{"id":"W1981929466","doi":"10.1075/ml.6.2.04tre","title":"The effects of N-gram probabilistic measures on the recognition and production of four-word sequences","year":2011,"lang":"en","type":"article","venue":"The Mental Lexicon","topic":"Reading and Literacy Development","field":"Psychology","cited_by":92,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Trigram; Bigram; n-gram; Probabilistic logic; Computer science; Logarithm; Speech recognition; Artificial intelligence; Latency (audio); Production (economics); Gram; Natural language processing; Mathematics; Language model","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":[0.0007504359,0.00008128387,0.00008831881,0.00002136246,0.00014896,0.00001075,0.0001241237,0.00002654405,0.00002450516],"category_scores_gemma":[0.0001380095,0.00003454534,0.00002822742,0.00007148534,0.000286809,0.00002852623,0.00001803129,0.00008965799,0.00001807183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001858091,"about_ca_system_score_gemma":0.00001076121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001469613,"about_ca_topic_score_gemma":0.00001607322,"domain_scores_codex":[0.9991246,0.000314171,0.0001749288,0.000134986,0.0001419283,0.0001093924],"domain_scores_gemma":[0.999243,0.0003535454,0.0001398024,0.0002159577,0.00003359765,0.00001412197],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001616366,0.0005973108,0.003906752,0.0003056231,0.0004597953,0.000003932703,0.1186902,0.000001310805,0.0517274,0.02178746,0.002673432,0.7982305],"study_design_scores_gemma":[0.001305762,0.002963905,0.1858947,0.001484009,0.0002438787,0.0001312043,0.008612446,0.00001727277,0.6160148,0.1782514,0.004628065,0.0004524326],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9929277,0.0002340014,0.00000257371,0.0006287239,0.0008674843,0.0006501779,0.000002461271,0.00001318135,0.004673685],"genre_scores_gemma":[0.9990783,0.00005043735,0.00003338378,0.00005057742,0.00003986845,0.0001007566,0.000002932136,0.000006269865,0.0006374381],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.797778,"threshold_uncertainty_score":0.1408718,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0802736112841805,"score_gpt":0.2824544277143404,"score_spread":0.2021808164301599,"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."}}