{"id":"W4231486013","doi":"10.1007/978-1-4614-6170-8_110113","title":"Automatic Document Topic Identification","year":2014,"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; 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":[0.0005905897,0.001026391,0.0007905196,0.00379442,0.0007927374,0.002141223,0.0008301325,0.0006677974,0.01662096],"category_scores_gemma":[0.001610399,0.0004411557,0.0007678281,0.002762951,0.0003530707,0.002075815,0.001188766,0.001017277,0.02103308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004647964,"about_ca_system_score_gemma":0.0005955104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006991829,"about_ca_topic_score_gemma":0.001081871,"domain_scores_codex":[0.9994722,0.00007566993,0.00003560364,0.000154064,0.0002094561,0.00005300083],"domain_scores_gemma":[0.9990674,0.0003082166,0.0000515644,0.0001566005,0.0003721793,0.00004405273],"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":[0.00008036694,0.00004104953,0.0003384026,0.0003307556,0.00002413189,0.00008188352,0.0001313704,0.0007375085,0.03165999,0.00492744,0.06791469,0.8937325],"study_design_scores_gemma":[0.00003827506,0.0001416548,0.005541773,0.0003584236,0.0001962826,0.002464359,0.0004957386,0.08545154,0.1605986,0.030161,0.7144324,0.0001199954],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0145245,0.01382431,0.8836918,0.000863069,0.001734236,0.0002491774,0.003105079,0.01711548,0.06489226],"genre_scores_gemma":[0.1080499,0.009842523,0.6419629,0.0003528025,0.001314695,0.0003065397,0.01686393,0.00282067,0.218486],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01662096,"threshold_uncertainty_score":0.05560267,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01064088907043684,"score_gpt":0.2615044887871174,"score_spread":0.2508635997166805,"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."}}