{"id":"W2163364265","doi":"10.3115/1614108.1614116","title":"A fast method for parallel document identification","year":2007,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University of Alberta","keywords":"Computer science; Identification (biology); Homogeneous; Information retrieval; Domain (mathematical analysis); Parallel corpora; Frequency domain; Parallel algorithm; Natural language processing; Data mining; Artificial intelligence; Algorithm; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.001114327,0.00006408727,0.00006440664,0.00007744945,0.00006399917,0.0001546752,0.0005536432,0.00003945253,0.00000611992],"category_scores_gemma":[0.00004985199,0.00005101495,0.0000371009,0.0001792036,0.000008042176,0.0003823452,0.00008930219,0.00004590419,0.00001041741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003627569,"about_ca_system_score_gemma":0.00001495026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000223897,"about_ca_topic_score_gemma":0.00001282962,"domain_scores_codex":[0.9992689,0.00001363553,0.0001743755,0.0002340493,0.0001367604,0.0001722169],"domain_scores_gemma":[0.9994068,0.00009895059,0.00006710797,0.0002968685,0.00009158613,0.00003874746],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000004275541,0.00001237657,0.000006040489,0.00001015842,0.000003462821,0.000001284745,0.0001846496,0.000002040745,0.01169744,0.5772566,0.001404096,0.4094176],"study_design_scores_gemma":[0.00021591,0.00004960971,0.0001411382,0.00001103285,0.000004979733,0.0000146012,0.00003262328,0.01945392,0.4082473,0.5655653,0.006063529,0.000200015],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00003289422,0.0002269523,0.9971757,0.0009959087,0.00009790746,0.0002286786,2.78788e-7,0.0005563173,0.0006853495],"genre_scores_gemma":[0.02476631,0.00000151289,0.9728327,0.0004396015,0.00003378555,0.00003080808,0.000001945808,0.000004272031,0.00188902],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4092176,"threshold_uncertainty_score":0.2080329,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01542303074993952,"score_gpt":0.3515386115069515,"score_spread":0.336115580757012,"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."}}