{"id":"W4393815784","doi":"10.5281/zenodo.7141165","title":"Kiswahili Monolingual Corpus","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Global Maritime and Colonial Histories","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":"codex-gemma-dda1882f352a","candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009470343,0.0001827333,0.0002196389,0.0002230302,0.00968022,0.000852578,0.002151962,0.0001787828,0.355036],"category_scores_gemma":[0.001303085,0.0002292154,0.00008969461,0.0006962356,0.0004810079,0.0001640408,0.001890425,0.0006247455,0.008049078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007607664,"about_ca_system_score_gemma":0.0000357284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00308585,"about_ca_topic_score_gemma":0.00006201427,"domain_scores_codex":[0.9970437,0.0008449829,0.0002487702,0.0004756174,0.0008652844,0.0005216722],"domain_scores_gemma":[0.9986034,0.00003854324,0.0001694457,0.000504312,0.0004451776,0.000239089],"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":[0.00003836293,0.00009993536,9.579588e-8,0.00002997968,0.00002691941,0.00004645871,0.001778561,0.00000295741,0.000004333896,0.002298709,0.9798084,0.01586532],"study_design_scores_gemma":[0.0001619689,0.0001801401,0.000005084117,0.00001120803,0.00003160638,0.00001935642,0.0008095684,6.987413e-7,0.000001234229,0.00028159,0.9982561,0.0002413854],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00007024522,0.0002979077,0.000005649828,0.0005872669,0.0007900273,0.0004155186,0.8823811,0.0005687123,0.1148835],"genre_scores_gemma":[0.000394827,0.0007505273,0.00001164273,0.0002554869,0.0005747285,9.165367e-8,0.9934261,0.0006023687,0.003984159],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.3469869,"threshold_uncertainty_score":0.9927233,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03182316603825341,"score_gpt":0.2781406451941617,"score_spread":0.2463174791559082,"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."}}