{"id":"W3146905089","doi":"10.23977/jaip.2020.040101","title":"The Recognition of Tibetan Handwritten Numbers Based on Federated Learning","year":2021,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Practice","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Numeral system; Computer science; Identification (biology); Process (computing); Artificial intelligence; Pattern recognition (psychology); Speech recognition","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":[0.0003906039,0.0003791289,0.0004205476,0.0007902578,0.000239355,0.0005672949,0.0005899228,0.0003029078,0.001317054],"category_scores_gemma":[0.0008369026,0.00009720268,0.0002902793,0.0006723019,0.0002364941,0.0007954846,0.0004139389,0.0002823995,0.0005684556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004373813,"about_ca_system_score_gemma":0.0004732623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003179827,"about_ca_topic_score_gemma":0.003963627,"domain_scores_codex":[0.9997388,0.00003008139,0.0000221342,0.00008856914,0.00008022744,0.00004019837],"domain_scores_gemma":[0.9997248,0.00004244205,0.00004111177,0.00006603278,0.0001086537,0.00001685922],"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":[0.0003489035,0.0001542836,0.006737511,0.0001053314,0.00005902601,0.0002759314,0.00009426384,0.02536235,0.04618254,0.00198009,0.002945942,0.9157538],"study_design_scores_gemma":[0.00002857076,0.0002908697,0.0128643,0.00004901513,0.00007298024,0.0007229442,0.000127884,0.8658624,0.1071308,0.004594842,0.00820631,0.00004907261],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3021484,0.0008218852,0.6786416,0.0002129085,0.0002406241,0.0001522863,0.0004710068,0.006979146,0.01033215],"genre_scores_gemma":[0.8425354,0.0003273638,0.1492092,0.0001409563,0.00003666533,0.00006288838,0.0007878831,0.00003997231,0.006859599],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003179827,"threshold_uncertainty_score":0.006322622,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04480459474651922,"score_gpt":0.3226153127098592,"score_spread":0.2778107179633399,"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."}}