{"id":"W2805269870","doi":"10.3758/s13428-018-1058-z","title":"Procura-PALavras (P-PAL): A Web-based interface for a new European Portuguese lexical database","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Reading and Literacy Development","field":"Psychology","cited_by":42,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Lexical database; Word lists by frequency; Bigram; Unicode; Natural language processing; Pronunciation; Vowel; Syllable; Word (group theory); Speech recognition; Artificial intelligence; Sentence; Linguistics; Trigram; WordNet","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.01337402,0.0003037862,0.0003660903,0.0005430723,0.0003173948,0.0001544456,0.0008992417,0.000140742,0.002735035],"category_scores_gemma":[0.001700564,0.0002625281,0.0001582712,0.0007220465,0.000478485,0.0001444872,0.0002940997,0.0007800123,0.001136224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001411296,"about_ca_system_score_gemma":0.0005840928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000289574,"about_ca_topic_score_gemma":0.00002786758,"domain_scores_codex":[0.9923359,0.004135647,0.0006188534,0.001028511,0.0006461823,0.001234946],"domain_scores_gemma":[0.9961202,0.001257663,0.0001113919,0.001237102,0.0005682195,0.0007053972],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001008195,0.0008825143,0.003615782,0.00005974307,0.00005663519,0.0001992247,0.003896571,1.808454e-7,0.03963078,0.0009749843,0.1579206,0.7917548],"study_design_scores_gemma":[0.003442392,0.001579868,0.03445644,0.0002119227,0.00005644229,0.00006822572,0.0006034242,0.0002151616,0.02460466,0.0002036422,0.9339912,0.0005666532],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4088382,0.001326333,0.5278837,0.002516603,0.003209912,0.006004984,0.0002652041,0.0007532117,0.04920186],"genre_scores_gemma":[0.1756507,0.0000109238,0.747924,0.0003069543,0.001374556,0.001437177,0.0001691814,0.0002064809,0.07292002],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7911882,"threshold_uncertainty_score":0.9999827,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3698592726057386,"score_gpt":0.6163019402785802,"score_spread":0.2464426676728416,"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."}}