{"id":"W4233455550","doi":"10.1515/iupac.87.0104","title":"Boston Naming Test (BNT)","year":2016,"lang":"en","type":"dataset","venue":"IUPAC Standards Online","topic":"Psychological Testing and Assessment","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"","keywords":"Glossary; Chemical nomenclature; Relation (database); Test (biology); Computer science; Psychology; Linguistics; Chemistry; Data mining; Philosophy; Biology; Organic chemistry","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":[],"category_scores_codex":[0.0009384743,0.000645746,0.0008159803,0.0002265665,0.000177289,0.00007542072,0.0008096112,0.0007465815,0.0177462],"category_scores_gemma":[0.001572095,0.0004577949,0.0002438699,0.0002610792,0.0002287127,0.0000512916,0.0002053058,0.001024863,0.00007367737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003925854,"about_ca_system_score_gemma":0.0002756814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001339765,"about_ca_topic_score_gemma":0.00007283105,"domain_scores_codex":[0.9961818,0.0002095854,0.0007077458,0.001084217,0.0009383172,0.0008783776],"domain_scores_gemma":[0.9965092,0.0009660423,0.0004647097,0.001485078,0.0002848756,0.0002900919],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007791896,0.0009236356,0.0001374749,0.00004318438,0.0001156727,0.0003597276,0.00001545967,1.344829e-7,0.00001925534,0.00003017493,0.9785088,0.01976855],"study_design_scores_gemma":[0.001289722,0.0007709645,0.0009529986,0.0005720574,0.0001004572,0.00007567024,0.00004809473,6.892665e-7,0.000002895253,0.0002929201,0.995272,0.0006215018],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0002590386,0.0008485255,0.0001773578,0.00108507,0.003403201,0.0003217662,0.9897247,0.000272758,0.003907588],"genre_scores_gemma":[0.0002081615,0.0002111781,0.0001171512,0.0009473671,0.002123381,0.00005590026,0.991731,0.0000645432,0.004541271],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01914705,"threshold_uncertainty_score":0.9997874,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03857503140811151,"score_gpt":0.4968499245471082,"score_spread":0.4582748931389967,"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."}}