{"id":"W2516087440","doi":"10.18653/v1/p16-1063","title":"Generative Topic Embedding: a Continuous Representation of Documents","year":2016,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Research (Canada)","funders":"National Research Foundation","keywords":"Embedding; Computer science; Representation (politics); Generative grammar; Natural language processing; Artificial intelligence; Political science","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":[0.00006456308,0.00004213945,0.00008152687,0.00003309047,0.00001733607,0.00002105134,0.0002387696,0.00001808462,0.0000571629],"category_scores_gemma":[0.00003519263,0.00002617456,0.00002514698,0.00007316163,0.00001214127,0.000306504,0.0001006668,0.00001397594,0.00001568621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001527407,"about_ca_system_score_gemma":0.0000144176,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003943841,"about_ca_topic_score_gemma":0.000003439095,"domain_scores_codex":[0.9994321,0.00002836637,0.0001454385,0.0001791004,0.0001268904,0.00008813653],"domain_scores_gemma":[0.9995235,0.00004450287,0.00005441231,0.0002980574,0.00005492728,0.00002456934],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00000423508,0.00004226661,0.009747273,0.000006395976,0.00003159401,0.000006476861,0.001538426,0.0001401316,0.07967761,0.5717302,0.001263118,0.3358122],"study_design_scores_gemma":[0.002199944,0.0001897212,0.006509589,0.00008545262,0.00001029119,0.00001439405,0.0001600322,0.1551253,0.7526539,0.08013589,0.002525598,0.0003899083],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1018286,0.00001013577,0.8896134,0.001138298,0.0001464873,0.0000626229,2.058448e-7,0.00004027556,0.007160019],"genre_scores_gemma":[0.8872498,0.000003857445,0.1072282,0.00008692565,0.00003054989,0.000004806774,1.153546e-7,0.000001587864,0.005394111],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7854213,"threshold_uncertainty_score":0.1067367,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02855893766562122,"score_gpt":0.3116345904051909,"score_spread":0.2830756527395697,"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."}}