{"id":"W6911919542","doi":"10.5281/zenodo.14183387","title":"Supplementary Material, Towards the LLM-Based Generation of Formal Specifications from Natural-Language Contracts: Early Experiments with Symboleo","year":2024,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"","field":"","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Formal specification; Formal methods; Formal verification; Refinement","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":[0.002968126,0.003376614,0.001490952,0.002946285,0.001017508,0.00254836,0.00331789,0.003817051,0.1032338],"category_scores_gemma":[0.01516459,0.000930879,0.001869671,0.002983975,0.000664663,0.001815577,0.002271091,0.002198543,0.08686034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002536705,"about_ca_system_score_gemma":0.00316729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02234426,"about_ca_topic_score_gemma":0.03767107,"domain_scores_codex":[0.9973143,0.000773848,0.0002852129,0.0005461626,0.0008491653,0.0002313762],"domain_scores_gemma":[0.9905984,0.005494738,0.0003989426,0.002030631,0.001127825,0.0003494962],"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":[0.0002239191,0.0001371829,0.0008285869,0.001043861,0.00005514386,0.0000803408,0.00003839535,0.001973464,0.0003036927,0.001432409,0.9879273,0.00595575],"study_design_scores_gemma":[0.001783284,0.0001456792,0.006133222,0.0005905151,0.000111015,0.0003196561,0.0002541227,0.01596244,0.002980759,0.01350422,0.9580946,0.0001204251],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0007553062,0.0001155165,0.0007901619,0.0001744813,0.00006376368,0.00004299835,0.9929234,0.003469181,0.001665202],"genre_scores_gemma":[0.00118791,0.00004331209,0.002003032,0.00006664653,0.000005966421,0.0001631389,0.9955149,0.0002787776,0.000736381],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1032338,"threshold_uncertainty_score":0.3453514,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05607664310694618,"score_gpt":0.2722292201756608,"score_spread":0.2161525770687146,"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."}}