{"id":"W4406948310","doi":"10.1109/tai.2025.3535456","title":"SAMScore: A Content Structural Similarity Metric for Image Translation Evaluation","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institutes of Health; National Cancer Institute; Foundation for the National Institutes of Health","keywords":"Translation (biology); Similarity (geometry); Structural similarity; Metric (unit); Content (measure theory); Artificial intelligence; Computer science; Image (mathematics); Mathematics; Pattern recognition (psychology); Natural language processing; Biology; Mathematical analysis; Engineering; Biochemistry","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":[0.0006836453,0.0001946179,0.0001885786,0.0005027091,0.000368847,0.000265651,0.0006123491,0.0001266815,0.0000332889],"category_scores_gemma":[0.00009831275,0.0001834608,0.0001604527,0.001332989,0.00008281947,0.0006607131,0.000003031058,0.0002734976,0.00001121304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001892214,"about_ca_system_score_gemma":0.0001515488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007276671,"about_ca_topic_score_gemma":0.0001367137,"domain_scores_codex":[0.9982719,0.0001076255,0.0004543899,0.0005067997,0.0003917483,0.0002674785],"domain_scores_gemma":[0.9985228,0.0003681465,0.0001004752,0.0004226198,0.000531641,0.00005430613],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006637751,0.00007093464,6.302882e-7,0.0000283959,0.00002127433,9.074807e-7,0.0002474912,0.001748808,0.01649003,0.02226722,0.00002720536,0.9590307],"study_design_scores_gemma":[0.00004342173,0.00006799217,0.000005089618,0.00002925384,0.00003256478,0.0000016377,0.00003168132,0.3867542,0.4851685,0.1277232,0.00002481341,0.000117669],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001200619,0.0004038968,0.9942561,0.001524705,0.00103481,0.001038587,0.00002101926,0.0004246582,0.00009560648],"genre_scores_gemma":[0.7034355,0.000009526989,0.2960847,0.0002376228,0.00002172082,0.0001613954,0.00000341314,0.000007158473,0.00003899302],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.958913,"threshold_uncertainty_score":0.7481315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1261758897786528,"score_gpt":0.3829559761525539,"score_spread":0.2567800863739011,"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."}}