{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001516758,0.00006276723,0.00008510037,0.00006286104,0.00008687922,0.0002390256,0.0005398812,0.00003184353,0.000005719778],"category_scores_gemma":[0.01074765,0.00006027427,0.00002264881,0.00003521335,0.00001748962,0.0008381758,0.0002388394,0.00003844105,0.0000018183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003944822,"about_ca_system_score_gemma":0.00005961182,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001287064,"about_ca_topic_score_gemma":0.000001673452,"domain_scores_codex":[0.9990299,0.00001053097,0.0001097289,0.0001821419,0.0005122849,0.0001553841],"domain_scores_gemma":[0.9985425,0.000442329,0.00004481374,0.0006080591,0.0003159338,0.00004634833],"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":[0.000005928798,0.0000424695,0.02557051,0.00021926,0.00009324626,0.000001601609,0.0003146548,0.004369582,0.0053598,0.007877097,0.0008970988,0.9552488],"study_design_scores_gemma":[0.001046618,0.0001013611,0.2999104,0.00007380408,0.0000200839,0.000002905071,0.000005317323,0.6809325,0.01620076,0.001012163,0.0005089254,0.0001851306],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1417278,0.00008730689,0.8574349,0.00008106938,0.0002052205,0.0003014955,0.000002090497,0.0001018669,0.00005827715],"genre_scores_gemma":[0.8412924,0.000002753958,0.1585684,0.000005111587,0.00002674617,0.00005068682,9.301391e-7,0.000006343296,0.00004663564],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9550636,"threshold_uncertainty_score":0.9975852,"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."}}