{"id":"W2089679262","doi":"10.1073/pnas.1204678110","title":"Automated reconstruction of ancient languages using probabilistic models of sound change","year":2013,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":134,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Sound change; Computer science; Probabilistic logic; Austronesian languages; Comparative method; Set (abstract data type); Process (computing); Inference; Function (biology); Artificial intelligence; Natural language processing; Linguistics; Programming language","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":[0.002301541,0.0009329297,0.0008740808,0.002423783,0.001052015,0.001981238,0.001458723,0.001095927,0.002195402],"category_scores_gemma":[0.009662799,0.001116574,0.001568296,0.001389789,0.001214896,0.002709598,0.001833013,0.001547151,0.0008097856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001204726,"about_ca_system_score_gemma":0.001232397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008975032,"about_ca_topic_score_gemma":0.01184447,"domain_scores_codex":[0.9986663,0.0004759918,0.00007202286,0.0004555133,0.000225952,0.0001041978],"domain_scores_gemma":[0.9955637,0.002802499,0.0003470331,0.0007571363,0.000425266,0.000104406],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006767451,0.0001387998,0.03045105,0.0002345332,0.0003174414,0.0009936845,0.003088018,0.4866305,0.04507458,0.02050344,0.004454528,0.4074366],"study_design_scores_gemma":[0.0000228313,0.00002740414,0.002310867,0.00001209681,0.00002604248,0.0001476544,0.0002264322,0.9774648,0.004571918,0.01351141,0.00164712,0.00003144364],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2633956,0.0002764619,0.7258697,0.0003430564,0.00004312442,0.00006872519,0.0005279821,0.006904582,0.002570834],"genre_scores_gemma":[0.7195113,0.0001314202,0.2765347,0.00008819401,0.00003050169,0.00006355395,0.001287904,0.0006767838,0.001675679],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008975032,"threshold_uncertainty_score":0.01784557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07284500180176527,"score_gpt":0.3273278073997781,"score_spread":0.2544828055980128,"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."}}