{"id":"W6947633094","doi":"10.48448/06fw-yp11","title":"Do Language Models Understand Measurements?","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Botanical Research and Applications","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Language model; Language understanding; Simple (philosophy); Embedding; Work (physics); Natural language; Modeling language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00281155,0.001407847,0.0006805586,0.0009768151,0.0003321939,0.003243393,0.00130338,0.001640127,0.005732371],"category_scores_gemma":[0.02759618,0.0006771242,0.0008322333,0.0007379042,0.0008746318,0.0108726,0.001248546,0.003333796,0.004838537],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007122756,"about_ca_system_score_gemma":0.001078865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003759342,"about_ca_topic_score_gemma":0.0028248,"domain_scores_codex":[0.9980587,0.001048422,0.00007447795,0.000512129,0.0001708927,0.0001353367],"domain_scores_gemma":[0.9873369,0.009385023,0.0007937833,0.001380811,0.0008787414,0.0002247377],"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":[0.0006635757,0.0003316364,0.02587469,0.00129716,0.0006686889,0.0005008368,0.002817679,0.09052155,0.01945257,0.1043732,0.04067971,0.7128188],"study_design_scores_gemma":[0.00006333146,0.00009470356,0.005732587,0.0002143508,0.00009106223,0.000265629,0.0009544761,0.6942983,0.00655817,0.2752251,0.0163991,0.0001033147],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1144726,0.003316349,0.8308464,0.0164468,0.0008199678,0.0001251052,0.003886474,0.006101749,0.02398447],"genre_scores_gemma":[0.9020285,0.001611643,0.08238314,0.002154379,0.000405022,0.0001650201,0.004642722,0.0007446018,0.00586488],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005732371,"threshold_uncertainty_score":0.01917666,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1099746847172679,"score_gpt":0.3209974188198076,"score_spread":0.2110227341025397,"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."}}