{"id":"W4409903669","doi":"10.1007/s43681-025-00731-7","title":"Ethical impacts of a NLP-based ML framework: the case of AI2","year":2025,"lang":"en","type":"article","venue":"AI and Ethics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Natural language processing; Psychology; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00194033,0.00008525135,0.0001529564,0.0000738402,0.000184889,0.00005737158,0.0004358765,0.0004485394,0.000007713827],"category_scores_gemma":[0.002627823,0.00006061311,0.00005254679,0.0005331771,0.0003876004,0.00009614157,0.0001860705,0.001551655,0.00000337292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001168946,"about_ca_system_score_gemma":0.0004141681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009975102,"about_ca_topic_score_gemma":0.0004369067,"domain_scores_codex":[0.9989288,0.0002449993,0.0002603931,0.0001897306,0.0001816729,0.0001943853],"domain_scores_gemma":[0.9957027,0.003328972,0.00007997779,0.0005434148,0.0002896217,0.00005531781],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001210906,0.0000400594,0.0002301926,0.0001259002,0.00001324955,0.00007259895,0.007554658,0.0002871657,0.0004513415,0.9820083,0.0003810068,0.008823355],"study_design_scores_gemma":[0.0001459716,0.0002602064,0.0003456928,0.0004652641,0.00003129156,0.00004745618,0.001224214,0.1746677,0.1218695,0.6988677,0.001884492,0.0001904544],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09662505,0.0003740877,0.7985108,0.1032829,0.0002414888,0.0001369146,0.000003343611,0.00003569104,0.0007897088],"genre_scores_gemma":[0.981781,0.00004716824,0.00570628,0.01241478,0.00001468143,0.000003639187,2.382361e-7,0.000003233985,0.00002900323],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8851559,"threshold_uncertainty_score":0.6741254,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04437262732881977,"score_gpt":0.3861558590667429,"score_spread":0.3417832317379231,"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."}}