{"id":"W4400242886","doi":"10.1145/3643991.3644864","title":"CodeLL: A Lifelong Learning Dataset to Support the Co-Evolution of Data and Language Models of Code","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Lifelong learning; Code (set theory); Data modeling; Artificial intelligence; Natural language processing; Data science; Programming language; Software engineering; Psychology","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":[0.001703483,0.001186523,0.0006174899,0.004366122,0.0009319041,0.001579871,0.002056108,0.001997389,0.003179791],"category_scores_gemma":[0.01367768,0.0004174823,0.001017629,0.004092806,0.0006552381,0.002281958,0.002413906,0.002465264,0.005254027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001158732,"about_ca_system_score_gemma":0.001880262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01135449,"about_ca_topic_score_gemma":0.03154083,"domain_scores_codex":[0.9975945,0.0004291187,0.0003120399,0.0008732975,0.0005996873,0.0001912607],"domain_scores_gemma":[0.9912242,0.003059249,0.001136178,0.002126396,0.001747593,0.0007064815],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008446386,0.001574989,0.149314,0.003025315,0.0004050421,0.0008102893,0.002014055,0.01613626,0.01065146,0.005670737,0.5823429,0.2272103],"study_design_scores_gemma":[0.0003615718,0.0005842345,0.1304624,0.0005129689,0.0001394025,0.001078145,0.001177199,0.09258204,0.01352297,0.009456989,0.749831,0.0002911066],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.1342643,0.002078384,0.03163119,0.001517357,0.0004073643,0.0005674267,0.8039822,0.01816491,0.007386917],"genre_scores_gemma":[0.0631723,0.0003470911,0.03417721,0.0002916922,0.00006922598,0.0008253118,0.8971856,0.0009901886,0.002941428],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01135449,"threshold_uncertainty_score":0.02257675,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05609616902081996,"score_gpt":0.3477873227265498,"score_spread":0.2916911537057298,"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."}}