{"slug": "beyond-similarity-grounded-agentic-extraction-and-expert-adjudicated-evaluation", "title": "Beyond Similarity: Grounded Agentic Extraction and Expert-Adjudicated Evaluation of Intertextuality in Classical Chinese Histories", "summary": "Researchers from an unspecified institution introduced an agentic extraction method using large language models to identify and characterize intertextual reuse in classical Chinese histories, validated against an expert-adjudicated benchmark of 2,533 pairs from the Analects and Book of Han, with precision ranging from 56% to 93% across twelve LLMs. Scaling to the full Twenty-Four Histories (65,380 comparisons, 5,766 pairs) revealed that while aggregate citation composition remained stable over eighteen centuries, literal quotation declined, consistent with cultural-attraction theory. The study releases its extraction protocol and benchmark.", "body_md": "arXiv:2607.27595v1 Announce Type: new\nAbstract: Computational approaches to intertextuality have advanced from string matching to neural retrieval, yet their outputs, similarity scores and parallel-passage lists, identify where texts reuse one another without characterizing how or why. We recast fine-grained intertextuality extraction as an agentic task in which a large language model (LLM) reads two text units in full and, through a constrained tool interface, must ground each proposed reuse in exact character spans on both sides and label it under a five-dimension typology of reuse (form, aspect, source-marking, function, stance). We validate the approach on an exhaustive comparison of the Analects with the Book of Han, where three domain experts adjudicate a pooled multi-model candidate set into a benchmark of 2,533 intertextual pairs. Against this standard we study twelve LLMs, reporting precision (56%-93%), a 51$\\times$ cost spread at comparable quality, and how well their confidence is calibrated. Expert agreement traces a reliability gradient: dimensions legible on the textual surface are annotated consistently, while those requiring inference of intent are contested, delimiting the claims such annotation supports. Scaling the validated extractor to the full Twenty-Four Histories (65,380 comparisons, 5,766 pairs) recovers corpus-level structure a similarity score cannot express. The interpretive composition of citation shows no systematic change across eighteen centuries, yet the same passage is quoted less and less literally. Stability in the aggregate with drift in the individual case is what a cultural-attraction account expects. We release the extraction protocol and the expert-adjudicated benchmark.", "url": "https://wpnews.pro/news/beyond-similarity-grounded-agentic-extraction-and-expert-adjudicated-evaluation", "canonical_source": "https://www.machinebrief.com/news/beyond-similarity-grounded-agentic-extraction-and-expert-adj-0l9m", "published_at": "2026-07-31 04:00:00+00:00", "updated_at": "2026-07-31 04:37:07.098375+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-agents", "ai-research"], "entities": ["Analects", "Book of Han", "Twenty-Four Histories", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/beyond-similarity-grounded-agentic-extraction-and-expert-adjudicated-evaluation", "markdown": "https://wpnews.pro/news/beyond-similarity-grounded-agentic-extraction-and-expert-adjudicated-evaluation.md", "text": "https://wpnews.pro/news/beyond-similarity-grounded-agentic-extraction-and-expert-adjudicated-evaluation.txt", "jsonld": "https://wpnews.pro/news/beyond-similarity-grounded-agentic-extraction-and-expert-adjudicated-evaluation.jsonld"}}