{"id":"W4385270039","doi":"10.1109/nlbse59153.2023.00019","title":"Evaluating Code Comment Generation With Summarized API Docs","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Automatic summarization; Computer science; Documentation; Application programming interface; Java; Leverage (statistics); Code (set theory); Artificial intelligence; Machine learning; Programming language","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":[0.004038663,0.002338512,0.0009678888,0.002994097,0.0004820307,0.001496635,0.0016656,0.001925249,0.002364933],"category_scores_gemma":[0.02224962,0.000333982,0.001173078,0.001521238,0.0004455954,0.002358285,0.0008651901,0.001161607,0.002196347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001464234,"about_ca_system_score_gemma":0.00150866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01159433,"about_ca_topic_score_gemma":0.01447676,"domain_scores_codex":[0.9971766,0.001040888,0.0002437538,0.0006708973,0.0007338109,0.000133901],"domain_scores_gemma":[0.9827431,0.01224106,0.0007578321,0.001562788,0.0023102,0.0003849512],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002385272,0.001720373,0.02643457,0.002217504,0.0007036964,0.0007055127,0.0004419881,0.3442125,0.01602365,0.001350745,0.06067307,0.5431311],"study_design_scores_gemma":[0.0001485925,0.0005752743,0.003523221,0.0000620369,0.0001051398,0.0001371898,0.0001422647,0.9762793,0.01360241,0.0007417927,0.004642095,0.0000406058],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7154999,0.005364368,0.1603171,0.001602197,0.0008643395,0.001366225,0.02104952,0.08553032,0.008405913],"genre_scores_gemma":[0.7376888,0.0008802759,0.1810511,0.000469927,0.0002041777,0.0005137179,0.07271022,0.001142766,0.005339079],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01159433,"threshold_uncertainty_score":0.02305371,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1338888887134159,"score_gpt":0.3754235916566441,"score_spread":0.2415347029432282,"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."}}