{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009401498,0.0001487598,0.0002340823,0.0004814665,0.00017058,0.001088387,0.0005310695,0.00003098739,1.80593e-7],"category_scores_gemma":[0.00008774839,0.0001046555,0.00002848865,0.003110242,0.00007205542,0.0005245663,0.0004038602,0.0001790034,5.353331e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003669255,"about_ca_system_score_gemma":0.00003572877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003202606,"about_ca_topic_score_gemma":3.423841e-7,"domain_scores_codex":[0.998416,0.00001134748,0.000269004,0.0006325362,0.0004097647,0.0002613165],"domain_scores_gemma":[0.9993326,0.0001525933,0.00007385548,0.000150554,0.0001546691,0.0001357325],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000473773,0.00006959136,0.001658714,0.001014374,0.0002243722,0.00002101292,0.00241323,0.01760507,0.0884042,0.5921678,0.001663147,0.2947111],"study_design_scores_gemma":[0.00006630534,0.00006889486,0.001764905,0.0006171857,0.00001467513,0.00005945035,0.000006868773,0.9896325,0.006582757,0.000147919,0.0008858365,0.0001526951],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5790942,0.003262813,0.4090599,0.003983947,0.003166771,0.0006121223,0.000003176966,0.0004527942,0.0003643206],"genre_scores_gemma":[0.9884412,0.0000322607,0.01083601,0.00004629149,0.00007573244,0.000007761817,1.150677e-7,0.000006910302,0.0005537758],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9720274,"threshold_uncertainty_score":0.9999486,"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."}}