The paper proposes a five‑stage AI‑driven framework to autonomously harvest and enrich cultural heritage data for Indonesia’s Open Digital Library of Culture. It addresses coverage, integrity, and completeness gaps by combining focused crawling, multilingual extraction, vector encoding, agentic decision‑making, and idempotent publication, while preserving key human roles such as curator, approver, auditor, and guardian of meaning. The methodology includes formal economic, statistical, and ethical safeguards to ensure accurate, non‑overwriting, and culturally sensitive data integration.
arXiv:2607. 03233v1 Announce Type: cross Abstract: The rapid growth of publicly available digital information has rendered manual open-source intelligence (OSINT) analysis insufficient for modern intelligence, cybersecurity, and cyber investigation.
The paper introduces data stories as narrative documents that combine explanatory text, images, and executable SPARQL queries with visualized results to make cultural‑heritage knowledge graphs more accessible. It describes how these stories guide users through unfamiliar graphs, create reproducible narratives, and uncover hidden data‑quality issues. The authors present LODEON, an authoring platform with Sparnatural and AI‑assisted tools, and report early positive feedback from seminars and workshops.
The study examines how generative AI has reshaped the public web in under five years, using over 5 million crawlable pages. It finds that AI-generated text has risen sharply but unevenly, with higher prevalence on English-language and .com sites, lower on .gov and .edu, and varying by a page’s centrality in the web graph. The authors employ multiple detection tools and a Bayesian hierarchical model to estimate prevalence while accounting for detector errors.
arXiv:2608.23263v1 Announce Type: new Abstract: The FAIR Digital Object (FDO) framework mandates that metadata attribute values be expressed as persistent identifiers (PIDs) wherever possible, to pro...
The FAIR Digital Object (FDO) framework mandates that metadata attribute values be expressed as persistent identifiers (PIDs) wherever possible, to produce a fully machine-actionable graph in which ev...
INDRA is a research platform that integrates multiple archival collections—such as UCSF’s Industry Documents Library, Columbia and CUNY’s ToxicDocs, and Stanford’s SRITA—into a single, LLM‑readable corpus. It employs three safeguards: a closed evidentiary sandbox, real‑time provenance tagging, and a deterministic system‑level protocol to ensure that model outputs are clearly distinguished from archival evidence and from the model’s own inferences. The platform enables large‑language‑model‑powered investigations across these archives while keeping the conditions of knowledge production transparent and auditable.
The paper introduces a production-ready content‑extraction system tailored for generative AI workloads, addressing the heterogeneity of enterprise data formats such as PDFs, spreadsheets, and scanned documents. It features selective OCR routing, a scarcity‑first curation engine with a reference‑based extraction scorer, a deterministic structure‑aware chunker, and a read‑only retrieval evaluator that generates grounded questions and reports metrics like Hit@k and MRR. On a 180‑document corpus, the system achieves high accuracy (97.4/100 character score, 0.13% error rate) and strong retrieval performance (Hit@1 68.6%, Hit@10 92.8%, MRR 0.77).
In less than five years, generative artificial intelligence (AI) has dramatically reshaped the public-facing web. Using a sample of more than 5 million crawlable webpages, we demonstrate that the shar...
arXiv:2606. 13669v1 Announce Type: new Abstract: Current LLM-based research agents have advanced through agent orchestration, yet largely overlook scientific knowledge orchestration.
The paper presents a knowledge layer that reorganizes enterprise Retrieval-Augmented Generation (RAG) for multi‑agent systems by placing an ontology at the artifact level rather than on extracted entities. Using a seven‑agent reverse‑engineering pipeline, the authors processed 241 repositories across 18 services to generate thousands of artifacts that capture scope, journeys, rules, and acceptance criteria, each tagged with provenance metadata. The resulting self‑describing catalog, sparse metadata registry, and navigation hypergraph enable queries to resolve to artifact identifiers, thereby structurally disambiguating near‑identical rules and improving retrieval accuracy. The system was built in under a week and helped root‑cause over 100 production defects and attribute 35 release regressions to specific rules and services.
arXiv:2511.18354v2 Announce Type: replace-cross Abstract: AI agents, not humans, are becoming the web's primary consumers, yet the web still ships content structured for human browsing, with no nativ...
arXiv:2610.07132v1 Announce Type: cross Abstract: Croissant has emerged as a standard for machine-readable dataset metadata, yet populating its fields remains labor-intensive and requires careful rea...