{"id":"W7126202239","doi":"10.18280/isi.301203","title":"Interpretable Multi-Label Classification of Human- and Large Language Model-Generated Texts Using Transformer Embeddings and Explainable Artificial Intelligence","year":2025,"lang":"","type":"article","venue":"Ingénierie des systèmes d information","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Transformer; Natural language; Pattern recognition (psychology); Applications of artificial intelligence; Language model","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001667621,0.0005334048,0.0006668593,0.001043389,0.001195777,0.001207703,0.0006310517,0.0004041661,0.00003168186],"category_scores_gemma":[0.0003840988,0.0005905068,0.00009354353,0.00172324,0.0006259945,0.008935631,0.0003100111,0.0003969896,0.00001337503],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004599974,"about_ca_system_score_gemma":0.0004186877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006272178,"about_ca_topic_score_gemma":0.0001779103,"domain_scores_codex":[0.9957466,0.0001843722,0.002165605,0.0005953507,0.0004295064,0.0008785356],"domain_scores_gemma":[0.9973013,0.0001268488,0.0008219845,0.0006095241,0.0009575514,0.0001828203],"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":[0.0001643835,0.0003836431,0.0004035418,0.002609644,0.0001451423,0.000005208074,0.1488108,0.008520721,0.1718057,0.2152751,0.00002584207,0.4518502],"study_design_scores_gemma":[0.0002173944,0.0001316418,0.00009804288,0.0009530384,0.0000723353,0.00001272358,0.0141316,0.8329437,0.1398484,0.0111415,0.00002786246,0.0004216716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3649142,0.0007518201,0.6323633,0.00004838729,0.0002180321,0.0006972572,0.00003920957,0.00007878715,0.0008890145],"genre_scores_gemma":[0.9689489,0.0001875514,0.03035112,0.0001371463,0.00002681563,0.00006532625,0.00004227566,0.00002217021,0.0002186661],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.824423,"threshold_uncertainty_score":0.9998291,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0527775078637612,"score_gpt":0.3249960898983826,"score_spread":0.2722185820346215,"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."}}