{"id":"W2955898947","doi":"10.1145/3331184.3331395","title":"Information Retrieval Meets Scalable Text Analytics","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"SPARK (programming language); Scalability; Computer science; Analytics; Downstream (manufacturing); Pipeline transport; Range (aeronautics); Data science; Database; Programming language; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001547213,0.00006450836,0.00009207087,0.00006148407,0.00004293102,0.00007015457,0.0002068578,0.00002803257,0.0001338382],"category_scores_gemma":[0.000028547,0.00005041013,0.00002411198,0.0002988242,0.00001063891,0.003191879,0.0001539102,0.00004587776,0.001834757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002198324,"about_ca_system_score_gemma":0.00003593514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002657857,"about_ca_topic_score_gemma":0.000003368295,"domain_scores_codex":[0.9993765,0.00001070248,0.0001749541,0.00009248028,0.0002006784,0.0001446601],"domain_scores_gemma":[0.9993294,0.00002588849,0.00006150686,0.0004570847,0.00007897051,0.00004711935],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000005396865,0.00000778993,0.0006083453,0.00002553738,0.000006637349,7.083029e-7,0.0002142875,0.0005636416,0.0003933962,0.9876674,0.004307775,0.006199125],"study_design_scores_gemma":[0.0002656152,0.00005419312,0.0008034729,0.00001751496,0.000001415416,0.00001016954,0.000132903,0.09758528,0.004231902,0.0004465467,0.8962811,0.0001699121],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006094626,0.00001914158,0.9465941,0.0003600534,0.0003344419,0.0001136715,0.000004895235,0.0001306857,0.04634844],"genre_scores_gemma":[0.748635,0.00001757712,0.2389833,0.001012853,0.00005792388,0.000002460612,0.000030873,0.000006185707,0.0112538],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9872208,"threshold_uncertainty_score":0.9989424,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008595608315333266,"score_gpt":0.2252329320424834,"score_spread":0.2166373237271501,"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."}}