{"id":"W4321471877","doi":"","title":"Identifying Similar Test Cases That Are Specified in Natural Language","year":2022,"lang":"en","type":"report","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Test (biology); Natural (archaeology); Computer science; Natural language processing; Linguistics; Artificial intelligence; Geography; Geology; Archaeology; Philosophy; Paleontology","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":[0.004974076,0.002110079,0.00143485,0.008106047,0.001050187,0.002469492,0.003223129,0.002318822,0.003159827],"category_scores_gemma":[0.05555964,0.00063333,0.003030647,0.004144728,0.001764443,0.003382311,0.001793901,0.001732597,0.001117733],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001859209,"about_ca_system_score_gemma":0.003170657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006439561,"about_ca_topic_score_gemma":0.006974685,"domain_scores_codex":[0.9840552,0.004386422,0.002103593,0.003655202,0.004948262,0.00085131],"domain_scores_gemma":[0.9404731,0.04206364,0.005778268,0.005301013,0.005734934,0.000648977],"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":[0.001866323,0.003386408,0.1129856,0.004981099,0.001309247,0.02474519,0.006050654,0.06852412,0.09079995,0.05552239,0.0316599,0.5981691],"study_design_scores_gemma":[0.0006617807,0.00155444,0.04423346,0.00112227,0.0009568892,0.01917311,0.004033179,0.6623822,0.08611485,0.1024248,0.07691582,0.0004271868],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2933698,0.0009247142,0.681003,0.001093662,0.0003083761,0.002478204,0.005041176,0.009353504,0.006427533],"genre_scores_gemma":[0.5597674,0.000468489,0.4062934,0.0009569578,0.0002063305,0.002476182,0.02525974,0.001628239,0.002943396],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008106047,"threshold_uncertainty_score":0.02630579,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04958766760511681,"score_gpt":0.2766729641058174,"score_spread":0.2270852965007006,"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."}}