scores_gemma":[0.00002639686,0.00005148876,0.0002677125,0.00001546629,0.00002329257,0.00005992679,0.00006698891,0.9804782,0.005348013,0.01138131,0.002267946,0.00001323316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1195213,0.0002771932,0.8434405,0.0006294805,0.0002946728,0.000217121,0.001985858,0.02993422,0.003699607],"genre_scores_gemma":[0.5127759,0.0001853677,0.4671559,0.0002065204,0.00007385576,0.0002989542,0.009784452,0.004923336,0.004595642],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003765988,"threshold_uncertainty_score":0.01259851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05795592383751554,"score_gpt":0.3158428256601142,"score_spread":0.2578869018225987,"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."}}