{"id":"W2909676388","doi":"10.1017/s0952675720000056","title":"An algorithm for learning phonological classes from distributional similarity","year":2020,"lang":"en","type":"article","venue":"Phonology","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Phonology; Phonological rule; Computer science; Similarity (geometry); Set (abstract data type); Natural (archaeology); Artificial intelligence; Natural language processing; Natural language; Speech recognition; Linguistics; Image (mathematics)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002143899,0.0002303698,0.0004144166,0.00005927354,0.000255015,0.00003767854,0.00058183,0.0005592642,0.004942115],"category_scores_gemma":[0.000296961,0.0002251927,0.0001264906,0.0001961592,0.0003906362,0.00006981676,0.0001493132,0.0009025545,0.0007529173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004344703,"about_ca_system_score_gemma":0.00009039428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002651993,"about_ca_topic_score_gemma":0.00002718048,"domain_scores_codex":[0.997574,0.0004032613,0.0003250556,0.000827865,0.0001280498,0.0007417751],"domain_scores_gemma":[0.9984305,0.0007024001,0.00009993661,0.0003252996,0.0001306279,0.0003112196],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.003511133,0.003037896,0.08371666,0.00003468934,0.001705051,0.0004031964,0.01424775,0.0001592886,0.1158911,0.0235413,0.07308368,0.6806683],"study_design_scores_gemma":[0.007504552,0.006886713,0.5906603,0.000007628691,0.0001395247,0.00007855138,0.001948724,0.05727357,0.009599855,0.05087424,0.2737591,0.001267314],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8198864,0.0007897431,0.1653074,0.0093335,0.001211951,0.0005120213,0.001343334,0.0004201664,0.001195451],"genre_scores_gemma":[0.9898066,0.00003829897,0.006097828,0.001593143,0.0008379498,0.0001893861,0.001275011,0.00003167035,0.0001300906],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.679401,"threshold_uncertainty_score":0.9959675,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08843556346368177,"score_gpt":0.3850009426556763,"score_spread":0.2965653791919945,"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."}}