{"id":"W4415683709","doi":"10.3390/info16110937","title":"DefAn: Definitive Answer Dataset for LLM Hallucination Evaluation","year":2025,"lang":"en","type":"article","venue":"Information","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"King Fahd University of Petroleum and Minerals","keywords":"Benchmark (surveying); Benchmarking; Consistency (knowledge bases); Scope (computer science); Scale (ratio); Generative grammar","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":[],"consensus_categories":[],"category_scores_codex":[0.0006590214,0.00005690249,0.00005382037,0.0001622833,0.00009722391,0.0001495153,0.0002235288,0.00004388907,0.000006517809],"category_scores_gemma":[0.0002425568,0.00005785806,0.00001809355,0.0001785476,0.000006315173,0.003101486,0.00005726251,0.00003849414,0.00004586828],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009341357,"about_ca_system_score_gemma":0.0001132945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001620559,"about_ca_topic_score_gemma":0.000008672425,"domain_scores_codex":[0.9993352,0.00002513232,0.000233488,0.00009694513,0.0002094387,0.00009974743],"domain_scores_gemma":[0.9992583,0.00007160475,0.00008962561,0.0002604753,0.0003049986,0.00001495018],"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":[0.000007720531,0.00001579608,0.00004394642,0.00003980253,0.00001010851,4.51037e-8,0.001054294,0.006234948,0.0000159682,0.2293129,0.009857766,0.7534067],"study_design_scores_gemma":[0.0004501219,0.00001998888,0.0007744718,0.00001685245,0.000009415309,6.391716e-7,0.00004518262,0.9458501,0.0003674909,0.01262832,0.0397746,0.00006280028],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001187589,0.00001844097,0.9907421,0.0008490852,0.0004308331,0.0004643695,0.0000911641,0.00004971764,0.006166722],"genre_scores_gemma":[0.8277586,0.000005911732,0.164607,0.002794886,0.00005130265,0.0002880901,0.004442991,0.000002812285,0.00004841162],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9396152,"threshold_uncertainty_score":0.2359383,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03434413762232726,"score_gpt":0.3188867060780858,"score_spread":0.2845425684557585,"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."}}