{"id":"W7155511093","doi":"10.5281/zenodo.19734193","title":"Why and how to evaluate Trustworthiness in AI?","year":2025,"lang":"","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian AIDS Treatment Information Exchange","funders":"European Commission","keywords":"Trustworthiness; Sociotechnical system; Work (physics); Simple (philosophy); Strengths and weaknesses; Perception","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09105615,0.001146656,0.001762335,0.006612933,0.002340282,0.01039308,0.001648282,0.00339607,0.002082796],"category_scores_gemma":[0.3309642,0.0006560045,0.001310092,0.004220821,0.01048322,0.01587451,0.003718674,0.003808302,0.001253031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004271018,"about_ca_system_score_gemma":0.005902593,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004805074,"about_ca_topic_score_gemma":0.003842949,"domain_scores_codex":[0.9029126,0.05901718,0.009082679,0.003997087,0.02331745,0.001672959],"domain_scores_gemma":[0.6625952,0.2001518,0.03932249,0.02381519,0.06608294,0.0080324],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007272893,0.0005102272,0.1395583,0.004541823,0.001034625,0.0003249662,0.01954045,0.006514883,0.00477403,0.1372115,0.01776403,0.6674979],"study_design_scores_gemma":[0.0002616148,0.001765727,0.1251294,0.01280313,0.0009437589,0.001119015,0.03154615,0.03811349,0.01104204,0.7107337,0.06574316,0.0007989549],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.277333,0.04216938,0.4837386,0.1020447,0.003111396,0.002244741,0.0009046553,0.001496456,0.08695705],"genre_scores_gemma":[0.8693475,0.005429474,0.1193212,0.002153423,0.0005353956,0.0008717662,0.0002427447,0.0002729195,0.001825657],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.09105615,"threshold_uncertainty_score":0.4815567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05420382342108316,"score_gpt":0.3451927253118996,"score_spread":0.2909889018908164,"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."}}