{"id":"W4386942653","doi":"10.48550/arxiv.2309.10880","title":"Classifying Organizations for Food System Ontologies using Natural Language Processing","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Science Foundation","keywords":"Computer science; Artificial intelligence; Natural language processing; Government (linguistics); Information retrieval; Data science","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001404003,0.0002608196,0.0004400655,0.0005512122,0.0005210483,0.0005978233,0.001700827,0.0002186243,0.00001469692],"category_scores_gemma":[0.001693051,0.0002508261,0.0001745694,0.001563542,0.000116641,0.0005059945,0.002200014,0.0003166211,0.00008341909],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003602009,"about_ca_system_score_gemma":0.0002516718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001373373,"about_ca_topic_score_gemma":0.0008365451,"domain_scores_codex":[0.9975559,0.0002108165,0.0004430664,0.001149323,0.0002798392,0.0003611218],"domain_scores_gemma":[0.9971715,0.0006230701,0.0005671025,0.0009806438,0.0005737215,0.00008402236],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001915688,0.0002212941,0.00589397,0.003452279,0.0007466208,0.0005013474,0.007429107,0.61132,0.0002358852,0.3469679,0.009577739,0.01346234],"study_design_scores_gemma":[0.0004967622,0.00003837861,0.0007187832,0.0004018483,0.0002637076,0.000003760264,0.05297006,0.9266939,0.00006705312,0.0161492,0.001626624,0.0005699166],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2238858,0.0002368179,0.7713999,0.000177275,0.001671768,0.0007863382,0.000467654,0.0006855578,0.0006888831],"genre_scores_gemma":[0.9934418,0.000009984726,0.002181664,0.00004911371,0.0001100998,0.000002208446,0.000126016,0.00003119741,0.004047924],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.769556,"threshold_uncertainty_score":0.9999944,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4832696815824964,"score_gpt":0.3328273787771146,"score_spread":0.1504423028053818,"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."}}