{"id":"W2294768574","doi":"10.1109/icppw.2015.42","title":"Efficient Parallelization of the Google Trigram Method for Document Relatedness Computation","year":2015,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Trigram; Computation; Set (abstract data type); Construct (python library); Theoretical computer science; Word (group theory); Parallel computing; Artificial intelligence; Algorithm; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006762104,0.0008162631,0.0008877923,0.001693532,0.0008565966,0.001262219,0.001497219,0.0004557032,0.005456417],"category_scores_gemma":[0.003160869,0.0002825454,0.0009190544,0.003073571,0.0004126099,0.001378556,0.0009615243,0.0007555226,0.002551102],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008734484,"about_ca_system_score_gemma":0.002371553,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01637267,"about_ca_topic_score_gemma":0.02283309,"domain_scores_codex":[0.9991034,0.000146089,0.00007243518,0.0001552342,0.0004053834,0.0001174473],"domain_scores_gemma":[0.9988728,0.0002923272,0.00006360275,0.0002804979,0.0004120599,0.00007864976],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005187017,0.0002321131,0.003175228,0.0002811559,0.0001213168,0.0004304322,0.0004022248,0.1012876,0.01893525,0.02053325,0.02420154,0.8298813],"study_design_scores_gemma":[0.0001158727,0.0000842885,0.001148451,0.00001331147,0.00002887983,0.0002196649,0.0001863892,0.958769,0.009826643,0.01842455,0.01115008,0.00003296164],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04859723,0.000676401,0.930595,0.0003239807,0.0002682899,0.0002405364,0.0008077422,0.01126228,0.007228512],"genre_scores_gemma":[0.1948689,0.0003000295,0.7962405,0.00009059549,0.0001008468,0.000326992,0.002079914,0.0004166256,0.005575553],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01637267,"threshold_uncertainty_score":0.03255475,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2641596666964932,"score_gpt":0.4911128465630769,"score_spread":0.2269531798665838,"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."}}