{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002503303,0.0005625456,0.0003508666,0.006822255,0.001018401,0.002774502,0.0009079744,0.000897557,0.002852481],"category_scores_gemma":[0.01404818,0.000260205,0.001329305,0.004694013,0.0008297944,0.004183307,0.00132936,0.001116896,0.0009815613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003386338,"about_ca_system_score_gemma":0.002926712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02103055,"about_ca_topic_score_gemma":0.0359545,"domain_scores_codex":[0.9974537,0.0007645415,0.0002722315,0.000598384,0.0008057671,0.0001052854],"domain_scores_gemma":[0.9916956,0.005121859,0.0009662308,0.0009114344,0.00114446,0.0001605037],"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":[0.0002958505,0.0009894873,0.07979369,0.001439069,0.0002737702,0.001165389,0.004447632,0.1109239,0.01346962,0.1332774,0.05132627,0.602598],"study_design_scores_gemma":[0.00006848852,0.00007939127,0.02078853,0.0002800594,0.0001069728,0.0003063588,0.003384918,0.6925463,0.01000209,0.1822897,0.09006468,0.00008241973],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1930384,0.0005926312,0.740149,0.005687548,0.0001530128,0.001756793,0.03078181,0.006693515,0.02114724],"genre_scores_gemma":[0.3841487,0.0003718009,0.5758873,0.0005059016,0.00004076865,0.0006910692,0.03590149,0.0002879107,0.002165118],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02103055,"threshold_uncertainty_score":0.04181629,"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."}}