{"id":"W6930477573","doi":"10.5281/zenodo.14183386","title":"Supplementary Material, Towards the LLM-Based Generation of Formal Specifications from Natural-Language Contracts: Early Experiments with Symboleo","year":2025,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Molecular Biology Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Formal specification; Formal methods; Formal verification; Software","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.003384878,0.002322895,0.001152634,0.003535263,0.0008737997,0.002500548,0.003217184,0.003227822,0.07981429],"category_scores_gemma":[0.01816721,0.0008401938,0.001578123,0.003562524,0.0006110773,0.001500689,0.002131102,0.002182204,0.06742902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002400148,"about_ca_system_score_gemma":0.003187017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01972672,"about_ca_topic_score_gemma":0.03962575,"domain_scores_codex":[0.9971187,0.0008417711,0.0003785467,0.0005694176,0.0008571877,0.0002343668],"domain_scores_gemma":[0.9884621,0.006595989,0.0006071074,0.002507744,0.001352247,0.0004748983],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000196945,0.0001166929,0.001252076,0.001665322,0.00006636971,0.00007407558,0.0000474503,0.001764096,0.0003112608,0.001500733,0.988477,0.004527977],"study_design_scores_gemma":[0.001421078,0.00008346795,0.00613017,0.0006304121,0.00008573703,0.0001683764,0.0001937254,0.005913413,0.001688147,0.006519485,0.9770929,0.00007311292],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0003424613,0.00007357511,0.0003085193,0.0001282325,0.00003170401,0.00002526235,0.9971541,0.001194373,0.0007417339],"genre_scores_gemma":[0.0007222075,0.00004266221,0.001122968,0.00006728903,0.000004201091,0.0001196762,0.9973853,0.0001143509,0.0004212878],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.07981429,"threshold_uncertainty_score":0.2670054,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02857803114807167,"score_gpt":0.2693016141996271,"score_spread":0.2407235830515554,"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."}}