{"id":"W2561412020","doi":"10.1371/journal.pone.0181142","title":"\"What is relevant in a text document?\": An interpretable machine learning approach","year":2017,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":268,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; Banting and Best Diabetes Centre, University of Toronto; National Research Foundation of Korea; Deutsche Forschungsgemeinschaft; National Research Foundation","keywords":"Computer science; Artificial intelligence; Relevance (law); Natural language processing; Categorization; Support vector machine; Convolutional neural network; Classifier (UML); Word (group theory); Machine learning; Document classification; Tracing; Information retrieval","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007403527,0.0001898291,0.0003006263,0.000159654,0.000464346,0.001983189,0.002147149,0.00008188045,0.0000989874],"category_scores_gemma":[0.0002422617,0.0001871956,0.00004779368,0.0001854029,0.00009268866,0.00545316,0.0007609823,0.0004323881,0.000367292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009770435,"about_ca_system_score_gemma":0.00004658988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001118442,"about_ca_topic_score_gemma":0.0002150719,"domain_scores_codex":[0.9979032,0.0001326474,0.0003311609,0.0006615118,0.0004538044,0.000517717],"domain_scores_gemma":[0.9979693,0.00006234684,0.0001988097,0.001533767,0.00009083211,0.0001449732],"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":[0.0004168024,0.02041461,0.1123071,0.001004233,0.0008131425,0.000652649,0.166329,0.004045365,0.1524875,0.1609816,0.0004911917,0.3800569],"study_design_scores_gemma":[0.0002354079,0.0003208811,0.0006678928,0.0003932484,0.00001796276,0.00000614257,0.0006283998,0.8883874,0.09744117,0.01087799,0.0005945688,0.0004289616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9119898,0.001104651,0.06057853,0.005050291,0.0003678482,0.0008753035,0.000002363383,0.0004288636,0.01960233],"genre_scores_gemma":[0.9661341,0.0003391149,0.02907059,0.0003291426,0.00005817412,0.00005265707,0.000003425671,0.00002179687,0.003990995],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.884342,"threshold_uncertainty_score":0.9990528,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06341091681322418,"score_gpt":0.2827673665988876,"score_spread":0.2193564497856634,"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."}}