{"id":"W3212549866","doi":"10.18653/v1/2021.findings-emnlp.214","title":"Novel Natural Language Summarization of Program Code via Leveraging Multiple Input Representations","year":2021,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Korea Advanced Institute of Science and Technology","keywords":"Computer science; Automatic summarization; Programming language; Python (programming language); Source code; Code (set theory); Encoder; Redundant code; Code generation; Task (project management); Artificial intelligence; Natural language processing; Set (abstract data type); Operating system","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":[0.0001195762,0.00006467552,0.00008421206,0.00009031461,0.0000424082,0.00008285796,0.0003221084,0.00002774942,0.00001494021],"category_scores_gemma":[0.0009366186,0.00006434265,0.0000365186,0.0007181891,0.00001954168,0.0002741978,0.0002632442,0.0001164889,0.000006807297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002966333,"about_ca_system_score_gemma":0.00007162157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001563868,"about_ca_topic_score_gemma":0.00006614857,"domain_scores_codex":[0.999122,0.00002350745,0.0001476668,0.0002459595,0.0002868111,0.0001740412],"domain_scores_gemma":[0.9988561,0.000428093,0.00002931902,0.0004339126,0.0002079328,0.00004466433],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006884853,0.000679929,0.142588,0.0001561214,0.0001019519,0.00009511779,0.006039095,0.01357996,0.5653492,0.0049885,0.000902032,0.2655133],"study_design_scores_gemma":[0.000393071,0.00001654862,0.08050559,0.00001833953,0.000002460887,0.00002617355,0.0000947579,0.7836003,0.1349617,0.00003672087,0.0002235957,0.0001207812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06534787,0.0001093185,0.9334063,0.0002399987,0.0001893834,0.000141592,0.000002398994,0.0003709829,0.0001921538],"genre_scores_gemma":[0.7253437,0.000001438608,0.2740079,0.00002467636,0.00001824104,0.00001517432,0.00002230255,0.000006039869,0.0005604886],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7700203,"threshold_uncertainty_score":0.2623817,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02481779938061277,"score_gpt":0.3109085428145918,"score_spread":0.2860907434339791,"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."}}