{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001024462,0.00008893698,0.0001838188,0.000261639,0.00009256199,0.00003194594,0.001263058,0.00007749991,0.000003684869],"category_scores_gemma":[0.0003573872,0.00005924029,0.00005685324,0.001151192,0.0007294769,0.001756507,0.0002896814,0.0001003139,1.828588e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004135629,"about_ca_system_score_gemma":0.00004355766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006251216,"about_ca_topic_score_gemma":8.102778e-8,"domain_scores_codex":[0.9983029,0.00000984077,0.0004011604,0.0002278134,0.0009073447,0.0001509659],"domain_scores_gemma":[0.9982432,0.00007050705,0.0008612185,0.00001937262,0.0007818587,0.00002386618],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000003207403,0.00005479567,0.001202044,0.0003387069,0.000010897,4.887645e-9,0.0009250815,0.0003163989,0.7882277,0.2050808,0.00008962077,0.003750685],"study_design_scores_gemma":[0.00005691205,0.00003397941,0.002967009,0.0002516553,0.000005944241,0.00001645114,0.0001029165,0.2918299,0.3731503,0.331517,5.31408e-7,0.00006748431],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9970112,0.0007822994,0.0006584867,0.0005057555,0.00002627185,0.0003884442,0.000006870092,0.0001028144,0.0005177993],"genre_scores_gemma":[0.8112614,0.000004780584,0.1886413,0.00005728348,0.00001739485,0.00001053637,3.76208e-8,0.000002289039,0.000004964816],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4150774,"threshold_uncertainty_score":0.2687788,"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."}}