{"id":"W2250863190","doi":"10.3115/v1/d14-1051","title":"An I-vector Based Approach to Compact Multi-Granularity Topic Spaces Representation of Textual Documents","year":2014,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Agence Nationale de la Recherche","keywords":"Granularity; Computer science; Representation (politics); Information retrieval; Vector space; Natural language processing; Artificial intelligence; Mathematics; Programming language; Pure mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004614024,0.0002706698,0.000488289,0.0002094184,0.00005789421,0.0002975101,0.001745561,0.0001985782,0.0000201592],"category_scores_gemma":[0.00006517415,0.0002476507,0.0001397949,0.000186611,0.00003099758,0.0002575118,0.0005843536,0.0003022451,0.00001060616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000716823,"about_ca_system_score_gemma":0.0001180736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003529913,"about_ca_topic_score_gemma":0.00007484079,"domain_scores_codex":[0.9973985,0.0002879218,0.0004708448,0.001024073,0.0005446639,0.0002740186],"domain_scores_gemma":[0.9973073,0.00007128475,0.0002382382,0.002026153,0.0001577308,0.0001992998],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003998914,0.00160745,0.04272979,0.0006898379,0.0001295822,0.000004505684,0.003635447,0.8804996,0.002993194,0.04035656,0.0007880631,0.02652595],"study_design_scores_gemma":[0.0004204655,0.00005238547,0.01399597,0.00004109219,0.0000119283,7.515417e-7,0.00004315651,0.9800136,0.004493936,0.0005774043,0.00007820398,0.0002711007],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07624552,0.000009555361,0.9194775,0.0003395004,0.0003560468,0.000628464,0.000006335364,0.0001775622,0.002759497],"genre_scores_gemma":[0.6265412,5.280464e-7,0.373054,0.0001459749,0.00006397334,0.00001549247,0.00002749075,0.000007691933,0.0001436703],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5502957,"threshold_uncertainty_score":0.9999976,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06669668175130425,"score_gpt":0.3379462876103425,"score_spread":0.2712496058590382,"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."}}