{"id":"W4409186862","doi":"10.1007/s00530-025-01769-7","title":"Towards a unified evaluation framework: integrating human perception and metrics for AI-generated images","year":2025,"lang":"en","type":"article","venue":"Multimedia Systems","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Perception; Computer graphics; Cryptography; Artificial intelligence; Data science; Human–computer interaction; Computer security; Psychology","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":[0.0013413,0.0001322768,0.0001804445,0.0003885166,0.000297074,0.0004012446,0.0002052658,0.0001413174,0.000005499072],"category_scores_gemma":[0.0006063436,0.0001169448,0.00005254095,0.0007936319,0.00002841747,0.0003186929,0.00006077482,0.000140789,0.000005957384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001423182,"about_ca_system_score_gemma":0.00006830352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002315108,"about_ca_topic_score_gemma":0.00001463712,"domain_scores_codex":[0.9985638,0.0002349914,0.000342201,0.0003709935,0.0003095803,0.0001784041],"domain_scores_gemma":[0.9989388,0.0001196923,0.0001120548,0.0002319869,0.0005440537,0.00005342619],"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":[0.00001634804,0.0001293686,0.001537964,0.0002796955,0.00007328353,0.000001245305,0.003194835,0.0003300965,0.1052572,0.01996123,0.001950158,0.8672686],"study_design_scores_gemma":[0.0005123403,0.00008149456,0.004463231,0.0001053326,0.0000246352,0.000002401614,0.0005470666,0.99101,0.001762514,0.001070473,0.0002963663,0.0001241205],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03750117,0.0002007283,0.9586272,0.0003455829,0.001861439,0.0008693683,0.000004721831,0.0001852872,0.0004045553],"genre_scores_gemma":[0.9533635,0.000007320155,0.04574702,0.0001053078,0.0001127071,0.0002444697,0.0000251403,0.000007052381,0.0003875268],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9906799,"threshold_uncertainty_score":0.4768869,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05179110395672034,"score_gpt":0.3740683480577116,"score_spread":0.3222772441009912,"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."}}