{"id":"W4405767409","doi":"10.48550/arxiv.2412.17075","title":"Iterative NLP Query Refinement for Enhancing Domain-Specific Information Retrieval: A Case Study in Career Services","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Humber Polytechnic","funders":"","keywords":"Computer science; Information retrieval; Domain (mathematical analysis); Query expansion; Natural language processing; Artificial intelligence; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009340501,0.001117358,0.00133618,0.002567591,0.001463449,0.002074972,0.002033748,0.002228218,0.002593144],"category_scores_gemma":[0.02695994,0.0003559137,0.001054586,0.004019741,0.001221699,0.004044449,0.001777786,0.001760004,0.002398666],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001254176,"about_ca_system_score_gemma":0.002039469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01010319,"about_ca_topic_score_gemma":0.01172147,"domain_scores_codex":[0.9906582,0.005979311,0.0006695751,0.0006974016,0.001661852,0.0003336433],"domain_scores_gemma":[0.9678566,0.02560196,0.0006172218,0.002212512,0.003180871,0.0005308294],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001359679,0.002731826,0.01266478,0.00614214,0.000240256,0.004669215,0.01800518,0.02720793,0.1224179,0.007826438,0.03201655,0.7647182],"study_design_scores_gemma":[0.0009403616,0.003212355,0.02582761,0.0004778666,0.0004829871,0.01011192,0.0223515,0.3910493,0.284804,0.01784747,0.2422532,0.0006413709],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5029365,0.003925047,0.4595826,0.004768377,0.0001731041,0.002065437,0.002354689,0.01439335,0.009801039],"genre_scores_gemma":[0.3560458,0.001244028,0.631679,0.0008776711,0.0001145955,0.0004455779,0.004050442,0.0008308629,0.004711998],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01010319,"threshold_uncertainty_score":0.04939783,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07543960327363322,"score_gpt":0.2191019969790739,"score_spread":0.1436623937054407,"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."}}