{"id":"W4250002556","doi":"10.1007/978-1-4939-7131-2_100048","title":"Automatic Document Topic Identification","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Identification (biology); Computer science; Information retrieval; Natural language processing; World Wide Web; Biology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006574857,0.001067889,0.0008081822,0.003978011,0.0008391104,0.002403491,0.0008329303,0.0007241833,0.01816893],"category_scores_gemma":[0.001894966,0.0004461554,0.0008250259,0.002888705,0.0003554485,0.002236963,0.001307031,0.001135554,0.02423012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004789901,"about_ca_system_score_gemma":0.0006562262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005812274,"about_ca_topic_score_gemma":0.0008824129,"domain_scores_codex":[0.9994129,0.00008400495,0.00004086475,0.0001806413,0.0002223064,0.00005933885],"domain_scores_gemma":[0.9989136,0.0003473915,0.00006182104,0.0001935508,0.0004289361,0.00005467578],"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":[0.0001023715,0.00005109891,0.0003842332,0.000403134,0.00002932198,0.00009315929,0.0001452491,0.0008228535,0.03462581,0.005837599,0.07982178,0.8776833],"study_design_scores_gemma":[0.00004144091,0.000149052,0.005101288,0.0003630285,0.0002093701,0.002266975,0.0004619368,0.08362454,0.1516289,0.03213953,0.7238979,0.0001160327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01569912,0.01409894,0.8742151,0.001056742,0.002241873,0.0002796605,0.003848403,0.01940954,0.06915064],"genre_scores_gemma":[0.1204863,0.009904166,0.6290028,0.0004130009,0.001679485,0.0003599818,0.0199173,0.003231074,0.2150059],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01816893,"threshold_uncertainty_score":0.06078112,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01362815349892899,"score_gpt":0.2761468307642007,"score_spread":0.2625186772652717,"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."}}