{"id":"W4289914272","doi":"10.3765/amp.v9i0.5168","title":"Comparative Reconstruction Probabilistically: The Role of Inventory and Phonotactics","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Annual Meetings on Phonology","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Phonotactics; Spurious relationship; Phonology; Computer science; Scope (computer science); Merge (version control); Natural language processing; Artificial intelligence; Linguistics; Econometrics; Machine learning; Mathematics; Information retrieval; 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":[0.000579361,0.000115269,0.0002223905,0.00008927287,0.0002578744,0.00002744173,0.001190821,0.00005631003,0.000005398384],"category_scores_gemma":[0.0004318683,0.00007346732,0.00004295458,0.0004128914,0.0004216391,0.0002203175,0.001108387,0.0004496412,5.459165e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005047515,"about_ca_system_score_gemma":0.00005414032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003974543,"about_ca_topic_score_gemma":0.000001397516,"domain_scores_codex":[0.9989831,0.00004570167,0.000272753,0.0002686284,0.0002594374,0.0001703649],"domain_scores_gemma":[0.9987007,0.0001466212,0.0005274895,0.0001613264,0.0004388762,0.00002496448],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001945081,0.00020901,0.006215789,0.0001011855,0.00006758168,3.882443e-7,0.02246339,0.00001083192,0.1229365,0.8154534,0.001276286,0.03107119],"study_design_scores_gemma":[0.0002547884,0.0007525739,0.0007262181,0.00007151008,0.00003033853,0.0001607361,0.007497889,0.001787832,0.5148376,0.4694295,0.004244643,0.0002064032],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9916766,0.0008107218,0.00008969991,0.002627166,0.0002583097,0.0004414443,0.00001103561,0.0001412617,0.003943782],"genre_scores_gemma":[0.980597,0.000007907876,0.01908213,0.0002082822,0.00002021424,0.00004408035,1.870568e-7,0.000005400543,0.00003477528],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3919011,"threshold_uncertainty_score":0.2995911,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009442116124865847,"score_gpt":0.2370501893360765,"score_spread":0.2276080732112107,"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."}}