{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003113442,0.001526142,0.001827537,0.004684885,0.001578131,0.00256601,0.003275642,0.001889245,0.003662356],"category_scores_gemma":[0.01643038,0.001583983,0.002101279,0.005387316,0.0007553541,0.004835833,0.002906099,0.003340031,0.002589702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001089119,"about_ca_system_score_gemma":0.001658114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.013324,"about_ca_topic_score_gemma":0.03270957,"domain_scores_codex":[0.9975334,0.001010636,0.000144005,0.0005959251,0.0005000202,0.0002158858],"domain_scores_gemma":[0.9911608,0.006578004,0.0003276214,0.000954158,0.0007574768,0.0002219463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006223901,0.0003682496,0.00877146,0.0007057468,0.0006999401,0.0003094161,0.001427129,0.1029256,0.006989487,0.05506562,0.07412387,0.7479913],"study_design_scores_gemma":[0.0001043493,0.00003020025,0.001066057,0.00005010876,0.0001182515,0.0001412054,0.0002055394,0.8661307,0.00130796,0.1228182,0.00799918,0.00002826077],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008407648,0.002019215,0.9841905,0.0004613729,0.00009180095,0.0001203684,0.001082846,0.002522294,0.001104033],"genre_scores_gemma":[0.2071586,0.001679103,0.7749498,0.0003252086,0.0006299023,0.0005109544,0.01006674,0.000770531,0.003909086],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.013324,"threshold_uncertainty_score":0.02649289,"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."}}