{"id":"W1988834855","doi":"10.1002/meet.1450420170","title":"MARTT: Using induced knowledge base to automatically mark up plant taxonomic descriptions with XML","year":2005,"lang":"en","type":"article","venue":"Proceedings of the American Society for Information Science and Technology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Markup language; XML; Computer science; RuleML; Domain (mathematical analysis); Knowledge base; XHTML; Natural language processing; Artificial intelligence; Information retrieval; World Wide Web; Mathematics","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":[0.0007281086,0.0001224681,0.0002103112,0.0004280663,0.0004258497,0.0001485894,0.00122003,0.00004300634,3.642001e-7],"category_scores_gemma":[0.0002354432,0.00008729369,0.00007031582,0.004080038,0.001015016,0.003078069,0.0005383161,0.000116096,0.000002415434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002191705,"about_ca_system_score_gemma":0.0002394233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008506941,"about_ca_topic_score_gemma":0.000003178317,"domain_scores_codex":[0.9988389,0.000001587287,0.0003110335,0.0002217916,0.0002756316,0.0003510299],"domain_scores_gemma":[0.9983088,0.00002901577,0.0004549539,0.0002239657,0.0009016332,0.00008161959],"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":[0.00002992484,0.00008291585,0.002490531,0.00008970338,0.00007177407,3.091154e-8,0.005310924,0.00005548462,0.2227845,0.327734,0.004180414,0.4371697],"study_design_scores_gemma":[0.0007834823,0.0008772993,0.002300588,0.0001714036,0.00009126925,0.00009569027,0.009438846,0.6324581,0.302351,0.006211834,0.04443422,0.000786259],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7829086,0.000005698216,0.2118695,0.003903508,0.00002528585,0.0005159961,0.000005915095,0.0002940445,0.0004714763],"genre_scores_gemma":[0.5979272,0.000004422439,0.4015416,0.0004564965,0.000006062389,0.00005369282,1.922253e-7,0.000002710752,0.000007634672],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6324026,"threshold_uncertainty_score":0.3739869,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02088201374965352,"score_gpt":0.2770650099305437,"score_spread":0.2561829961808902,"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."}}