{"id":"W2899883143","doi":"10.3897/bdj.6.e29616","title":"Incentivising use of structured language in biological descriptions: Author-driven phenotype data and ontology production","year":2018,"lang":"en","type":"article","venue":"Biodiversity Data Journal","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba; University of Winnipeg; University of Ottawa; Agriculture and Agri-Food Canada","funders":"","keywords":"Variation (astronomy); Ontology; Computer science; Data science; Scale (ratio); Geography","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":[],"consensus_categories":[],"category_scores_codex":[0.0003305833,0.00008009095,0.0001299291,0.00006680004,0.0001229368,0.00003114643,0.0005462712,0.0001353045,0.00001922929],"category_scores_gemma":[0.000918251,0.00006509502,0.00001296201,0.00008180893,0.000524506,0.00003137993,0.001151504,0.0001414346,0.000002433766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001065794,"about_ca_system_score_gemma":0.0000470075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000115013,"about_ca_topic_score_gemma":0.0004812401,"domain_scores_codex":[0.9991309,0.0001295483,0.0001582665,0.0003444294,0.00008437328,0.0001524652],"domain_scores_gemma":[0.9992062,0.00001275652,0.0001149569,0.0005482368,0.00006138391,0.00005641334],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005295114,0.0001675764,0.6296335,0.0000208728,0.0001283626,0.00004259353,0.0006341584,0.000001304402,0.2464921,0.000009585311,0.04127026,0.08107007],"study_design_scores_gemma":[0.00231888,0.001628958,0.7852166,0.000139104,0.0001546895,0.0006587949,0.003856014,0.0007690706,0.01075259,0.0001561424,0.1937201,0.0006290536],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9965825,0.0006408019,0.001419166,0.0003644624,0.0003135052,0.00005310809,0.0006154304,0.000006319317,0.000004697362],"genre_scores_gemma":[0.9812927,0.0003483016,0.01711783,0.00006066997,0.0002044545,1.114266e-7,0.0009618174,0.000001996216,0.00001215379],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2357395,"threshold_uncertainty_score":0.2654498,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1776877162654172,"score_gpt":0.3320332862511854,"score_spread":0.1543455699857683,"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."}}