搜索结果：registry

RAMPART is a compile-time memory model and pure in-RAM block registry for LLM-based agents. Context assembly is a programmable runtime operation where content is compiled from a structured registry under explicit policy for ordering, inclusion, and eviction. Five composable primitives (promote, gate, write, evict, rollback) act on named addressable blocks before compilation at zero prompt-token cost. Provenance tags and non-evictable authorship flags implement a permissioned memory model with block-level ownership. Controlled probes with Qwen3-8B Q4 show that compile-time placement and the structural relationship between blocks and the task query affect task success, with the cliff falling at roughly the seventh block position when the task follows the registry and the twelfth when it precedes. Grouping the critical block with content-adjacent neighbours and promoting the group as a unit lifts task success by tens of percentage points at positions where single-block placement fails. Cross-model replication on Qwen2.5-7B, Llama-3.1-8B, Mistral-7B-v0.3, and Qwen3-14B shows the content-priming effect appears at the same absolute positions across families, with magnitude varying with m

Density functional theory (DFT) is widely used to model twisted bilayers, but the accuracy of the local stacking energetics underlying such models remains uncertain. Here, we benchmark the local-registry landscape of bilayer InSe using diffusion quantum Monte Carlo (DMC). DFT predicts that AB, AAr, and ABr stackings, which share the same interfacial Se registry, are nearly degenerate within 1.5 meV/f.u. and exhibit nearly indistinguishable DFT charge-density responses. DMC instead separates these stackings by 8(5) and 41(4) meV/f.u., while the energy difference between the most stable and least stable registries reaches 60(7) meV/f.u.. These large energy separations show that the stacking energetics are not determined by the interfacial atomic motif alone but depend on the full registry and its associated many-body electronic response. More broadly, these results show that DFT-based moiré models can substantially underestimate local stacking-energy corrugation, with direct consequences for predicted structural relaxation, domain formation, and electronic reconstruction in twisted layered materials.

Large Language Model (LLM) agents are increasingly extended at runtime via skill packages, structured natural-language instruction bundles loaded from a well-known directory. Community install tooling and registries exist, but two gaps persist: no public tool scores skill packages against Anthropic's published format specification, and no mechanism bundles related skills with the shared context they need to remain mutually coherent. We present Skilldex, a package manager and registry for agent skill packages addressing both gaps. The two novel contributions are: (1) compiler-style format conformance scoring against Anthropic's skill specification, producing line-level diagnostics on description specificity, frontmatter validity, and structural adherence; and (2) the skillset abstraction, a bundled collection of related skills with shared assets (vocabulary files, templates, reference documents) that enforce cross-skill behavioral coherence. Skilldex also provides supporting infrastructure: a three-tier hierarchical scope system, a human-in-the-loop agent suggestion loop, a metadata-only community registry, and a Model Context Protocol (MCP) server. The system is implemented as a Ty

Modernizing cancer registries with deep learning is opening new opportunities to automate labor-intensive tasks such as the coding of pathology reports. However, progress is constrained by the scarcity of report-level human-annotated training data. Cancer registries generate substantial volumes of expert-assigned labels as a routine product of their operations, but these exist at the patient level and are not linked to the individual pathology reports that informed them, limiting their direct use for training models. We develop an efficient framework for training deep learning classifiers by leveraging these operationally-generated labels without requiring per-report human annotation, demonstrated for tumor group classification at the BC Cancer Registry. We use Attention-Based Multiple Instance Learning (ABMIL) to recover the lost link between patient-level labels and the reports that informed them, leveraging the attention the model places on each report to distil a large, noisily-labeled corpus into a compact, high-quality per-report training dataset. A classifier fine-tuned on a distilled dataset achieved a macro F1 of 0.83, outperforming established baselines across most tumor

Supervised machine learning (ML) is used extensively in biology and deserves closer scrutiny. The DOME recommendations aim to enhance the validation and reproducibility of ML research by establishing standards for key aspects such as data handling and processing, optimization, evaluation, and model interpretability. The recommendations help to ensure that key details are reported transparently by providing a structured set of questions. Here, we introduce the DOME Registry (URL: registry.dome-ml.org), a database that allows scientists to manage and access comprehensive DOME-related information on published ML studies. The registry uses external resources like ORCID, APICURON and the Data Stewardship Wizard to streamline the annotation process and ensure comprehensive documentation. By assigning unique identifiers and DOME scores to publications, the registry fosters a standardized evaluation of ML methods. Future plans include continuing to grow the registry through community curation, improving the DOME score definition and encouraging publishers to adopt DOME standards, promoting transparency and reproducibility of ML in the life sciences.

The rise of generative AI (GenAI) multi-agent systems (MAS) necessitates standardized protocols enabling agents to discover and interact with external tools. However, these protocols introduce new security challenges, particularly; tool squatting; the deceptive registration or representation of tools. This paper analyzes tool squatting threats within the context of emerging interoperability standards, such as Model Context Protocol (MCP) or seamless communication between agents protocols. It introduces a comprehensive Tool Registry system designed to mitigate these risks. We propose a security-focused architecture featuring admin-controlled registration, centralized tool discovery, fine grained access policies enforced via dedicated Agent and Tool Registry services, a dynamic trust scoring mechanism based on tool versioning and known vulnerabilities, and just in time credential provisioning. Based on its design principles, the proposed registry framework aims to effectively prevent common tool squatting vectors while preserving the flexibility and power of multi-agent systems. This work addresses a critical security gap in the rapidly evolving GenAI ecosystem and provides a foundat

Public commercial registries are formally open, yet their practical analysis remains difficult because relevant facts are scattered across millions of records that combine structured metadata, multilingual legal notices, temporal events, and entity aliases. This paper presents a controlled, tool-mediated agentic GraphRAG architecture for auditable natural-language analysis of such registries. The proposed pipeline transforms publications from the Swiss Official Gazette of Commerce into a Neo4j knowledge graph comprising over five million nodes and 4.7 million relationships. It combines deterministic ingestion of structured registry fields, LLM-assisted extraction of latent actors from unstructured notices, and a deterministic identity-resolution layer. An analytical agent operates on this graph through intent routing, restricted graph tools, bounded reflection, and state-machine-guided response synthesis. We evaluate the system using a multi-tier protocol covering answer quality, retrieval behavior, entity resolution, and multi-turn conversational performance. The complete architecture is compared with dense, lexical, and hybrid flat-retrieval baselines and with controlled architec

Autonomous AI agents now operate across cloud, enterprise, and decentralized domains, creating demand for registry infrastructures that enable trustworthy discovery, capability negotiation, and identity assurance. We analyze five prominent approaches: (1) MCP Registry (centralized publication of mcp.json descriptors), (2) A2A Agent Cards (decentralized self-describing JSON capability manifests), (3) AGNTCY Agent Directory Service (IPFS Kademlia DHT content routing extended for semantic taxonomy-based content discovery, OCI artifact storage, and Sigstore-backed integrity), (4) Microsoft Entra Agent ID (enterprise SaaS directory with policy and zero-trust integration), and (5) NANDA Index AgentFacts (cryptographically verifiable, privacy-preserving fact model with credentialed assertions). Using four evaluation dimensions: security, authentication, scalability, and maintainability, we surface architectural trade-offs between centralized control, enterprise governance, and distributed resilience. We conclude with design recommendations for an emerging Internet of AI Agents requiring verifiable identity, adaptive discovery flows, and interoperable capability semantics.

LLM-based agents are rapidly proliferating, yet the infrastructure for discovering, evaluating, and governing them remains fragmented compared to mature ecosystems like software package registries (e.g., npm) and model hubs (e.g., Hugging Face). Existing efforts typically address naming, distribution, or protocol descriptors, but stop short of providing a registry layer that makes agents discoverable, comparable, and governable under automated reuse. We present AgentHub, a registry layer and accompanying research agenda for agent sharing that targets discovery and workflow integration, trust and security, openness and governance, ecosystem interoperability, lifecycle transparency, and capability clarity with evidence. We describe a reference prototype that implements a canonical manifest with publish-time validation, version-bound evidence records linked to auditable artifacts, and an append-only lifecycle event log whose states are respected by default in search and resolution. We also provide initial discovery results using an LLM-as-judge recommendation pipeline, showing how structured contracts and evidence improve intent-accurate retrieval beyond keyword-driven discovery. Agen

Differential privacy (DP) -- a principled approach to producing statistical data products with strong, mathematically provable privacy guarantees for the individuals in the underlying dataset -- has seen substantial adoption in practice over the past decade. Applying DP requires making several implementation decisions, each with significant impacts on data privacy and/or utility. Hence, to promote shared learning and accountability around DP deployments, Dwork, Kohli, and Mulligan (2019) proposed a public-facing repository ("registry") of DP deployments. The DP community has recently started to work toward realizing this vision. We contribute to this effort by (1) developing a holistic, hierarchical schema to describe any given DP deployment and (2) designing and implementing an interactive interface to act as a registry where practitioners can access information about past DP deployments. We (3) populate our interface with 21 real-world DP deployments and (4) conduct an exploratory user study with DP practitioners ($n=16$) to understand how they would use the registry, as well as what challenges and opportunities they foresee around its adoption. We find that participants were ent

In this article, we describe the Registry of Scientometric Data Sources (RSDS) and several scientometric data sources recorded in this open registry that could be of interest for scientometricians, institutional researchers, librarians, practitioners, policy makers, students and other stakeholders with an interest in scientometrics. This registry was created after carrying out a literature review and a technical evaluation of several data sources. Each data source is recorded with descriptive metadata fields and URLs to further information. This article describes the motivation behind the development of the registry, explains the features that are available on its public website (https://labs.tib.eu/rosi), and closes with a call for participation.

We introduce did:self, a Decentralized Identifier (DID) method that does not depend on any trusted registry for storing the corresponding DID documents. Information for authenticating a did:self subject can be disseminated using any means and without making any security assumption about the delivery method. did:self is lightweight, it allows controlled delegation, it offers increased security and privacy, and it can be used for identifying people, content, as well as IoT devices. Furthermore, DID documents in did:self can be implicit, allowing re-construction of DID documents based on other authentication material, such as JSON Web Tokens and X.509 certificates.

An aspect of interest in surveillance of diseases is whether the survival time distribution changes over time. By following data in health registries over time, this can be monitored, either in real time or retrospectively. With relevant risk factors registered, these can be taken into account in the monitoring as well. A challenge in monitoring survival times based on registry data is that the information related to cause of death might either be missing or uncertain. To quantify the burden of disease in such cases, relative survival methods can be used, where the total hazard is modelled as the population hazard plus the excess hazard due to the disease. We propose a CUSUM procedure for monitoring for changes in the survival time distribution in cases where use of excess hazard models is relevant. The CUSUM chart is based on a survival log-likelihood ratio and extends previously suggested methods for monitoring of time to event data to the excess hazard setting. The procedure takes into account changes in the population risk over time, as well as changes in the excess hazard which is explained by observed covariates. Properties, challenges and an application to cancer registry da

The Virtual Observatory Registry is a distributed directory of information systems and other resources relevant to astronomy. To make it useful, facilities to query that directory must be provided to humans and machines alike. This article reviews the development and status of such facilities, also considering the lessons learnt from about a decade of experience with Registry interfaces. After a brief outline of the history of the standards development, it describes the use of Registry interfaces in some popular clients as well as dedicated UIs for interrogating the Registry. It continues with a thorough discussion of the design of the two most recent Registry interface standards, RegTAP on the one hand and a full-text-based interface on the other hand. The article finally lays out some of the less obvious conventions that emerged in the interaction between providers of registry records and Registry users as well as remaining challenges and current developments.

We consider $Z_2$ gauge field theory coupled to "Higgs" matter fields invoking several copies of such matter, interacting entirely through the gauge fields, the $Z_2 \times Z_2 \times Z_2\cdots / Z_2$ and the $O(N) \times O(N) \times O(N) \cdots / Z_2$ families of theories. We discover that the Higgs phase of such theories is characterized by a hitherto unidentified "registry" order parameter. This is characterized by a gauge invariant $p = 2^{N_{\text{rep}}}/2$ Potts type symmetry where $N_{\text{rep}}$ is the number of matter copies. The meaning of this registry is that the different matter copies align their vectors locally in strictly parallel or anti-parallel fashion, even dealing with the continuous $O(2)$ symmetry. Supported by Monte-Carlo simulations, we identify the origin of this registry order in terms of the gauge interactions mediated by the fluxes ("visons") associated with the $Z_2$ gauge fields, indirectly imposing the discrete symmetry in the gauge invariant global symmetry controlled effective order parameter theory. In addition, it appears that our simulations reveal a hitherto unidentified "pseudo-universality" associated with the very similar form of the overal

The rising popularity of computational workflows is driven by the need for repetitive and scalable data processing, sharing of processing know-how, and transparent methods. As both combined records of analysis and descriptions of processing steps, workflows should be reproducible, reusable, adaptable, and available. Workflow sharing presents opportunities to reduce unnecessary reinvention, promote reuse, increase access to best practice analyses for non-experts, and increase productivity. In reality, workflows are scattered and difficult to find, in part due to the diversity of available workflow engines and ecosystems, and because workflow sharing is not yet part of research practice. WorkflowHub provides a unified registry for all computational workflows that links to community repositories, and supports both the workflow lifecycle and making workflows findable, accessible, interoperable, and reusable (FAIR). By interoperating with diverse platforms, services, and external registries, WorkflowHub adds value by supporting workflow sharing, explicitly assigning credit, enhancing FAIRness, and promoting workflows as scholarly artefacts. The registry has a global reach, with hundreds

We present DECORAIT; a decentralized registry through which content creators may assert their right to opt in or out of AI training as well as receive reward for their contributions. Generative AI (GenAI) enables images to be synthesized using AI models trained on vast amounts of data scraped from public sources. Model and content creators who may wish to share their work openly without sanctioning its use for training are thus presented with a data governance challenge. Further, establishing the provenance of GenAI training data is important to creatives to ensure fair recognition and reward for their such use. We report a prototype of DECORAIT, which explores hierarchical clustering and a combination of on/off-chain storage to create a scalable decentralized registry to trace the provenance of GenAI training data in order to determine training consent and reward creatives who contribute that data. DECORAIT combines distributed ledger technology (DLT) with visual fingerprinting, leveraging the emerging C2PA (Coalition for Content Provenance and Authenticity) standard to create a secure, open registry through which creatives may express consent and data ownership for GenAI.

The Cancer Registry of Norway (CRN) is a part of the Norwegian Institute of Public Health (NIPH) and is tasked with producing statistics on cancer among the Norwegian population. For this task, CRN develops, tests, and evolves a software system called Cancer Registration Support System (CaReSS). It is a complex socio-technical software system that interacts with many entities (e.g., hospitals, medical laboratories, and other patient registries) to achieve its task. For cost-effective testing of CaReSS, CRN has employed EvoMaster, an AI-based REST API testing tool combined with an integrated classical machine learning model. Within this context, we propose Qlinical to investigate the feasibility of using, inside EvoMaster, a Quantum Neural Network (QNN) classifier, i.e., a quantum machine learning model, instead of the existing classical machine learning model. Results indicate that Qlinical can achieve performance comparable to that of EvoClass. We further explore the effects of various QNN configurations on performance and offer recommendations for optimal QNN settings for future QNN developers.