Semantic Caching for Large Language Model Inference: A Systematic Literature Review — master corpus, screening decisions, and quality-appraisal data

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

This dataset contains the complete screening and quality-appraisal record for the systematic literature review "Semantic Caching for Large Language Model Inference: A Systematic Literature Review". It covers all 89 numbered records considered during the review: 66 included corpus papers, 18 excluded at full-text screening, and 5 background/methodological citations. The workbook has five sheets: Summary (headline counts and cluster breakdown), Included_Corpus (66 papers with cluster, synthesis fields, and four-dimension quality scores with tiers), Excluded_Records (18 full-text exclusions with reasons), Background_Citations (5 cited-but-not-screened works), and Meta_Analysis (the 18 papers with quantitatively comparable results). Each sheet carries a "Manuscript Key" column mapping rows to the paper's citation keys. Quality tiers: 27 High, 36 Moderate, 3 Low. See the included README for the full column guide.