{"id":"W16815992","doi":"10.1542/pir.27-7-243","title":"A Real-Time N-Gram Approach to Choosing Synonyms Based on Context","year":2015,"lang":"en","type":"article","venue":"Pediatrics in Review","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Computer science; n-gram; Gram; Artificial intelligence; Geography; Geology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001826164,0.0002007047,0.0004004784,0.000279527,0.00003650747,0.0001267984,0.001210041,0.0000822631,0.000003457019],"category_scores_gemma":[0.001207677,0.0001667343,0.00007176839,0.001874228,0.00001494544,0.0002244234,0.0002244719,0.0002816697,0.0001352022],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001968361,"about_ca_system_score_gemma":0.0002081676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000458654,"about_ca_topic_score_gemma":0.000001047085,"domain_scores_codex":[0.9980934,0.0001758574,0.0003866795,0.0005060468,0.0005163376,0.000321649],"domain_scores_gemma":[0.9985459,0.0001596386,0.0001459401,0.0007652917,0.0001648401,0.0002183795],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002597904,0.0007999361,0.0008500515,0.006630322,0.000006754615,0.000120148,0.0008040608,0.0001677515,0.00006449705,0.03869565,0.1270383,0.8247965],"study_design_scores_gemma":[0.006535682,0.003432026,0.000652822,0.04189076,0.0005205204,0.0003189016,0.00009395665,0.5095785,0.002033282,0.07865849,0.3456537,0.01063141],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003759943,0.2958742,0.6557551,0.00484655,0.0004747122,0.002975016,0.000007675924,0.001871243,0.03781953],"genre_scores_gemma":[0.01755835,0.007553688,0.9681491,0.006241985,0.0001744269,0.0001613794,0.000008493515,0.00002771729,0.0001248932],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8141651,"threshold_uncertainty_score":0.6799229,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03765216871223324,"score_gpt":0.3160731365407805,"score_spread":0.2784209678285472,"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."}}