{"id":"W2760730809","doi":"10.1109/re.2017.64","title":"Panel: Context-Dependent Evaluation of Tools for NL RE Tasks: Recall vs. Precision, and Beyond","year":2017,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Recall; Context (archaeology); Computer science; Precision and recall; Cognitive psychology; Artificial intelligence; Natural language processing; Psychology","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":[0.002607856,0.0000828296,0.0001520416,0.00006590224,0.0001293105,0.0003868828,0.0008588295,0.00006090728,0.00002999012],"category_scores_gemma":[0.008174922,0.00006979443,0.00004025613,0.00004326711,0.00004293469,0.0007484488,0.000352955,0.0000692151,0.000007348268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004507024,"about_ca_system_score_gemma":0.00009800713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004461589,"about_ca_topic_score_gemma":0.00002884056,"domain_scores_codex":[0.9985266,0.00004629016,0.0001924702,0.0003167117,0.0007353267,0.0001825944],"domain_scores_gemma":[0.9969902,0.00126749,0.00008122275,0.001035094,0.0005500411,0.00007597332],"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":[0.00002180551,0.00003112859,0.001695076,0.00003510873,0.00002860913,0.000001004363,0.0003626721,0.0002199029,0.0005415474,0.003711083,0.00349506,0.989857],"study_design_scores_gemma":[0.006120477,0.001188763,0.321007,0.0001956038,0.00007913641,0.00002205442,0.000197583,0.5791649,0.04896761,0.02988897,0.01244526,0.0007227139],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2024477,0.0005041504,0.7918392,0.001739562,0.0005298108,0.001414155,0.00001361257,0.0001454224,0.001366414],"genre_scores_gemma":[0.9755834,0.00001854405,0.02381366,0.00004000139,0.00003314026,0.00007582096,0.00000189917,0.000008157753,0.0004253192],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9891343,"threshold_uncertainty_score":0.9786736,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1336489168214906,"score_gpt":0.3628396132054447,"score_spread":0.2291906963839541,"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."}}