{"id":"W4406806463","doi":"10.18280/isi.300104","title":"Hallucinations in GPT-2 Trained Model","year":2025,"lang":"fr","type":"article","venue":"Ingénierie des systèmes d information","topic":"Hallucinations in medical conditions","field":"Neuroscience","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Psychology; Computer science; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001031068,0.0003096957,0.0003413339,0.001586624,0.0006298698,0.0003840785,0.0005648578,0.0003909805,0.0004786164],"category_scores_gemma":[0.006917973,0.0003712365,0.0001283405,0.00295434,0.0008176187,0.005287916,0.0001478575,0.0006430559,0.0004796843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00148731,"about_ca_system_score_gemma":0.0008867849,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001578098,"about_ca_topic_score_gemma":0.0001973609,"domain_scores_codex":[0.9968382,0.0003029066,0.001350692,0.0003157486,0.0005308082,0.0006616582],"domain_scores_gemma":[0.9981998,0.0005087108,0.0002865019,0.0004890895,0.0003663943,0.0001495302],"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":[0.00001776202,0.0002329245,0.0001373757,0.0007295668,0.00001802729,0.00001592982,0.009212686,0.04314986,0.000472734,0.7990073,0.004773912,0.1422319],"study_design_scores_gemma":[0.001351734,0.00006195366,0.00399884,0.001262059,0.00005441024,0.00004460339,0.001343464,0.8228586,0.00159709,0.1445924,0.02241657,0.0004182566],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04066123,0.0006841842,0.5536367,0.01103345,0.002650905,0.001279292,0.0003703833,0.0002943734,0.3893895],"genre_scores_gemma":[0.9799388,0.0002332681,0.005087175,0.002753478,0.00005485752,0.0003045246,0.0001312511,0.00001692527,0.0114797],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9392776,"threshold_uncertainty_score":0.9998739,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02470563173087292,"score_gpt":0.287810083541481,"score_spread":0.263104451810608,"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."}}