{"id":"W4253188200","doi":"10.31224/osf.io/wxv9e","title":"Predicting Verification Methods from Natural Language Requirements","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Similarity (geometry); Data mining; Inference; Set (abstract data type); Natural language; Consistency (knowledge bases); Certification; Artificial intelligence; Programming language","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00438591,0.0006271214,0.0003464836,0.003454083,0.0004034237,0.001519254,0.0008077721,0.00094218,0.002317778],"category_scores_gemma":[0.03852164,0.0002780628,0.0009388068,0.001487246,0.000625759,0.00218429,0.0008641314,0.001151302,0.0008609647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001732985,"about_ca_system_score_gemma":0.001685428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006759461,"about_ca_topic_score_gemma":0.008024347,"domain_scores_codex":[0.9942731,0.002852715,0.0004169435,0.0008567066,0.001425141,0.0001752633],"domain_scores_gemma":[0.9454587,0.04310294,0.003153755,0.001711254,0.006188229,0.0003850981],"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":[0.0005569067,0.0007800495,0.07591604,0.001004374,0.0002067951,0.0006062589,0.0008186068,0.3652856,0.01283177,0.02310121,0.01207368,0.5068187],"study_design_scores_gemma":[0.00002045177,0.0000569997,0.005824158,0.00003743383,0.00001272844,0.00008683853,0.000155336,0.9793128,0.003618926,0.009156787,0.0017008,0.00001684503],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2969539,0.000454257,0.6937081,0.0007818555,0.00005877017,0.0004647467,0.002355078,0.00186585,0.003357518],"genre_scores_gemma":[0.7028728,0.0001307318,0.2890095,0.0001359104,0.00003469054,0.0003128243,0.006501578,0.0001541885,0.000847764],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006759461,"threshold_uncertainty_score":0.02319515,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06407901670036724,"score_gpt":0.390507515203784,"score_spread":0.3264284985034168,"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."}}