{"id":"W4244522263","doi":"10.1002/asi.20463","title":"The reusability of induced knowledge for the automatic semantic markup of taxonomic descriptions","year":2006,"lang":"en","type":"article","venue":"Journal of the American Society for Information Science and Technology","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Markup language; Computer science; Natural language processing; Knowledge base; XML; Artificial intelligence; Information retrieval; Reusability; Text corpus; World Wide Web; Programming language; Software","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001396028,0.00004788037,0.0001226051,0.00004299717,0.000303759,0.00001613115,0.0005113754,0.00005058093,1.711514e-7],"category_scores_gemma":[0.001022451,0.00002234843,0.0001454971,0.0004456627,0.00312835,0.00001882073,0.0001053691,0.00007194431,7.326242e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000203478,"about_ca_system_score_gemma":0.0002420429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001004987,"about_ca_topic_score_gemma":0.000007248234,"domain_scores_codex":[0.9993508,0.00001131263,0.0003602945,0.00004763615,0.0001132984,0.0001166556],"domain_scores_gemma":[0.9983592,0.0001570986,0.0007573226,0.0002069792,0.0005067938,0.00001261984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008395885,0.00008268402,0.004179045,0.0001111314,0.000152899,1.11304e-8,0.0005511284,0.00002712248,0.3197683,0.004192437,0.01924769,0.6516036],"study_design_scores_gemma":[0.002802501,0.0045348,0.1060591,0.0001450125,0.0003725927,0.0001610447,0.0503692,0.01990571,0.3482738,0.01238146,0.4545774,0.0004174193],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9877387,0.000265396,0.00779701,0.003836775,0.0001127648,0.0001978563,0.00000827342,0.000003862444,0.00003941356],"genre_scores_gemma":[0.9946619,0.0001060062,0.0051063,0.00007640341,0.0000216021,0.00001388865,4.357892e-7,0.000001422433,0.0000120185],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6511862,"threshold_uncertainty_score":0.9995846,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01596344210632304,"score_gpt":0.2855851794837944,"score_spread":0.2696217373774714,"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."}}