{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005005859,0.0001397199,0.0002387537,0.001560146,0.0001228807,0.0008921426,0.002107043,0.0001463363,0.000251911],"category_scores_gemma":[0.005021341,0.0001311153,0.0001565199,0.00147841,0.00007112897,0.004591348,0.0003559639,0.0007511699,0.0001045444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005402402,"about_ca_system_score_gemma":0.001627327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001605397,"about_ca_topic_score_gemma":6.915383e-7,"domain_scores_codex":[0.9924978,0.0002790531,0.001522513,0.000147295,0.005197267,0.0003560811],"domain_scores_gemma":[0.9879332,0.0006307813,0.0007114376,0.0005213163,0.009893396,0.0003098865],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003572762,0.0005815878,0.001030413,0.0002146316,0.0003650454,0.0001485255,0.01473805,0.436034,0.01371125,0.2815808,0.001501248,0.2465216],"study_design_scores_gemma":[0.003075895,0.001154075,0.003830691,0.0007671762,0.0000163611,0.0002513372,0.001405012,0.5961088,0.362534,0.009583506,0.0208159,0.0004572786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2169606,0.00003764364,0.7769337,0.003704569,0.00126299,0.0001605416,0.00001893928,0.00002173901,0.0008992322],"genre_scores_gemma":[0.9325889,0.00002408817,0.06647877,0.0006521113,0.000201101,0.000001358852,0.00002755237,0.000005303416,0.00002076761],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7156283,"threshold_uncertainty_score":0.8602952,"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."}}