{"id":"W7082255579","doi":"10.48448/25h5-c625","title":"Towards Multi-dimensional Evaluation of LLM Summarization across Domains and Languages","year":2025,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Automatic summarization; Benchmark (surveying); Annotation; Domain (mathematical analysis); Face (sociological concept); Multi-document summarization","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":[0.01102454,0.00208273,0.001075224,0.009198846,0.00109385,0.003782528,0.001631437,0.001533494,0.003084391],"category_scores_gemma":[0.05036561,0.0003209861,0.001027783,0.005852255,0.0007669857,0.00494125,0.004085962,0.001594654,0.002348558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001663994,"about_ca_system_score_gemma":0.001445244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00585317,"about_ca_topic_score_gemma":0.008816253,"domain_scores_codex":[0.9883648,0.006154766,0.001407421,0.001617682,0.002136431,0.0003188497],"domain_scores_gemma":[0.9714112,0.01376315,0.002296952,0.004706876,0.006935698,0.0008861088],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002271635,0.001107113,0.02963402,0.005626814,0.001033747,0.0004119376,0.002422979,0.05673297,0.02400408,0.009244922,0.2083019,0.6592078],"study_design_scores_gemma":[0.0007635155,0.001999579,0.04573342,0.001122149,0.0005844476,0.000650044,0.005494846,0.6688395,0.0708108,0.03561649,0.1680029,0.0003823442],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.4598198,0.01508534,0.3083091,0.004245281,0.001423524,0.002145073,0.1017878,0.07580037,0.03138372],"genre_scores_gemma":[0.4717343,0.001348843,0.2936371,0.0007930388,0.0003323764,0.001299529,0.2225442,0.002438335,0.005872351],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01102454,"threshold_uncertainty_score":0.05830401,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02793363362821578,"score_gpt":0.3372077479586524,"score_spread":0.3092741143304367,"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."}}