{"id":"W4402464111","doi":"10.11159/cist24.162","title":"A BoW-BoC Indexing Method to Enhance Business-Related Document Representation and Retrieval","year":2024,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Search engine indexing; Information retrieval; Computer science; Representation (politics); Natural language processing","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001701238,0.001038363,0.001527922,0.008844562,0.001141679,0.002169533,0.001412361,0.001170175,0.004963116],"category_scores_gemma":[0.005565202,0.0003953235,0.001213553,0.01158493,0.0006089099,0.003425472,0.002024957,0.001586117,0.005523683],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001085039,"about_ca_system_score_gemma":0.00263315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006155558,"about_ca_topic_score_gemma":0.007971194,"domain_scores_codex":[0.9978938,0.000258822,0.0002097168,0.0003736545,0.001059427,0.0002045919],"domain_scores_gemma":[0.998111,0.0003231573,0.0001419419,0.0002837532,0.001042403,0.00009771808],"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":[0.000158925,0.000225402,0.0007332724,0.0003081259,0.00006327325,0.00009124295,0.0001751232,0.004332182,0.04767305,0.010888,0.02382439,0.911527],"study_design_scores_gemma":[0.0001749537,0.0006777637,0.006022521,0.0001667777,0.00028488,0.002127357,0.0004647663,0.7356345,0.09491943,0.02515115,0.1340562,0.0003196943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01164739,0.002174232,0.9755585,0.0003287028,0.0004541458,0.0004900415,0.0008156464,0.004600132,0.003931208],"genre_scores_gemma":[0.07700071,0.001453061,0.9081693,0.000326304,0.0004232749,0.000572204,0.003506652,0.0003759243,0.008172727],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008844562,"threshold_uncertainty_score":0.01660335,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006808312459740094,"score_gpt":0.2619668309442504,"score_spread":0.2551585184845103,"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."}}