{"id":"W4398999541","doi":"10.7910/dvn/rqtsd2","title":"GLOCR: GeezLab OCR Dataset","year":2021,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Image Processing and 3D Reconstruction","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Information retrieval; Artificial intelligence; Natural language processing","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":[0.001143111,0.00776162,0.002964285,0.006900919,0.002109949,0.00273116,0.006880965,0.004250093,0.03286679],"category_scores_gemma":[0.003736198,0.0009553255,0.002349914,0.006113132,0.000981021,0.00197021,0.003149461,0.00289645,0.09786719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00236381,"about_ca_system_score_gemma":0.00266006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04249488,"about_ca_topic_score_gemma":0.08544092,"domain_scores_codex":[0.9973431,0.0003144806,0.0002315003,0.0007549243,0.001004332,0.0003517363],"domain_scores_gemma":[0.9983054,0.0002234327,0.0001298384,0.000554846,0.0006474112,0.0001390378],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001649064,0.0001661182,0.0008178611,0.0009738173,0.00008642756,0.0001317242,0.00003059957,0.00106425,0.001155502,0.0003470009,0.9762177,0.01884398],"study_design_scores_gemma":[0.0006370914,0.0001824185,0.01290686,0.0006505621,0.000165396,0.001092653,0.0002942854,0.01209549,0.007335456,0.002412945,0.9620172,0.0002097016],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.002513925,0.001265223,0.0009421296,0.0001897486,0.0001870714,0.0002012292,0.9839168,0.007121306,0.003662514],"genre_scores_gemma":[0.001147749,0.0001157558,0.001299933,0.00005734101,0.00001548505,0.0001324075,0.995946,0.0001479209,0.001137442],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.04249488,"threshold_uncertainty_score":0.1099503,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01266044463865132,"score_gpt":0.2398873355641047,"score_spread":0.2272268909254534,"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."}}