{"id":"W4413062930","doi":"10.1145/3715335.3737684","title":"Community-Driven Data Practices for Advancing Ethical and Equitable AI in Low-Resource Language Contexts","year":2025,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Resource (disambiguation); Knowledge management; Data science","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":[0.1155424,0.001054154,0.00124771,0.008233692,0.007588975,0.01726521,0.008215643,0.00537224,0.01226009],"category_scores_gemma":[0.2812867,0.001330983,0.001476108,0.007065956,0.01202217,0.03018502,0.02402714,0.01115982,0.005333862],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005647772,"about_ca_system_score_gemma":0.02162806,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007207941,"about_ca_topic_score_gemma":0.01199773,"domain_scores_codex":[0.8663457,0.1065503,0.003867737,0.007857916,0.01358548,0.001792814],"domain_scores_gemma":[0.5992862,0.2433948,0.008322192,0.09265044,0.04475969,0.01158678],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001765211,0.0006276876,0.006993663,0.0006969779,0.0001705379,0.0002581859,0.03404616,0.00880065,0.003201162,0.730803,0.03321914,0.1810063],"study_design_scores_gemma":[0.00005455438,0.0000497367,0.0006577569,0.0003796874,0.00003221608,0.0001537439,0.008356716,0.03160004,0.002433928,0.8363926,0.119816,0.00007300837],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006613187,0.000382959,0.9510857,0.01963408,0.000258079,0.0006726115,0.0004250348,0.001596797,0.01933164],"genre_scores_gemma":[0.1807298,0.0004647369,0.8049099,0.002829362,0.0003364492,0.002130697,0.001597749,0.001251893,0.005749516],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1155424,"threshold_uncertainty_score":0.6110539,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05674212384201326,"score_gpt":0.3930905079977772,"score_spread":0.336348384155764,"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."}}