{"id":"W3209857478","doi":"10.4018/ijirr.289950","title":"An End-to-End Efficient Lucene-Based Framework of Document/Information Retrieval","year":2021,"lang":"en","type":"article","venue":"International Journal of Information Retrieval Research","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Trois-Rivières; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Information retrieval; Word (group theory); Automatic summarization; Context (archaeology); Set (abstract data type); Document retrieval; Natural language processing","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":[0.001471682,0.0007814964,0.0009537662,0.0017939,0.0008664267,0.002826198,0.001640215,0.001157415,0.005051068],"category_scores_gemma":[0.00385986,0.0003981597,0.0009984776,0.001580762,0.0006980164,0.004344607,0.002024765,0.001383397,0.006852755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007535575,"about_ca_system_score_gemma":0.0008467468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002031131,"about_ca_topic_score_gemma":0.002779717,"domain_scores_codex":[0.9987973,0.0002524089,0.000119391,0.0002518138,0.0004879424,0.00009113529],"domain_scores_gemma":[0.9986707,0.0003109818,0.00008563598,0.000458437,0.0004160829,0.00005826082],"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":[0.001022322,0.0004660438,0.001441756,0.001200241,0.0002749087,0.0008014124,0.001365187,0.04758091,0.1779348,0.100806,0.0361764,0.6309299],"study_design_scores_gemma":[0.00009493923,0.000473164,0.001026516,0.0001180628,0.0001366064,0.0009640792,0.0002657596,0.6585739,0.1770997,0.05344721,0.107598,0.0002019655],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003144586,0.0002517982,0.9862406,0.00008684984,0.00002586262,0.0001149045,0.0003441724,0.008506101,0.001285169],"genre_scores_gemma":[0.07355174,0.0004848023,0.9144794,0.0001627349,0.00007830269,0.0003400261,0.003021561,0.0008204538,0.00706097],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005051068,"threshold_uncertainty_score":0.01689756,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03288790709535719,"score_gpt":0.3763032752844996,"score_spread":0.3434153681891424,"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."}}