{"id":"W2403989326","doi":"","title":"OCR-Based Image Features for Biomedical Image and Article Classification: Identifying Documents Relevant to Genomic Cis-Regulatory Elements.","year":2012,"lang":"en","type":"article","venue":"National Conference on Artificial Intelligence","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Image (mathematics); Artificial intelligence; Contextual image classification; Information retrieval; Computational biology; Pattern recognition (psychology); Biology","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":[0.0009349692,0.000167096,0.0001347542,0.000149903,0.0001893208,0.0001530895,0.0002749416,0.0001460179,0.0001228957],"category_scores_gemma":[0.0009022622,0.0001540776,0.00006376277,0.0001342196,0.0003130986,0.00002499775,0.0001096771,0.0001279198,0.0001628559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006685556,"about_ca_system_score_gemma":0.0002337759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006146165,"about_ca_topic_score_gemma":0.00001497591,"domain_scores_codex":[0.9980243,0.00005175511,0.0004704668,0.0003338742,0.0006714135,0.0004481361],"domain_scores_gemma":[0.9987211,0.00007627428,0.0001050338,0.0002087517,0.0005239067,0.0003649367],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000236622,0.0002199413,0.00013324,0.00004454392,0.00002605667,3.920926e-7,0.0001167282,0.000004588084,0.9413034,0.0115492,0.00256679,0.04379854],"study_design_scores_gemma":[0.0002641743,0.0006949129,0.01151369,0.00005246837,0.00001969941,0.000004418207,0.0007028315,0.007753496,0.9596258,0.008219591,0.01072188,0.0004270145],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5910616,0.0002269312,0.3964488,0.00710783,0.0007728186,0.0015465,0.0003185181,0.00004412341,0.00247295],"genre_scores_gemma":[0.9784865,0.00005126798,0.01975599,0.0007923053,0.0003703076,0.00008839621,0.0002185827,0.00001467157,0.0002220103],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3874249,"threshold_uncertainty_score":0.6283104,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0875309987850259,"score_gpt":0.3880385414947419,"score_spread":0.300507542709716,"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."}}