{"id":"W4382395083","doi":"10.18280/ts.400323","title":"Enhancing the Resolution of Historical Ottoman Texts Using Deep Learning-Based Super-Resolution Techniques","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Image Processing Techniques and Applications","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Resolution (logic); Artificial intelligence; Deep learning; Superresolution; Computer science; History; Natural language processing","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005865445,0.0007298148,0.000435896,0.001388982,0.0002125728,0.0007567548,0.0006352881,0.0005244461,0.00136861],"category_scores_gemma":[0.001884093,0.0001973594,0.0005414805,0.0007918797,0.0004218002,0.001341531,0.0006321041,0.0009104681,0.0006268373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000543088,"about_ca_system_score_gemma":0.0005923175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005298812,"about_ca_topic_score_gemma":0.01225382,"domain_scores_codex":[0.9997308,0.00003677116,0.00001777191,0.00004866576,0.0001268004,0.00003923568],"domain_scores_gemma":[0.999453,0.0001781323,0.00008297892,0.00007269697,0.0001820176,0.00003118924],"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":[0.0004374554,0.0001160873,0.002205497,0.0004465399,0.0001558821,0.0005476879,0.0003445235,0.1329396,0.1849225,0.004474701,0.005005323,0.6684042],"study_design_scores_gemma":[0.00001316339,0.000090641,0.002454221,0.00003941629,0.0000705394,0.0003059239,0.0001157972,0.9232911,0.06668085,0.002662718,0.004247311,0.00002831138],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1600385,0.002030644,0.8283775,0.0005278222,0.000125343,0.00008570416,0.0004244223,0.002481619,0.00590842],"genre_scores_gemma":[0.5621691,0.001566356,0.4285323,0.0003558185,0.00007605724,0.00004452266,0.0008689304,0.0002246072,0.006162365],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005298812,"threshold_uncertainty_score":0.01053596,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01906853586702206,"score_gpt":0.2498590704254829,"score_spread":0.2307905345584608,"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."}}