{"id":"W4393888730","doi":"10.5281/zenodo.7141089","title":"Luganda Monolingual Corpus","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Multilingual Education and Policy","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Natural language processing; Linguistics; Computer science; Artificial intelligence; Philosophy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.001340043,0.002609999,0.001312449,0.003826559,0.002058679,0.002139944,0.002653617,0.002095973,0.04132957],"category_scores_gemma":[0.003856829,0.0006236522,0.001014639,0.004390447,0.0007889704,0.0017538,0.002685367,0.002007059,0.07157377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002071257,"about_ca_system_score_gemma":0.002908604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03806198,"about_ca_topic_score_gemma":0.08501147,"domain_scores_codex":[0.9984377,0.0005065858,0.000153474,0.0004168496,0.000276272,0.0002092014],"domain_scores_gemma":[0.9985361,0.0003800819,0.00008865101,0.0003937352,0.0004702931,0.0001310568],"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":[0.000133231,0.00006262225,0.0005513263,0.0006968486,0.00003054661,0.00009988243,0.00008850561,0.0002804696,0.0004218891,0.0007056912,0.9893348,0.007594257],"study_design_scores_gemma":[0.0001506779,0.00003155094,0.004316989,0.0003184924,0.00002827161,0.0001597777,0.0003298175,0.0009157426,0.0007335299,0.0007905925,0.9921835,0.00004089783],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.002217593,0.0007437515,0.0003237669,0.0002955785,0.0002215374,0.00008475861,0.9889942,0.001098524,0.006020333],"genre_scores_gemma":[0.001643531,0.0001089895,0.0006261949,0.00006108017,0.0000195465,0.0001836298,0.9951291,0.00009658863,0.002131291],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.04132957,"threshold_uncertainty_score":0.1382611,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09052245231026375,"score_gpt":0.392930996975547,"score_spread":0.3024085446652832,"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."}}