{"id":"W4408033756","doi":"10.21203/rs.3.rs-5596193/v1","title":"AI-SSIM: Human-Centric Image Assessment through Pseudo-Reference Generation and Logical Consistency Analysis in AI-Generated Visuals","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"","keywords":"Consistency (knowledge bases); Image (mathematics); Computer science; Artificial intelligence; Computer vision; Computer graphics (images)","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002406498,0.0003733699,0.0006829251,0.00182453,0.0006301675,0.001409224,0.0009297035,0.0004891288,0.0001680164],"category_scores_gemma":[0.0002002849,0.000341104,0.0002161658,0.004586259,0.000205836,0.000553432,0.002027953,0.001945171,0.00002354942],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000531126,"about_ca_system_score_gemma":0.0007345831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001085053,"about_ca_topic_score_gemma":0.0006469107,"domain_scores_codex":[0.9930847,0.002238916,0.000841359,0.00164373,0.001472993,0.000718308],"domain_scores_gemma":[0.9970889,0.0001729166,0.000178753,0.001013543,0.001361062,0.0001848225],"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":[0.0001618436,0.008570431,0.1313916,0.004936816,0.002968265,0.001093446,0.005263699,0.02237107,0.1538206,0.5954677,0.0224685,0.051486],"study_design_scores_gemma":[0.001071186,0.0005142845,0.1037315,0.0003592295,0.0001353133,0.00000661965,0.0001710645,0.8756918,0.003610977,0.0131948,0.0006945832,0.0008186952],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3064528,0.0007369595,0.6819114,0.004625083,0.0004616317,0.001890965,0.0001081366,0.0003099787,0.003503049],"genre_scores_gemma":[0.9910474,0.0006187207,0.006389726,0.0004369884,0.0001048911,0.0002786544,0.0003618402,0.00001122107,0.0007505741],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8533207,"threshold_uncertainty_score":0.9999041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1611713441652229,"score_gpt":0.4940134275501158,"score_spread":0.332842083384893,"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."}}