{"id":"W3208275223","doi":"10.48550/arxiv.2111.00361","title":"Functional Neural Networks for Parametric Image Restoration Problems","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Image restoration; Computer science; Parametric statistics; Artificial intelligence; Artificial neural network; Image (mathematics); JPEG; Image quality; Noise reduction; Machine learning; Algorithm; Mathematics; Image processing; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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"],"consensus_categories":[],"category_scores_codex":[0.0002544412,0.0002966773,0.0002838095,0.0003313229,0.0002359596,0.0004487075,0.001149695,0.0002735242,0.000007553957],"category_scores_gemma":[0.0001502976,0.0003637062,0.0001996631,0.001160688,0.0001018721,0.001380305,0.001376974,0.0005844048,0.000003677377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000266998,"about_ca_system_score_gemma":0.0002069759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001926085,"about_ca_topic_score_gemma":0.00001036503,"domain_scores_codex":[0.9979964,0.00009747757,0.0002275935,0.001221481,0.0001051644,0.0003518926],"domain_scores_gemma":[0.99779,0.0001662821,0.0003562512,0.0009758106,0.0006064338,0.0001052005],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003328242,0.0001167979,0.0003379114,0.0001798601,0.00004622794,0.00009266009,0.00005960193,0.9734437,0.0002294071,0.02046815,0.001461164,0.003531172],"study_design_scores_gemma":[0.0002378955,0.00005029529,0.0002423817,0.00006350591,0.00003153906,0.000006820586,0.00001187826,0.9523944,0.000154885,0.04629894,0.0001512849,0.0003561284],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004318635,0.0002444192,0.9932353,0.0001407858,0.0006615698,0.0005089858,0.000005191266,0.0007349331,0.0001501715],"genre_scores_gemma":[0.7371638,0.00007156717,0.2620121,0.00009634111,0.0001148662,0.00001192256,0.00008191204,0.00002280514,0.0004246434],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7328452,"threshold_uncertainty_score":0.9998815,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08400814661701858,"score_gpt":0.2127871315397213,"score_spread":0.1287789849227027,"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."}}