{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001684954,0.0001564508,0.0001880508,0.000192483,0.0001503425,0.00008490424,0.0007090149,0.0001489892,0.0001084483],"category_scores_gemma":[0.0004906602,0.0001369494,0.00002555784,0.0006438711,0.0004914155,0.0001473273,0.0006002221,0.0001124407,0.00000494957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004948947,"about_ca_system_score_gemma":0.0007708591,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002407102,"about_ca_topic_score_gemma":0.0001488797,"domain_scores_codex":[0.9981516,0.00005747618,0.0002029649,0.0005429016,0.0007964864,0.0002485469],"domain_scores_gemma":[0.9987518,0.00004427686,0.0002108088,0.000444104,0.0004883719,0.0000606769],"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":[0.0000144475,0.0009662363,0.002372081,0.0009271306,0.000181081,0.00002763571,0.002630432,0.009096012,0.02942025,0.1826753,0.04487039,0.726819],"study_design_scores_gemma":[0.001510852,0.0000881392,0.004484125,0.0005357165,0.00006489368,0.0000184722,0.0005099578,0.9519203,0.01026637,0.006991569,0.02296313,0.0006465048],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.002205014,0.001771208,0.3500588,0.002568924,0.0008497337,0.0008426165,0.0001083395,0.0003799349,0.6412154],"genre_scores_gemma":[0.4918193,0.00008962942,0.222994,0.0004661283,0.0002252798,0.00003472553,0.0001489478,0.00003359673,0.2841884],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.9428242,"threshold_uncertainty_score":0.5584633,"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."}}