{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002087697,0.0002204226,0.0002865249,0.000216068,0.00005646667,0.0001757868,0.001082518,0.0001481036,0.000547323],"category_scores_gemma":[0.00001250503,0.0001981831,0.0001499766,0.00004106802,0.00003102747,0.0002314294,0.0002736841,0.000143677,0.0009611144],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001162622,"about_ca_system_score_gemma":0.00002524716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003940474,"about_ca_topic_score_gemma":0.000007909453,"domain_scores_codex":[0.9985636,0.00001321409,0.0004296659,0.0004873972,0.0003634371,0.000142666],"domain_scores_gemma":[0.9981107,0.00004565429,0.000305631,0.001394752,0.00008850308,0.00005477097],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[4.251051e-8,0.000001559173,3.724984e-7,0.0000107397,0.00001602564,0.000001395665,0.00001147855,0.000001048296,0.00002050443,0.7788616,0.0018964,0.2191788],"study_design_scores_gemma":[0.00003960237,0.00002165294,0.00001769472,0.00005046168,0.00002976692,0.000003948005,3.634019e-7,0.009524558,0.0008429759,0.7532469,0.2359248,0.0002972895],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.000001345925,0.00004928237,0.6509895,0.0002596672,0.00008635633,0.0001245771,1.743704e-7,0.000687704,0.3478014],"genre_scores_gemma":[0.003823546,0.00004790255,0.1333153,0.0002738133,0.0000697911,0.00002093978,0.00000915571,0.00001885662,0.8624207],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.5176741,"threshold_uncertainty_score":0.9998168,"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."}}