{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005385827,0.0007433369,0.0004170937,0.002309017,0.000730281,0.001975931,0.0006977568,0.001240993,0.0009245511],"category_scores_gemma":[0.06523847,0.0003668297,0.000441965,0.001311186,0.0008934375,0.002508436,0.0009223624,0.0007403222,0.0002936557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009187589,"about_ca_system_score_gemma":0.0008771209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001560148,"about_ca_topic_score_gemma":0.002229697,"domain_scores_codex":[0.9927248,0.004182986,0.0006413311,0.001072368,0.001160877,0.0002175925],"domain_scores_gemma":[0.8779576,0.1010022,0.01186088,0.002495865,0.006019342,0.0006641203],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.003659957,0.002440237,0.1327202,0.008658414,0.0002821813,0.003955949,0.1195852,0.008654765,0.4790673,0.008409657,0.005528573,0.2270375],"study_design_scores_gemma":[0.0007105292,0.006630472,0.5147941,0.001489416,0.0008118201,0.004939308,0.05200456,0.1191867,0.2152577,0.02810097,0.05538279,0.0006916887],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9423931,0.0003197922,0.05444155,0.00020567,0.00003210161,0.0004140809,0.0005217351,0.0003739909,0.00129789],"genre_scores_gemma":[0.9205474,0.0002274618,0.07643785,0.0001880587,0.00004094459,0.0004776402,0.001499841,0.0001184398,0.0004624644],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005385827,"threshold_uncertainty_score":0.02848333,"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."}}