{"id":"W7135620829","doi":"","title":"University of Amsterdam at the CLEF 2025 Eloquent Track:Evaluating the Influence of Stylistic Prompt Variations on Semantic Interpretation","year":2025,"lang":"en","type":"article","venue":"UvA-DARE (University of Amsterdam)","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Universiteit van Amsterdam; Canadian Institute of Steel Construction","keywords":"Clef; Robustness (evolution); Language understanding; Consistency (knowledge bases); Variation (astronomy); Semantic interpretation; Semantic similarity; Focus (optics)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.01642265,0.0008657174,0.0008373456,0.0006960233,0.001196934,0.003463543,0.001183575,0.002158526,0.01133353],"category_scores_gemma":[0.08518566,0.0004058586,0.0004948574,0.0006398576,0.0007624878,0.002325846,0.002458052,0.00192176,0.004496922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00218723,"about_ca_system_score_gemma":0.001609307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007215466,"about_ca_topic_score_gemma":0.006564042,"domain_scores_codex":[0.9809898,0.01356155,0.00057349,0.002110555,0.002282145,0.0004825621],"domain_scores_gemma":[0.9141201,0.07113706,0.001846828,0.004761375,0.006191932,0.001942652],"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":[0.01412055,0.00396595,0.07938292,0.003920818,0.0005728709,0.002644451,0.04697533,0.0545146,0.1007698,0.01446448,0.2701425,0.4085257],"study_design_scores_gemma":[0.004412466,0.007170361,0.1088121,0.0007083003,0.0004425423,0.002115929,0.02366488,0.2854646,0.09652697,0.02093208,0.4485644,0.001185554],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8897936,0.0008676604,0.04413006,0.003358431,0.0007522324,0.001060374,0.01127161,0.01184613,0.03691996],"genre_scores_gemma":[0.9439042,0.0001216344,0.03319746,0.0007225484,0.0001558092,0.0007676202,0.01222246,0.001452458,0.007455753],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01642265,"threshold_uncertainty_score":0.08685237,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01889684662323244,"score_gpt":0.2522827793762439,"score_spread":0.2333859327530114,"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."}}