{"id":"W2047348798","doi":"10.1145/2213836.2213970","title":"Towards scalable summarization and visualization of large text corpora (abstract only)","year":2012,"lang":"en","type":"article","venue":"","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Automatic summarization; Scalability; Information retrieval; NoSQL; World Wide Web; Visualization; Analytics; Full text search; Data visualization; Data science; Search engine; Database; Artificial intelligence","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":[0.0003625152,0.00008148528,0.0001127029,0.0001117989,0.00005949645,0.00008603255,0.000193065,0.00004955241,0.0001480772],"category_scores_gemma":[0.00006419129,0.00007245269,0.00001961679,0.000473459,0.00002482338,0.001209354,0.0001493177,0.00002773632,0.00002625425],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001188096,"about_ca_system_score_gemma":0.00004985827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002787085,"about_ca_topic_score_gemma":0.000006851819,"domain_scores_codex":[0.9991973,0.00002627174,0.0002297965,0.0001444475,0.0002183735,0.0001838151],"domain_scores_gemma":[0.9994099,0.00002195195,0.0001298852,0.0002211005,0.0001177524,0.00009942451],"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":[0.000001246467,0.0001777691,0.04818327,0.00003093699,0.000007523663,2.472456e-7,0.0002170017,0.000007989442,0.0004109043,0.9418017,0.001945854,0.007215512],"study_design_scores_gemma":[0.001734949,0.0001722793,0.3053989,0.00009917508,0.00005355601,0.00003174102,0.0003137318,0.5807362,0.03007341,0.004202755,0.07632893,0.0008543428],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008397089,0.00006629092,0.9775584,0.00009428539,0.0001337198,0.0000748244,0.00001074956,0.00008871887,0.01357592],"genre_scores_gemma":[0.9914952,0.00005689271,0.007089217,0.0003178163,0.00003348282,8.946058e-7,0.00009417741,0.000006915438,0.0009053978],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9830981,"threshold_uncertainty_score":0.2954535,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02637914321600676,"score_gpt":0.3125271263731714,"score_spread":0.2861479831571646,"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."}}