{"id":"W4402487814","doi":"10.3384/nejlt.2000-1533.2024.5217","title":"Documenting Geographically and Contextually Diverse Language Data Sources","year":2024,"lang":"en","type":"article","venue":"Northern European Journal of Language Technology","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Sorbonne Université; Università Bocconi; Centre National de la Recherche Scientifique; Grand Équipement National De Calcul Intensif; Simon Fraser University","keywords":"Spatial contextual awareness; Context (archaeology); Geography; Remote sensing","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.02702418,0.0009206197,0.001196209,0.02289252,0.003833008,0.00893464,0.002344528,0.001177088,0.003138102],"category_scores_gemma":[0.06588727,0.001117426,0.0009540666,0.02172525,0.001991492,0.01088061,0.009095831,0.002061008,0.00169978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002967599,"about_ca_system_score_gemma":0.009662352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01358122,"about_ca_topic_score_gemma":0.02901388,"domain_scores_codex":[0.9779856,0.009104858,0.004027218,0.003510428,0.004753424,0.0006184838],"domain_scores_gemma":[0.9177834,0.04165714,0.007555739,0.01622535,0.01535172,0.001426689],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003087536,0.0005958061,0.1140604,0.003267378,0.0003059109,0.002311643,0.09119362,0.007184144,0.02498427,0.09389028,0.03076654,0.6311313],"study_design_scores_gemma":[0.0001706073,0.0002773193,0.08240096,0.00225813,0.000379736,0.003076494,0.09938381,0.04874478,0.04705425,0.1224927,0.5932208,0.000540409],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1472145,0.00108643,0.7788972,0.003677502,0.0001625041,0.003295137,0.0376208,0.005815311,0.02223063],"genre_scores_gemma":[0.19747,0.0005837946,0.7592434,0.0004440527,0.00007318078,0.002563938,0.03466426,0.001260773,0.003696623],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02702418,"threshold_uncertainty_score":0.1429192,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01162351447033166,"score_gpt":0.2669204921008031,"score_spread":0.2552969776304714,"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."}}