{"id":"W4407901240","doi":"10.1016/j.patcog.2025.111491","title":"Refining attention weights for facial super-resolution with counterfactual attention learning","year":2025,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Counterfactual thinking; Refining (metallurgy); Computer science; Artificial intelligence; Resolution (logic); Face (sociological concept); Pattern recognition (psychology); Computer vision; Psychology; Social psychology; Chemistry; Linguistics","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":[0.0002447099,0.0001877224,0.0001646794,0.0002554581,0.0004068064,0.0002497713,0.0002557416,0.00009649227,0.000007338318],"category_scores_gemma":[0.00007339535,0.0001805147,0.00006653933,0.0002835304,0.00004520817,0.001298359,0.00008639954,0.000209695,0.00003079711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001350774,"about_ca_system_score_gemma":0.00004639324,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002443942,"about_ca_topic_score_gemma":0.00002747565,"domain_scores_codex":[0.9985978,0.00007579348,0.0002794084,0.0005221296,0.0002220728,0.0003027733],"domain_scores_gemma":[0.9991601,0.00008633088,0.000177228,0.000194773,0.0003465386,0.00003510444],"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":[0.00006580517,0.00006907513,0.006120402,0.0001316624,0.00002720806,0.000002721609,0.000142323,0.00001353351,0.02149206,0.0001511015,0.0001477342,0.9716364],"study_design_scores_gemma":[0.007818533,0.002534638,0.06308766,0.005745677,0.0003303693,0.0001251829,0.0004496407,0.7749041,0.07127088,0.05413385,0.01688583,0.002713631],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08751755,0.00003942083,0.9105002,0.0003830809,0.0002384031,0.0002531362,0.000009618748,0.0006521225,0.0004064809],"genre_scores_gemma":[0.7702784,0.00001228709,0.2285365,0.0002167943,0.00008646445,0.000240968,0.000228265,0.00002000674,0.0003802892],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9689227,"threshold_uncertainty_score":0.7361174,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02181851038999945,"score_gpt":0.2773361031655743,"score_spread":0.2555175927755748,"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."}}