{"id":"W4226020023","doi":"10.1007/s10936-022-09863-x","title":"The Persian Lexicon Project: minimized orthographic neighbourhood effects in a dense language","year":2022,"lang":"en","type":"article","venue":"Journal of Psycholinguistic Research","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"Athabasca University; University of Alberta","funders":"","keywords":"Psycholinguistics; Lexicon; Persian; Natural language processing; Linguistics; Computer science; Neighbourhood (mathematics); Artificial intelligence; Psychology; Cognition; Philosophy; Mathematics; Neuroscience","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":[0.007981261,0.0001363001,0.0002544536,0.001207511,0.0006241747,0.0003875477,0.00264727,0.00005424751,0.0000149298],"category_scores_gemma":[0.004430294,0.00009353668,0.0001512168,0.002417995,0.0001375186,0.0001345721,0.0004991014,0.002144244,0.000002394649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001832379,"about_ca_system_score_gemma":0.000575777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001134111,"about_ca_topic_score_gemma":0.00003864133,"domain_scores_codex":[0.995547,0.001421786,0.00052892,0.000291839,0.001623097,0.0005873396],"domain_scores_gemma":[0.9970101,0.001473184,0.0003020778,0.0005917571,0.0005102666,0.0001126818],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.004458786,0.003052847,0.0124501,0.0007002824,0.0004532989,0.0350834,0.111271,0.00009149958,0.02068781,0.3504619,0.0562735,0.4050156],"study_design_scores_gemma":[0.0247674,0.01364266,0.01810868,0.002448443,0.0001294891,0.0125552,0.02556391,0.02936141,0.007494398,0.7940958,0.06901307,0.002819603],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6913227,0.1428869,0.1047283,0.02312809,0.01263841,0.005340419,0.00001609545,0.0006378991,0.01930117],"genre_scores_gemma":[0.9462571,0.0000860403,0.05289178,0.0001268348,0.0003777958,0.00005085632,4.337396e-7,0.00001801204,0.0001911061],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4436338,"threshold_uncertainty_score":0.9315792,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03649627384294762,"score_gpt":0.4075648834884071,"score_spread":0.3710686096454595,"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."}}