{"id":"W2396331625","doi":"","title":"Merging Different Languages in a Single Document Collection.","year":2002,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Search engine indexing; Natural language processing; Information retrieval; Set (abstract data type); Artificial intelligence; Document retrieval; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007076098,0.00009248276,0.00009893121,0.000173761,0.0000513745,0.0001471833,0.0003912497,0.0000356136,0.0001605694],"category_scores_gemma":[0.00003141275,0.00007054472,0.00002582274,0.000435943,0.00001210337,0.0003116304,0.0001527285,0.000101298,0.00001800591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001177113,"about_ca_system_score_gemma":0.000003739875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000943576,"about_ca_topic_score_gemma":0.00007889196,"domain_scores_codex":[0.999259,0.00003134097,0.0001328268,0.0002244063,0.0001631776,0.0001892744],"domain_scores_gemma":[0.9996422,0.00003891836,0.00003332251,0.0002304116,0.00001999802,0.0000351265],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001001948,0.001110844,0.004267093,0.0001025493,0.00003742912,0.0003733349,0.0109318,0.00003007704,0.07716062,0.3810688,0.03307633,0.4918311],"study_design_scores_gemma":[0.001458132,0.0004394487,0.001586378,0.0002965741,0.00001017479,0.0001392068,0.0003878429,0.08218229,0.8148856,0.09235945,0.004961338,0.001293581],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06946199,0.01083253,0.8652607,0.008256765,0.0003315037,0.000447607,4.172309e-7,0.003014323,0.04239415],"genre_scores_gemma":[0.7916823,0.00001687264,0.2050878,0.0002264141,0.0000162727,0.00001575815,2.19373e-7,0.000004488197,0.002949902],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.737725,"threshold_uncertainty_score":0.287673,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01311184511933987,"score_gpt":0.2545793652213054,"score_spread":0.2414675201019655,"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."}}