{"id":"W4402861989","doi":"10.2139/ssrn.4967694","title":"Improving Attention Quality for Facial Image Super-Resolution Using Counterfactual Attention Learning","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Counterfactual thinking; Artificial intelligence; Quality (philosophy); Image quality; Image (mathematics); Computer science; Computer vision; Resolution (logic); Psychology; Cognitive psychology; Social psychology; Epistemology; Philosophy","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":[0.002116419,0.0007603184,0.0008819338,0.0007030885,0.0002810959,0.0008256716,0.0009152055,0.001051487,0.003453914],"category_scores_gemma":[0.008483366,0.0003928523,0.0005584113,0.0005494645,0.0004969967,0.00132727,0.001782232,0.001470468,0.000596216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004460121,"about_ca_system_score_gemma":0.0005557789,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001940982,"about_ca_topic_score_gemma":0.002442117,"domain_scores_codex":[0.9992772,0.0002038272,0.00003336896,0.0001637735,0.000229159,0.00009269562],"domain_scores_gemma":[0.9973882,0.00140043,0.000188463,0.0004044691,0.0005118852,0.0001066168],"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":[0.001238509,0.0002660787,0.002086758,0.0003422032,0.0002031987,0.0001876527,0.0001786098,0.05618201,0.2088505,0.006811013,0.003367753,0.7202858],"study_design_scores_gemma":[0.00003846257,0.0001899114,0.002720456,0.00002348573,0.00009913939,0.0002687542,0.00002546652,0.9407112,0.04829926,0.006251957,0.001346479,0.0000254339],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04933605,0.0009392743,0.9466125,0.0002982489,0.0001356102,0.00006233902,0.00008106772,0.0007939262,0.001741017],"genre_scores_gemma":[0.6376004,0.001078303,0.3569993,0.0004372517,0.0002235153,0.00007807476,0.0002874269,0.0002398573,0.003055985],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003453914,"threshold_uncertainty_score":0.01155448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0257493267158465,"score_gpt":0.3367197708677994,"score_spread":0.3109704441519529,"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."}}