{"id":"W4231760964","doi":"10.1515/iupac.79.1360","title":"Guinea-Pig Maximization Test","year":2016,"lang":"en","type":"dataset","venue":"IUPAC Standards Online","topic":"History and advancements in chemistry","field":"Chemistry","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Glossary; Chemical nomenclature; Computer science; Clinical toxicology; Toxicology; Chemistry; Biology; Philosophy; Linguistics","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":[0.0001948562,0.0005757894,0.0005555421,0.00007550555,0.0001926019,0.0000452902,0.0007001941,0.0006215924,0.04935615],"category_scores_gemma":[0.001407452,0.0005010926,0.0001650336,0.0001156803,0.0002026092,0.000114796,0.0001895172,0.0006107616,0.00001019084],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000977587,"about_ca_system_score_gemma":0.0005649082,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009277821,"about_ca_topic_score_gemma":0.00003583073,"domain_scores_codex":[0.9971651,0.00001409824,0.0006209422,0.0007181657,0.001008812,0.0004729194],"domain_scores_gemma":[0.9974896,0.0001576198,0.0004549502,0.001320262,0.0003776314,0.0001998888],"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":[0.00006309329,0.0003400985,0.00001396605,0.0006709231,0.0000632891,0.00008203356,0.000004618994,0.000003843958,0.002435194,0.000001354556,0.9931305,0.003191057],"study_design_scores_gemma":[0.000994344,0.00003133233,3.394298e-7,0.0007834912,0.0001103999,0.0000190173,0.00001287223,0.000003453776,0.004656422,0.00006941547,0.9927025,0.0006164269],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00002745803,0.0006383087,0.0001810199,0.0001404973,0.0005591764,0.00007038083,0.9955021,0.0001379325,0.002743167],"genre_scores_gemma":[0.000009027382,0.0008886838,0.0001329848,0.0001597227,0.002157743,0.00002255905,0.977564,0.00006801774,0.01899729],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.04934596,"threshold_uncertainty_score":0.9997441,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01201485869321755,"score_gpt":0.3713621684788462,"score_spread":0.3593473097856287,"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."}}