{"id":"W2962770186","doi":"10.18653/v1/d15-1179","title":"Fast, Flexible Models for Discovering Topic Correlation across Weakly-Related Collections","year":2015,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; John Templeton Foundation; National Science Foundation","keywords":"Computer science; Correlation; Information retrieval; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004211398,0.0002691533,0.0003272022,0.0001353108,0.0003469202,0.0006458037,0.0009363306,0.0003667113,0.00001245323],"category_scores_gemma":[0.00004590623,0.0002685481,0.0001732972,0.0003384347,0.0000254978,0.000666878,0.001573072,0.0004403229,0.00001433328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003198158,"about_ca_system_score_gemma":0.000382557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005209221,"about_ca_topic_score_gemma":0.00009671116,"domain_scores_codex":[0.9979214,0.00003803968,0.000501062,0.0008211468,0.0002968262,0.0004215444],"domain_scores_gemma":[0.9983198,0.00007836494,0.0001955052,0.001017705,0.0002641986,0.0001244501],"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":[0.000003278912,0.00002272481,0.00002154714,0.00003600166,0.00003109753,5.973078e-7,0.001674089,0.9163002,0.00001390039,0.076141,0.001185956,0.004569564],"study_design_scores_gemma":[0.0002848774,0.00002165154,0.00001177803,0.00005615998,0.00001069308,0.000004516898,0.00007426058,0.8083183,0.0001094079,0.1902485,0.0006109766,0.0002489067],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004173295,0.0001318804,0.968692,0.0004664846,0.003304646,0.0008440122,0.00002650878,0.0006339281,0.02172727],"genre_scores_gemma":[0.5726821,0.00002638576,0.3097633,0.0001297113,0.0003324014,0.0004581055,0.00007718641,0.00005034456,0.1164806],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6589288,"threshold_uncertainty_score":0.9999767,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06405536907975934,"score_gpt":0.3114599321620022,"score_spread":0.2474045630822428,"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."}}