{"id":"W4393315183","doi":"10.1007/978-3-031-57327-9_13","title":"Natural2CTL: A Dataset for Natural Language Requirements and Their CTL Formal Equivalents","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Equivalent; Programming language; CTL*; Natural language; Natural language processing; Artificial intelligence","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":[0.001418376,0.001906071,0.0008153337,0.006928585,0.0007594338,0.001529157,0.001912641,0.002480617,0.01806615],"category_scores_gemma":[0.01421071,0.0005988985,0.001552919,0.005364052,0.0005197473,0.001892752,0.002005673,0.00187175,0.01536953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001901455,"about_ca_system_score_gemma":0.002619565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02053251,"about_ca_topic_score_gemma":0.03144737,"domain_scores_codex":[0.9973206,0.0005062843,0.0003725515,0.00047588,0.001065598,0.0002591012],"domain_scores_gemma":[0.9869471,0.007245763,0.0009935248,0.002054289,0.001908458,0.0008508489],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007223864,0.0003696557,0.01042725,0.00358981,0.0001119439,0.0007666113,0.0003032601,0.004860875,0.004307513,0.006897409,0.9325159,0.03512746],"study_design_scores_gemma":[0.0005811965,0.0001910704,0.02561433,0.0006090184,0.00009686831,0.001148086,0.0006433438,0.01547236,0.006442998,0.006678822,0.9423857,0.0001360566],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.01280405,0.0005684423,0.00281868,0.0003380149,0.00006392816,0.0001544334,0.9716772,0.005147117,0.006428187],"genre_scores_gemma":[0.008505577,0.0002000014,0.003944814,0.0001566356,0.00001407026,0.0003102619,0.9850815,0.0003836631,0.001403525],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02053251,"threshold_uncertainty_score":0.06043726,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02064500264804897,"score_gpt":0.3020611085821761,"score_spread":0.2814161059341271,"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."}}