{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004979735,0.0005070908,0.0004878298,0.0004439644,0.0007889882,0.001554125,0.001216192,0.0003839741,0.00000238844],"category_scores_gemma":[0.0004091103,0.0005289197,0.0004897003,0.0002546524,0.00009777232,0.001362059,0.00150782,0.006799043,0.00001188494],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004463211,"about_ca_system_score_gemma":0.003784115,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001588976,"about_ca_topic_score_gemma":0.00008582715,"domain_scores_codex":[0.9945763,0.0002944162,0.0009275235,0.001051086,0.000662073,0.002488646],"domain_scores_gemma":[0.9977815,0.00008175545,0.0009511993,0.0004599605,0.0006297557,0.00009586241],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001886829,0.0001858238,0.0002950803,0.001394581,0.0004572594,0.00001589093,0.0007532656,0.00184219,0.5320292,0.06338765,0.00007651483,0.3993739],"study_design_scores_gemma":[0.0003897909,0.0002317352,0.00004432917,0.0004129712,0.0001115336,0.0002892213,0.0002947092,0.4731507,0.0009319041,0.5233742,0.0001634623,0.0006054544],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06515288,0.003089042,0.9288689,0.0003753202,0.001233481,0.0005072135,0.0000127378,0.0007305389,0.00002984283],"genre_scores_gemma":[0.6256782,0.0006012111,0.371872,0.00003173898,0.001013409,0.00006350164,0.00005200938,0.0001098839,0.0005779457],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5605254,"threshold_uncertainty_score":0.9997162,"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."}}