{"id":"W4414587094","doi":"10.1007/s11761-025-00474-7","title":"Benchmarking large language models for supply chain risk identification: an extended evaluation within the LARD-SC framework","year":2025,"lang":"en","type":"article","venue":"Service Oriented Computing and Applications","topic":"Supply Chain Resilience and Risk Management","field":"Business, Management and Accounting","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"University of New South Wales","keywords":"Benchmarking; Interpretability; Blueprint; Supply chain; Identification (biology); Supply chain risk management; Risk management; Set (abstract data type)","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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001958526,0.0001849862,0.0001525912,0.0001902332,0.001593623,0.0004269418,0.0004147331,0.00008143911,0.00001774727],"category_scores_gemma":[0.00007260255,0.0001504957,0.00005469972,0.001215836,0.00004061587,0.0004061849,0.0002221169,0.0001947758,0.00001469715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000333559,"about_ca_system_score_gemma":0.00003577914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004210775,"about_ca_topic_score_gemma":0.0003568016,"domain_scores_codex":[0.9984495,0.00004920658,0.0003832453,0.0005386001,0.0002902817,0.0002891542],"domain_scores_gemma":[0.9984189,0.0001788852,0.0003433518,0.0006161996,0.0004240318,0.00001868065],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002721385,0.0002380668,0.00362645,0.0002286887,0.00007750883,2.695148e-7,0.001970172,0.0357133,0.00006119497,0.8563403,0.0006107083,0.1011062],"study_design_scores_gemma":[0.0004514547,0.00000590007,0.006216909,0.00008744394,0.0002088997,2.952534e-7,0.009369854,0.9025257,0.00002515924,0.07210821,0.008830913,0.0001693249],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1520036,0.0004043302,0.8405121,0.002770758,0.0003535202,0.002439581,0.00002392439,0.000226142,0.001266012],"genre_scores_gemma":[0.9920817,0.00002025604,0.0028637,0.002962139,0.0008781592,0.0007126124,0.0003660365,0.00001973493,0.00009567362],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8668123,"threshold_uncertainty_score":0.9997061,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01134495648519082,"score_gpt":0.289217485497521,"score_spread":0.2778725290123302,"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."}}