{"id":"W4385571975","doi":"10.18653/v1/2023.cawl-1.9","title":"Disambiguating Numeral Sequences to Decipher Ancient Accounting Corpora","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Numeral system; Computer science; DECIPHER; Scripting language; Natural language processing; Bootstrapping (finance); Artificial intelligence; Notation; Set (abstract data type); Task (project management); Selection (genetic algorithm); Devanagari; Arithmetic; Programming language; Mathematics","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":[0.002264586,0.0007604634,0.0007002131,0.004701765,0.001585396,0.002482227,0.001278976,0.0008426789,0.004202786],"category_scores_gemma":[0.02048106,0.0004004555,0.000384947,0.004790091,0.001385806,0.004314496,0.002087357,0.001807133,0.002408551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008730802,"about_ca_system_score_gemma":0.001080168,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001492892,"about_ca_topic_score_gemma":0.003065787,"domain_scores_codex":[0.9975489,0.0008103268,0.0003679426,0.000604876,0.000562423,0.0001055043],"domain_scores_gemma":[0.9887468,0.006781618,0.0006516363,0.002174724,0.00145699,0.0001882296],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000827417,0.0003327744,0.01554171,0.001841187,0.0001011566,0.002021807,0.00655458,0.02824703,0.04999514,0.08526592,0.03728198,0.7719892],"study_design_scores_gemma":[0.0001582833,0.0002300164,0.02067482,0.000578845,0.0001253268,0.002820902,0.006550146,0.3770996,0.1702724,0.1408426,0.2804376,0.0002094222],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4656965,0.003091459,0.4836292,0.001377184,0.0006915689,0.0006395903,0.008782297,0.01045134,0.02564099],"genre_scores_gemma":[0.5515441,0.0006190964,0.4282521,0.0002033615,0.0001975769,0.0002261142,0.01430287,0.000997717,0.003657012],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004701765,"threshold_uncertainty_score":0.01405972,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0499249752871117,"score_gpt":0.3279673079420105,"score_spread":0.2780423326548988,"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."}}