{"id":"W7033740617","doi":"","title":"A quarter century of Swahili corpus building (1999-2024)","year":2024,"lang":"en","type":"article","venue":"Ghent University Academic Bibliography (Ghent University)","topic":"Bat Biology and Ecology Studies","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Swahili; Sketch; The Internet; Corpus linguistics; Annotation; Quarter (Canadian coin)","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":[0.006000292,0.0007809087,0.0006321209,0.01312249,0.003305572,0.005321228,0.001641954,0.001478481,0.05172108],"category_scores_gemma":[0.01674906,0.0009529169,0.0003751209,0.01704561,0.001862228,0.006572793,0.004042408,0.002122578,0.03676525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01116069,"about_ca_system_score_gemma":0.01296108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.08803681,"about_ca_topic_score_gemma":0.1194914,"domain_scores_codex":[0.9974681,0.0004682858,0.0004403701,0.0005388888,0.0008466793,0.0002378327],"domain_scores_gemma":[0.9900004,0.001571079,0.0005241188,0.001465236,0.005944978,0.000494211],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0001515574,0.00001969758,0.0009763676,0.0008466171,0.0000147116,0.0002284482,0.004071003,0.0001525014,0.0009459418,0.03268557,0.8134618,0.1464459],"study_design_scores_gemma":[0.000006274817,0.000003597302,0.002597919,0.0002978017,0.000002882252,0.00004064064,0.0006280496,0.00003953892,0.0005661896,0.0009489142,0.9948602,0.000007977775],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.03249029,0.02970877,0.0102933,0.04631637,0.01733498,0.001123958,0.376663,0.00309643,0.4829728],"genre_scores_gemma":[0.100041,0.01735527,0.02858228,0.009079861,0.002664839,0.003633039,0.3922206,0.005192292,0.4412308],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.08803681,"threshold_uncertainty_score":0.1750488,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0146850158930914,"score_gpt":0.1966544076806722,"score_spread":0.1819693917875808,"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."}}