{"id":"W4394571487","doi":"10.21203/rs.3.rs-4190039/v1","title":"Artificial Intelligence and the Spatial Documentation of Languages","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Documentation; Computer science; Field (mathematics); Process (computing); Artificial intelligence; Natural language processing; Multidisciplinary approach; Data science; Linguistics; World Wide Web; Programming language; Sociology","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":[0.003061354,0.0002838014,0.0002166535,0.003581123,0.00104284,0.006391442,0.0008114568,0.0005662741,0.006448334],"category_scores_gemma":[0.01797573,0.0002629328,0.0004142435,0.004798504,0.004065837,0.007211103,0.002057773,0.0008573887,0.001029562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001639295,"about_ca_system_score_gemma":0.001851813,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007898095,"about_ca_topic_score_gemma":0.006688209,"domain_scores_codex":[0.9977691,0.001503941,0.0001400995,0.0002006879,0.0003323274,0.00005377347],"domain_scores_gemma":[0.9887676,0.007805069,0.0009877207,0.001421144,0.0008949144,0.0001236629],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005198499,0.00003041647,0.005326642,0.0003285751,0.00003058985,0.0002975791,0.01797336,0.009365645,0.001325428,0.6866065,0.009384054,0.2692791],"study_design_scores_gemma":[0.00002637354,0.00002828081,0.007403078,0.0004634113,0.00003117491,0.0008039935,0.01358325,0.04978109,0.00427362,0.6923883,0.2311494,0.00006799474],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1583841,0.004564964,0.6454817,0.01715817,0.0003607503,0.000142092,0.001300971,0.003449075,0.1691582],"genre_scores_gemma":[0.7675316,0.001902771,0.2171034,0.0002731361,0.0001045005,0.00007040236,0.0008329612,0.0004393732,0.01174184],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007898095,"threshold_uncertainty_score":0.02157182,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05595285475847724,"score_gpt":0.4363178377246973,"score_spread":0.3803649829662201,"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."}}