{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001613295,0.001461099,0.001361119,0.006939046,0.00184158,0.002309615,0.001852555,0.001608881,0.009357414],"category_scores_gemma":[0.008341824,0.0007458765,0.001087144,0.005688404,0.0009071027,0.002775396,0.002315731,0.002179889,0.01302962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004937942,"about_ca_system_score_gemma":0.001983021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002274519,"about_ca_topic_score_gemma":0.002715134,"domain_scores_codex":[0.9964218,0.0004055357,0.0003139046,0.001023995,0.001597754,0.0002369522],"domain_scores_gemma":[0.994158,0.00142291,0.0004396058,0.001539687,0.002240867,0.0001989971],"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":[0.0001942408,0.00008680417,0.001072613,0.0002695473,0.00007578896,0.0002499487,0.0001902739,0.002729746,0.03463709,0.004479729,0.01139648,0.9446177],"study_design_scores_gemma":[0.0002663766,0.0004419392,0.007208276,0.0002031599,0.0002908999,0.007807797,0.0006504609,0.4673138,0.1966335,0.05350142,0.2651616,0.0005206872],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005283767,0.0006144142,0.9862091,0.000123841,0.0002550901,0.0002176001,0.0005654878,0.004851453,0.001879231],"genre_scores_gemma":[0.02891043,0.000346278,0.9615219,0.00008283825,0.0001875425,0.0003062787,0.001455656,0.0005219921,0.006667098],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009357414,"threshold_uncertainty_score":0.0313037,"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."}}