{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008150429,0.0004019451,0.0006088263,0.0005788896,0.0005691829,0.001182086,0.0009911266,0.0004441864,0.006038113],"category_scores_gemma":[0.002624962,0.0002731307,0.0004087706,0.0007275035,0.0006501256,0.001794524,0.002052763,0.0004619203,0.001173578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000228379,"about_ca_system_score_gemma":0.001195252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005461851,"about_ca_topic_score_gemma":0.01426081,"domain_scores_codex":[0.9996359,0.0001535191,0.00001670261,0.0001070313,0.00005756575,0.00002923415],"domain_scores_gemma":[0.9993165,0.0002871291,0.00003307637,0.0002040597,0.000107935,0.00005131501],"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":[0.002631479,0.0005405372,0.00999361,0.0006028783,0.000352377,0.000869227,0.001712237,0.05161255,0.1040927,0.129905,0.02737162,0.6703157],"study_design_scores_gemma":[0.001483886,0.0009028728,0.01279691,0.0000734198,0.000586483,0.0008626766,0.002449376,0.619871,0.07465002,0.2526675,0.03348739,0.0001685298],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6373252,0.0004051974,0.3381185,0.0005022935,0.00008582398,0.0001239829,0.002899264,0.007137373,0.01340235],"genre_scores_gemma":[0.7953601,0.0001413554,0.1942493,0.0001307654,0.00004282824,0.0001530982,0.003000281,0.001498357,0.005423814],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006038113,"threshold_uncertainty_score":0.02019948,"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."}}