data lifecycle management

This work addresses the challenge of knowledge evolution in traditional retrieval-augmented generation (RAG), which often retrieves outdated facts. The authors propose MemStrata, a temporally aware retrieval memory system that introduces, for the first time, a dual-temporal ledger mechanism. This mechanism automatically deprecates superseded facts by applying deterministic replacement rules to (subject, predicate, object) triples, eliminating the need for similarity thresholds or large language model intervention. MemStrata maintains strong static knowledge recall while significantly improving temporal accuracy. Experimental results show that on six local benchmarks, MemStrata matches RAG in static performance, achieves 0.95–1.00 accuracy on evolving knowledge (compared to RAG’s 0.20–0.47), reduces outdated errors to nearly 0%, and incurs only 2.1 seconds of retrieval latency.

In the era of large language models, traditional record-centric data engineering struggles to meet the demand for organizational knowledge as executable infrastructure. This work proposes a novel paradigm—knowledge architecture—that systematically reimagines core data engineering mechanisms by upgrading ETL, data lineage, and catalogs into knowledge ingestion, change detection, provenance, and knowledge catalogs. It introduces knowledge views and a three-tier layered model (raw–refined–operational) to structure knowledge effectively. By integrating emerging standards such as LLM Wiki and Open Knowledge Format (OKF), this study formally defines knowledge architecture for the first time and establishes a theoretical framework that supports knowledge representation, governance, and operational delivery, enabling direct invocation of organizational knowledge by humans, agents, workflows, and models alike.

Existing data discovery methods largely overlook the temporal dynamics of data relationships, particularly hindering timeliness-aware retrieval when explicit temporal metadata is absent. To address this, we propose “temporal-effective data discovery”—a novel paradigm introducing the first time-integrated data discovery system. Its core comprises four techniques: version discovery, temporal lineage inference, change-log synthesis, and time-aware querying. Crucially, the system models semantic evolution of data over time without relying on original timestamps, enabling dynamic lineage tracing and version-level precise retrieval. Experimental evaluation on enterprise and public data lakes demonstrates significant improvements in accuracy and practicality for timeliness-sensitive queries. Our work establishes a new research direction in data discovery centered on temporal evolution, advancing both theoretical foundations and real-world applicability.

This study addresses the low accuracy of large language models (LLMs) in FAIR-compliance validation of biosample metadata. We propose a structured-knowledge-guided prompting method, integrating the CEDAR template repository, domain-specific data dictionaries, and GPT-4 to construct a metadata standards-conformance verification framework—demonstrated on human lung cancer biosamples. Experimental results show that incorporating structured knowledge significantly improves field-level standards compliance from 79% to 97% (p < 0.01), providing the first empirical evidence that structured knowledge bases can overcome performance bottlenecks inherent to purely text-based LLM prompting in metadata governance. Our approach establishes a novel paradigm for automated, high-accuracy, and interpretable FAIR metadata quality control, enabling scalable, standards-aware curation of biomedical metadata.

This paper addresses two critical gaps in the evolution of the Semantic Web: (1) the theoretical lag behind practical applications, and (2) insufficient integration of trustworthiness mechanisms with AI. To bridge these gaps, we propose a unified analytical framework that synergistically integrates classical semantic technologies with modern AI. Methodologically, we extend the canonical “layered cake” model into a novel three-dimensional paradigm encompassing trustworthy computing, industrial validation, and LLM–KG co-adaptation—systematically unifying RDF/OWL representation, rule-based reasoning, distributed SPARQL query processing, knowledge graph embedding, graph neural networks, and LLM–KG alignment techniques. Our contributions include: (1) a comprehensive technology landscape charting 50 years of Semantic Web development; (2) a clarified integration roadmap for knowledge graphs and AI—particularly large language models; and (3) theoretical foundations and practical guidelines for building next-generation semantic infrastructure that is trustworthy, interpretable, and adaptive.

Current AI systems rely heavily on manual auditing and documentation, which hinders scalable governance for automated services. This work proposes Ontological Knowledge Blocks (OKBs), a novel framework that formalizes regulatory obligations as quintuples comprising ontologies, SHACL rules, evidence requirements, and provenance links. By leveraging RDF/OWL modeling, PROV-O for provenance tracking, and an intermediate representation–driven deterministic compiler, the approach enables dynamic switching of governance configurations without modifying service code. Evaluation in an AI-assisted HPC scheduling scenario demonstrates that compliance checks are configuration-sensitive, violations accumulate strictly additively, SHACL validation incurs only 12.6–100.3 milliseconds of latency, and the Combined configuration provides the most comprehensive coverage.

Existing RDF systems lack standardized message boundaries in event-driven and streaming contexts, resulting in poor interoperability and inefficient processing. This work proposes the concept of “RDF Messages,” formally defining, for the first time, a message structure with RDF datasets as atomic units and explicitly delineating message boundaries to support streaming, storage, and reproducible replay. Built upon W3C Semantic Web standards, the approach introduces a unified encapsulation mechanism that operates across serialization and transport layers, complemented by configuration profiles that describe message structure and processing policies. The proposed framework effectively enables incremental consumption in scenarios such as IoT observations and SPARQL CONSTRUCT results, laying the foundation for RDF message streams and logs while advancing related W3C standardization efforts.

Current large language model agents lack a persistent memory mechanism that is maintainable, updatable, and capable of providing evidence across sessions. This work proposes a topic-document-based textual persistent memory architecture that organizes memories into structured thematic units, temporarily buffers new observations, and periodically integrates them to support factual revision while preserving metadata. Additionally, it introduces an LLM-driven iterative tool-calling mechanism for precise retrieval. The approach significantly enhances the coherence, updatability, and retrieval effectiveness of long-term memory, achieving a 64.7% overall score on MemoryAgentBench. Ablation studies confirm the complementary benefits of maintaining thematic structure and performing iterative evidence verification.

This study addresses the fragmentation of research software and its associated scholarly resources—such as publications and datasets—across disparate platforms, which hinders reproducibility and cross-domain analysis due to a lack of unified semantic links. To bridge this gap, the authors construct a large-scale RDF knowledge graph comprising 81 million triples, integrating approximately 200,000 GitHub repositories with external academic knowledge graphs including SemOpenAlex, LPWC, and MLSea-KG. This integration enables unified semantic modeling of software alongside scholarly entities such as authors, papers, and datasets. The resulting knowledge graph supports cross-platform provenance tracing and complex semantic queries, significantly enhancing the capacity to assess software reproducibility and analyze its long-term sustainability within the scientific ecosystem.

Databases continuously evolve through operations such as schema changes, version updates, and data transformations; however, existing approaches typically address these functionalities in isolation, lacking a unified abstraction. This work proposes the first integrated model that unifies continuous schema evolution, version management, and data transformation within a single framework. Built upon general-purpose computational primitives, the model supports operation provenance, conditional update propagation, and change alerts, while employing a declarative mechanism to manage the co-evolution of dependent artifacts—including views and machine learning models. A prototype system implements this framework using an enhanced, parameterized Prolly Tree—a Merkle tree–inspired data structure—to construct a relational-like engine. Experimental evaluation demonstrates that the proposed approach is both feasible and offers tunable performance across diverse evolution scenarios.