{"id":"W4413863245","doi":"10.35490/ec3.2025.201","title":"Cyber Risk Identification in Construction with Language Models: The Next Generation","year":2025,"lang":"en","type":"article","venue":"Computing in construction","topic":"Software Engineering Techniques and Practices","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Tamkeen; York University; New York University Abu Dhabi","keywords":"Identification (biology); Computer science","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006550687,0.0001033132,0.0001018134,0.000254285,0.0001378667,0.0002604738,0.0002800356,0.00006899508,0.000001381408],"category_scores_gemma":[0.0001023404,0.00008552682,0.00002052355,0.0008561567,0.00006486697,0.000736617,0.00007507131,0.0002858297,0.000001714166],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001023052,"about_ca_system_score_gemma":0.00005639944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003179064,"about_ca_topic_score_gemma":0.0001157718,"domain_scores_codex":[0.9990042,0.000149678,0.0002816868,0.0002981287,0.0001260633,0.0001402381],"domain_scores_gemma":[0.9991614,0.0002212546,0.0001720509,0.0003721137,0.00005979911,0.00001336557],"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":[0.00001261811,0.00002929007,0.03039246,0.00002488473,0.00001771763,0.000005436556,0.001717903,0.1826995,0.00111529,0.1165798,0.0001014597,0.6673037],"study_design_scores_gemma":[0.0002196311,0.00001230782,0.01031063,0.00007550386,0.000007071773,0.00005086098,0.0002483416,0.9823899,0.001404155,0.005062932,0.0001110114,0.000107653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3514784,0.0001302333,0.6471468,0.0002056346,0.0005029562,0.0001438973,3.634963e-7,0.0001782629,0.0002134898],"genre_scores_gemma":[0.8192433,0.0000399712,0.1806001,0.00003443479,0.00005375458,0.0000123854,0.000003173788,0.000004385081,0.000008563991],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7996904,"threshold_uncertainty_score":0.3487683,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0267698074384189,"score_gpt":0.2665932297351993,"score_spread":0.2398234222967804,"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."}}