{"id":"W2251363724","doi":"10.3115/v1/p15-1075","title":"Efficient Methods for Inferring Large Sparse Topic Hierarchies","year":2015,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Science North","funders":"Defense Advanced Research Projects Agency; Allen Institute for Artificial Intelligence; National Science Foundation","keywords":"Computer science; Computational linguistics; Joint (building); Volume (thermodynamics); Natural language processing; Artificial intelligence; Data science; Engineering; Physics","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":[],"consensus_categories":[],"category_scores_codex":[0.000901625,0.00007753013,0.0001108015,0.00007280708,0.00006088518,0.00008102124,0.0004495472,0.00003051873,0.000005855102],"category_scores_gemma":[0.0001611116,0.00006438377,0.00004447235,0.0001143725,0.000009680209,0.00008282339,0.0003123748,0.00005731659,0.00001349993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003160478,"about_ca_system_score_gemma":0.00005953296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001829872,"about_ca_topic_score_gemma":0.000006563111,"domain_scores_codex":[0.9991603,0.0000579302,0.0001531871,0.0002491031,0.0001129362,0.0002665435],"domain_scores_gemma":[0.9992554,0.0001212898,0.00002758499,0.0004197344,0.00006641643,0.0001095546],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002497312,0.0000429933,0.0003602263,0.00001341736,0.000008306362,0.000001412731,0.002067638,0.01543282,0.0001649971,0.8287072,0.0002816627,0.1529168],"study_design_scores_gemma":[0.0003265313,0.00002705141,0.00007559176,0.00000454477,0.00000187225,0.000002581276,0.00003772427,0.955219,0.001118343,0.01568688,0.02740741,0.00009249581],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01431886,0.0001013582,0.9776497,0.0006508979,0.0005697486,0.0001567041,3.416923e-7,0.0001782622,0.006374164],"genre_scores_gemma":[0.1691037,5.104015e-7,0.8295716,0.0003091035,0.00007415748,0.00001991756,3.140518e-7,0.000004121317,0.0009166113],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9397861,"threshold_uncertainty_score":0.2625494,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1102563106285173,"score_gpt":0.382636016183524,"score_spread":0.2723797055550067,"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."}}