{"id":"W4391689861","doi":"10.1016/j.softx.2024.101649","title":"APRCOIE: An open information extraction system for Chinese","year":2024,"lang":"en","type":"article","venue":"SoftwareX","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; National Office for Philosophy and Social Sciences","keywords":"Computer science; Information extraction; Information retrieval; World Wide Web; Natural language processing","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003454226,0.00007364259,0.00007745039,0.00007793387,0.00009397374,0.001005779,0.0006925811,0.00004444892,0.00000402763],"category_scores_gemma":[0.00004436403,0.00006182073,0.00002675615,0.0001750796,0.000004244146,0.005279349,0.0001610395,0.00006279601,0.00008159805],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007568555,"about_ca_system_score_gemma":0.00007555921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006605792,"about_ca_topic_score_gemma":0.000006519487,"domain_scores_codex":[0.9993678,0.00001678973,0.0001775773,0.0001866861,0.0001253482,0.0001257891],"domain_scores_gemma":[0.9994429,0.00006240389,0.00003563661,0.0003543728,0.00005646315,0.00004818416],"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":[0.00001128683,0.00002316084,0.0002496559,0.0005960429,0.00001947545,0.000006010974,0.003400872,0.002064018,0.0002881542,0.1551844,0.001710081,0.8364469],"study_design_scores_gemma":[0.0001702035,0.0000559117,0.0004563865,0.00007303296,0.00000434559,0.00003274649,0.00006891989,0.9690517,0.0001281784,0.005912631,0.02391216,0.0001338045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007879412,0.00005815508,0.988429,0.0002291301,0.001457431,0.0003654275,0.000005663438,0.0007856093,0.0007902017],"genre_scores_gemma":[0.8691119,0.000001135635,0.1303496,0.0001005859,0.0001562834,0.00009153002,0.00001903559,0.00000662448,0.0001633468],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9669877,"threshold_uncertainty_score":0.9698754,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02400441237466808,"score_gpt":0.314194521563081,"score_spread":0.2901901091884129,"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."}}