{"id":"W3096440690","doi":"10.1109/icsme46990.2020.00052","title":"Characterizing Task-Relevant Information in Natural Language Software Artifacts","year":2020,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Natural language; Relevance (law); Task (project management); Consistency (knowledge bases); Semantics (computer science); Software documentation; Artifact (error); Natural language processing; Software; Documentation; Software development; Key (lock); Frame (networking); Artificial intelligence; Information retrieval; Programming language; Software development process","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001322102,0.00008728629,0.00009485621,0.000116278,0.00002361685,0.0001774814,0.0004834083,0.00003400951,0.00002024868],"category_scores_gemma":[0.001168041,0.00007852006,0.0000245312,0.0004656509,0.000008074575,0.00162485,0.0002398593,0.0002370987,0.0004524041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000459331,"about_ca_system_score_gemma":0.00004062945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002807094,"about_ca_topic_score_gemma":0.000003142438,"domain_scores_codex":[0.999119,0.00001787966,0.0001747868,0.0001495675,0.0002743794,0.0002644015],"domain_scores_gemma":[0.9994435,0.0001841162,0.00002715929,0.0002066009,0.00003403384,0.0001046156],"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":[0.00004496994,0.00007293599,0.03662477,0.000425394,0.00003815232,0.00032367,0.0655539,0.002216388,0.05247668,0.002812397,0.003570712,0.83584],"study_design_scores_gemma":[0.001205481,0.0001555582,0.3385888,0.0001032939,0.000002260589,0.00002969207,0.0004323668,0.6128752,0.03423657,0.00006422609,0.01150587,0.0008007533],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5473622,0.00008531411,0.4468926,0.004048395,0.0002650964,0.0002022297,0.000002106313,0.00102151,0.0001205103],"genre_scores_gemma":[0.9745547,0.000002317171,0.02391711,0.001444467,0.00003498238,0.000008328747,0.000009402514,0.000005004237,0.00002369944],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8350393,"threshold_uncertainty_score":0.5814891,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01164665645122397,"score_gpt":0.2386682515069486,"score_spread":0.2270215950557246,"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."}}