{"id":"W3194114348","doi":"10.1007/s10664-021-09986-0","title":"Empirical evaluation of tools for hairy requirements engineering tasks","year":2021,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Empirical research; Systems engineering; Software engineering; Engineering; Mathematics","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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001572697,0.0003400149,0.0004632274,0.0002790396,0.00007271355,0.0002060533,0.000823898,0.0002112979,0.00004309708],"category_scores_gemma":[0.02603362,0.0003754695,0.0002545962,0.001212829,0.00002150891,0.0008130212,0.0004436439,0.0003591274,0.00001697296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004143635,"about_ca_system_score_gemma":0.0004187939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002739798,"about_ca_topic_score_gemma":6.662875e-7,"domain_scores_codex":[0.9963216,0.00007179335,0.0006275795,0.000741415,0.001473933,0.0007637376],"domain_scores_gemma":[0.994146,0.003658122,0.00008369271,0.0009445521,0.0008853114,0.0002822941],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002840753,0.0004913096,0.1231889,0.001127069,0.0004917243,0.00009766027,0.001118247,0.7928572,0.01393047,0.0007711813,0.007303443,0.05859444],"study_design_scores_gemma":[0.002064228,0.000199528,0.1967971,0.0003294218,0.00008890236,0.00006189213,0.00001693323,0.7388078,0.04005982,0.0002575664,0.02030574,0.001011001],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1918951,0.0007100423,0.8051142,0.0002783541,0.0008399896,0.0004114451,0.00001374938,0.0007248052,0.00001227701],"genre_scores_gemma":[0.7328849,0.000009165295,0.2662986,0.00009876159,0.0002572803,0.0002783931,0.00004447172,0.00007848632,0.00004999486],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5409898,"threshold_uncertainty_score":0.9998697,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.134283438534654,"score_gpt":0.3755986931044231,"score_spread":0.241315254569769,"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."}}