{"id":"W4412438306","doi":"10.1145/3730436.3730529","title":"Comparative Analysis of Large Language Models for Context-Aware Code Completion using SAFIM Framework","year":2025,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Context (archaeology); Code (set theory); Programming language; Natural language processing","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":[],"consensus_categories":[],"category_scores_codex":[0.0002489958,0.0001034506,0.0004284882,0.000286513,0.00009857844,0.00004552665,0.0004290464,0.00007000846,0.00002153181],"category_scores_gemma":[0.00002172897,0.00009661244,0.0001552112,0.0008513712,0.00002245323,0.0002100235,0.0001523883,0.00008162161,9.029249e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004925453,"about_ca_system_score_gemma":0.00005087964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001927478,"about_ca_topic_score_gemma":0.0003480003,"domain_scores_codex":[0.9989904,0.00005328035,0.0003025738,0.0003093002,0.0001516076,0.000192866],"domain_scores_gemma":[0.9989365,0.0002820389,0.0001045993,0.0004668346,0.0001784075,0.00003166568],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008347707,0.00005054526,0.0004064305,0.00002259182,0.0003648348,4.644399e-7,0.003295392,0.1713247,0.0003361134,0.8232643,0.0001005657,0.000825712],"study_design_scores_gemma":[0.0002203695,0.00001063034,0.0002086553,0.00004037222,0.0001419709,1.408329e-7,0.0008505419,0.9869686,0.00112012,0.01025076,0.0000984822,0.00008933862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04801323,0.0001303102,0.950323,0.0002088791,0.00009829757,0.0002169949,0.00004757959,0.00007078948,0.0008909194],"genre_scores_gemma":[0.784825,9.072128e-7,0.2145616,0.0004578785,0.000009869609,0.000007627189,0.00001162292,0.000002022452,0.0001234578],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8156439,"threshold_uncertainty_score":0.3939741,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07661870692166582,"score_gpt":0.3764386418616509,"score_spread":0.299819934939985,"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."}}