{"id":"W4243472257","doi":"10.1109/icse.2015.212","title":"Leveraging Informal Documentation to Summarize Classes and Methods in Context","year":2015,"lang":"en","type":"article","venue":"2015 IEEE/ACM 37th IEEE International Conference on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Documentation; Automatic summarization; Software documentation; Identifier; Context (archaeology); Program comprehension; Source code; Code (set theory); Software; Focus (optics); Software engineering; Task (project management); Benchmark (surveying); Internal documentation; Information retrieval; Software bug; World Wide Web; Software development; Programming language; Software system; Software construction; Set (abstract data type); Engineering; Systems engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001116668,0.0003178742,0.0002968346,0.0008287707,0.00004152778,0.000523543,0.001386941,0.0001144914,0.00002358308],"category_scores_gemma":[0.004021336,0.0003438384,0.00004632694,0.0004879656,0.00002753504,0.001281456,0.0003670123,0.0004674284,0.00008918249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003754548,"about_ca_system_score_gemma":0.000217333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001462361,"about_ca_topic_score_gemma":0.00002298141,"domain_scores_codex":[0.9976248,0.00006975947,0.0004604103,0.0005470216,0.0007913134,0.0005067369],"domain_scores_gemma":[0.9975184,0.0009985702,0.000080265,0.0005475835,0.000453581,0.0004016448],"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":[0.0004160687,0.0003916597,0.1819492,0.0003587905,0.0005031149,0.0004305404,0.03050445,0.3380124,0.01912472,0.05768492,0.01352785,0.3570963],"study_design_scores_gemma":[0.005713773,0.0008258062,0.09195226,0.001373524,0.00002065921,0.0001933059,0.0009964589,0.8269508,0.03867954,0.002447432,0.02795853,0.002887881],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1588888,0.00005209244,0.83714,0.0006638491,0.002424558,0.0002601233,0.000006349617,0.0004089907,0.0001552745],"genre_scores_gemma":[0.6775598,0.00002024515,0.3216636,0.000228263,0.0001335621,0.00009436991,0.00000771444,0.00002937059,0.0002630821],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.518671,"threshold_uncertainty_score":0.9999014,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08999989506615488,"score_gpt":0.3885358259163932,"score_spread":0.2985359308502383,"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."}}