{"id":"W2758181130","doi":"10.1109/rew.2017.25","title":"Evaluation of Tools for Hairy Requirements and Software Engineering Tasks","year":2017,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Task (project management); Automatic summarization; Context (archaeology); Precision and recall; Recall; Software engineering; Software; Scale (ratio); Software system; Artificial intelligence; Dependability; Human–computer interaction; Programming language; Systems engineering; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01525058,0.001631045,0.001350206,0.009990514,0.0008775962,0.003482022,0.002062156,0.001922412,0.001263833],"category_scores_gemma":[0.1071053,0.0003853949,0.00150866,0.003833831,0.001059555,0.005272644,0.002294465,0.001203713,0.0005805364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001412248,"about_ca_system_score_gemma":0.001278066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001797203,"about_ca_topic_score_gemma":0.001712587,"domain_scores_codex":[0.9694192,0.01164631,0.004455249,0.002700133,0.01103405,0.0007451531],"domain_scores_gemma":[0.8451834,0.1161921,0.01347696,0.007246758,0.01501307,0.0028878],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.004355209,0.002045997,0.04785321,0.005988698,0.001439716,0.0006104491,0.004793372,0.03883873,0.03363796,0.00378556,0.008583624,0.8480674],"study_design_scores_gemma":[0.001504968,0.03053088,0.1812491,0.002998964,0.002467359,0.003717286,0.007724604,0.5787162,0.1290034,0.01363449,0.04747309,0.00097965],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8043051,0.0079838,0.1695807,0.0005857842,0.0003496204,0.001351062,0.001320541,0.006925067,0.007598358],"genre_scores_gemma":[0.8495459,0.001219472,0.1440589,0.0001753788,0.0001127685,0.0004807994,0.002912845,0.0003951444,0.00109884],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01525058,"threshold_uncertainty_score":0.08065373,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.132136767363288,"score_gpt":0.3629018789609057,"score_spread":0.2307651115976177,"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."}}