{"id":"W4417515405","doi":"10.1109/tvt.2025.3608811","title":"DriveSOTIF: Advancing SOTIF Through Multimodal Large Language Models","year":2025,"lang":"en","type":"preprint","venue":"IEEE Transactions on Vehicular Technology","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Benchmarking; Inference; Baseline (sea); Domain (mathematical analysis); Work (physics); Language model; Task analysis; Language understanding","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0002971909,0.0006747908,0.0007201929,0.001102444,0.0005614716,0.0001336734,0.003013276,0.00138031,0.000032346],"category_scores_gemma":[0.00003007606,0.0007382352,0.0004181358,0.001250833,0.0001673442,0.0003343213,0.0001653953,0.003796613,0.0001507165],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003267889,"about_ca_system_score_gemma":0.0003204429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006102457,"about_ca_topic_score_gemma":0.0001720347,"domain_scores_codex":[0.9960835,0.0001779414,0.0006334385,0.001780809,0.0004423114,0.0008819895],"domain_scores_gemma":[0.9958099,0.0001762716,0.0002940322,0.00340062,0.0002076303,0.0001115477],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008117629,0.0005633039,0.00002469052,0.000125525,0.0001927058,0.00004601863,0.001157154,0.9175804,0.001697723,0.03526042,0.0000640404,0.04327989],"study_design_scores_gemma":[0.0006662267,0.00006321714,0.00003683597,0.0002412526,0.00008311522,0.00002532818,0.0001335443,0.9512185,0.01964097,0.02624331,0.000994044,0.0006536516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01904006,0.0003656677,0.9686222,0.005414793,0.0009953381,0.00105734,0.000182285,0.003527869,0.0007944598],"genre_scores_gemma":[0.7525421,0.00009581728,0.245739,0.0003904585,0.00003552588,0.000732801,0.00002208498,0.00004361611,0.0003985789],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7335021,"threshold_uncertainty_score":0.9999161,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009577541560101646,"score_gpt":0.2838089407496976,"score_spread":0.274231399189596,"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."}}