Constraining the Commit Boundary: A DIO/ODI-Informed Authorization Guardrail for Agentic Entity Resolution

Ranked by how close their title and abstract are to this paper’s. Select some to read them together.

Closest papers

1. Close Another approach to the problem Not relevant

   Sovereign Assurance Boundary: Certificate-Bound Admission for Agentic Infrastructure

   Jun-Fei He, De-Ying Yu · 2026 · arXiv.org · preprint, not peer reviewed · cited 4 times · Not summarized yet

   Sovereign Assurance Boundary intercepts agent proposals and binds them to cryptographic execution contracts, while this paper gates persistent entity-identity changes using evidence and scope checks.

   Abstract

   Agentic infrastructure introduces a critical control-plane authorization problem: non-deterministic reasoning systems can propose high-stakes mutations to production resources, yet existing security mechanisms -- such as identity and access management (IAM), policy engines, consensus protocols, and audit logs -- either enforce static, context-unaware permissions or merely record actions post-execution. This paper introduces the Sovereign Assurance Boundary (SAB), a certificate-bound runtime admission layer for autonomous execution authority. SAB intercepts agent proposals at an assurance airlock, compiles them into typed execution contracts $C$, and binds these contracts to cryptographic evi…

2. Close Broader context Not relevant

   Partial Evidence Bench: Benchmarking Authorization-Limited Evidence in Agentic Systems

   Krti Tallam · 2026 · arXiv.org · preprint, not peer reviewed · cited 5 times · Not summarized yet

   Partial Evidence Bench measures answers that omit evidence beyond an authorization boundary, whereas this paper governs evidence eligibility for lasting entity-resolution changes.

   Abstract

   Enterprise agents increasingly operate inside scoped retrieval systems, delegated workflows, and policy-constrained evidence environments. In these settings, access control can be enforced correctly while the system still produces an answer that appears complete even though material evidence lies outside the caller's authorization boundary. This paper introduces Partial Evidence Bench, a deterministic benchmark for measuring that failure mode. The benchmark ships three scenario families -- due diligence, compliance audit, and security incident response -- with 72 tasks total, ACL-partitioned corpora, oracle complete answers, oracle authorized-view answers, oracle completeness judgments, and …

3. Close Same method, another problem Cited by this paper Not relevant

   Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents

   Igor Santos-Grueiro · 2026 · arXiv.org · preprint, not peer reviewed · cited 24 times · Not summarized yet

   Temporary Authority, Permanent Effects checks witness freshness and binding at commit time, as this paper checks evidence, scope, and versions before durable identity changes.

   Abstract

   LLM agents can commit durable effects from authority evidence that was valid earlier in execution: a DOM snapshot, approval epoch, version witness, branch token, or worker result. We study the commit boundary at which earlier authority evidence no longer authorizes a durable effect. We call this property commit-time authorization: a durable effect is authorized only if the witness that licensed its derived state remains fresh, causally prior, bound to the same effect, and eligible at commit time. We build a controlled-invalidation suite spanning browser, tool/API, and multi-agent workflows. The suite preserves the user goal and payload shape while invalidating the authority relation before d…

4. Close Groundwork for this paper Not relevant

   From Entity Resolution Anomalies to Reconstruction Failure Modes: A Taxonomic Note Following Minimum Viable Digital Identity Optimization (DIO)

   Daniel Beránek · 2026 · Zenodo (CERN European Organization for Nuclear Research) preprint · AI summary available

   The taxonomic note defines reconstruction failure distinctions that this paper maps to identity-preserving constraints for entity-resolution commits.

   In short

   The note organizes reconstruction failure modes into four diagnostic domains and distinguishes realized failures from susceptibility to destabilization.

5. Close Broader context Not relevant

   Authorization Propagation in Multi-Agent AI Systems: Identity Governance as Infrastructure

   Krti Tallam · 2026 · arXiv.org · preprint, not peer reviewed · cited 11 times · Not summarized yet

   Authorization Propagation studies invariants across retrieval, delegation, and synthesis, while this paper applies authorization controls to evidence and entity-resolution commits.

   Abstract

   The security discussion around agentic AI focuses heavily on prompt injection. This paper argues that multi-agent systems also create a distinct authorization problem: maintaining authorization invariants as non-human principals retrieve data, delegate tasks, and synthesize results across changing boundaries. We call this problem authorization propagation. It is not reducible to prompt injection and is not fully addressed by classical access-control models such as RBAC, ABAC, or ReBAC. The paper formalizes authorization propagation as a workflow-level property, identifies three sub-problems (transitive delegation, aggregation inference, and temporal validity), and derives seven structural re…

6. Close Broader context Not relevant

   Overlaying Governance: A Compositional Authorization Framework for Delegation and Scope in Agentic AI

   Amjad Ibrahim, Yong Li · 2026 · arXiv.org · preprint, not peer reviewed · cited 4 times · Not summarized yet

   Overlaying Governance formalizes delegation and scope in agentic systems, while this paper uses scope binding to constrain lasting identity changes.

   Abstract

   As AI systems evolve from passive models into autonomous active agents capable of initiating actions, collaborating, and delegating tasks, the traditional boundaries of software systems blur. Traditional authorization and delegation frameworks, built around fixed principals, explicit requests, and static scopes, are insufficient to govern agentic systems. Agentic AI demands richer authorization semantics: agents must inherit and delegate permissions, act under time-limited authority, and coordinate through shared protocols. Existing Identity and Access Management (IAM) systems fail to fully capture this notion of agency, lacking mechanisms for recursive delegation, contextual boundaries, and…

7. Close Broader context Not relevant

   Compliance-as-Code for AI-Driven Identity Systems: Clause-to-Control Traceability and Machine-Readable Evidence

   L. Nweke, P. Yeng · 2026 · IEEE Access · Not summarized yet

   Compliance-as-Code traces regulatory clauses to controls and evidence in AI identity workflows, while this paper governs evidence required to authorize entity-resolution mutations.

   Abstract

   Artificial intelligence (AI)-driven identity (ID) systems (document onboarding, wallet-based credential presentation, fraud/risk scoring) increasingly face regulatory obligations requiring demonstrable accountability, traceability, and technical documentation. Yet current compliance practice remains predominantly document-centric and manual, making it difficult to keep evidence synchronized with rapidly evolving systems and models. We present a compliance-as-code approach for AI-driven ID workflows that: 1) maintains clause-to-control traceability under policy/configuration evolution; 2) treats evidence completeness as an enforceable property via fixed monitoring-window semantics (silence is…

8. Close Broader context Not relevant

   Digital Identity for Agentic Systems: Toward a Portable Authorization Standard for Autonomous Agents

   Partha Madhira · 2026 · arXiv.org · preprint, not peer reviewed · Not summarized yet

   Digital Identity for Agentic Systems proposes portable agent authorization payloads, whereas this paper uses identity-governed constraints to authorize entity-resolution changes.

   Abstract

   Enterprise AI is shifting from copilots to autonomous agents capable of executing workflows, negotiating outcomes, and making decisions with limited human oversight. As these systems extend across organizational boundaries, identity alone is insufficient: an agent's authority must also be explicit, constrained, auditable, revocable, and consistently interpretable by independent receivers. This paper analyzes representative enterprise use cases in insurance claims processing and supply chain integrity to surface structural gaps in existing identity and access models. It proposes a portable authorization model for autonomous agents based on issuer-authored authorization payloads, typed constra…

Prior work it builds on

1. Related Broader context Not relevant

   From Intent to Execution Grant: An Execution-Boundary Conformance Profile for High-Risk AI Actions

   Meng-Rong Wu, Lin Wang, Yong Zhang et al. · 2026 · cited 2 times · Not summarized yet

   EBL-Core binds a materialized AI action to execution authority, while this paper binds evidence, scope, and versions to an entity-resolution commit.

   Abstract

   AI agents increasingly propose actions with external consequences, including financial transfers, infrastructure changes, software deployments, disclosures, and physical actuation. Authorization engines, policy languages, runtime monitors, provenance mechanisms, and agent guardrails provide important foundations, but do not necessarily define a common semantic contract for the final transition from a particular candidate action to execution authority. We specify EBL-Core, an execution-boundary conformance profile for deciding whether one canonical, fully materialized AI-generated candidate may receive action-scoped execution authority under explicit conditions. It binds a structured intent o…

2. Related Same question Not relevant

   AgenticER: the next frontier in Entity Resolution

   George Papadakis, Panos Korovesis, Manolis Koubarakis et al. · 2026 · arXiv.org · preprint, not peer reviewed · cited 1 time · Not summarized yet

   AgenticER studies iterative, context-dependent entity resolution, while this paper addresses when evidence from such reasoning may authorize persistent identity changes.

   Abstract

   Entity Resolution (ER) is a fundamental problem in data management, playing a critical role in tasks like data cleaning and knowledge graph construction. The existing ER approaches range from traditional rule-based to deep learning techniques and LLM-based methods, but typically operate under a ``passive paradigm'', as duplicates are detected through static, one-shot similarity computations. Such approaches fail to capture the inherently uncertain and context-dependent nature of real-world ER tasks, especially in data lakes with streaming content in heterogeneous formats such as CSV files, JSON files, RDF dumps, and free text. In such settings, resolving ambiguity often requires iterative ev…

3. Related Broader context Not relevant

   CONTINUITY: Security-Context Contracts for Composable LLM Agent Controls

   Chris Zheng, Yang Geng · 2026 · cited 4 times · Not summarized yet

   CONTINUITY preserves security context across agent components, while this paper specifies checks that preserve evidence eligibility and scope at the entity-resolution commit boundary.

   Abstract

   LLM agent systems increasingly combine provenance tracking, authorization, policy enforcement, protocol adapters, and execution controls. However, individually correct security mechanisms do not necessarily compose into an end-to-end secure system: security-critical context may be dropped, widened, rebound, or reinterpreted as actions cross component boundaries. We identify this failure mode as security-context discontinuity and introduce CONTINUITY, a framework for verifiable composition of agent security controls. CONTINUITY models each component with an assume-guarantee contract and carries authenticated security context across transitions using signed root grants, provenance commitments,…

4. Related Broader context Not relevant

   From Business Events to Auditable Decisions: Ontology-Governed Graph Simulation for Enterprise AI

   Hongyin Zhu, Jinming Liang, Mengjun Hou et al. · 2026 · arXiv.org · preprint, not peer reviewed · cited 1 time · Not summarized yet

   LOM-action uses ontology-governed graph simulation for auditable enterprise decisions, while this paper uses domain-governed constraints to control identity-changing graph mutations.

   Abstract

   Existing LLM-based agent systems share a common architectural failure: they answer from the unrestricted knowledge space without first simulating how active business scenarios reshape that space for the event at hand -- producing decisions that are fluent but ungrounded and carrying no audit trail. We present LOM-action, which equips enterprise AI with \emph{event-driven ontology simulation}: business events trigger scenario conditions encoded in the enterprise ontology~(EO), which drive deterministic graph mutations in an isolated sandbox, evolving a working copy of the subgraph into the scenario-valid simulation graph $G_{\text{sim}}$; all decisions are derived exclusively from this evolve…

5. Related Review Used in depth by this paper Not relevant

   An Overview of End-to-End Entity Resolution for Big Data

   V. Christophides, Vasilis Efthymiou, Themis Palpanas et al. · 2020 · ACM Computing Surveys · cited 300 times · Not summarized yet

   The overview surveys end-to-end entity-resolution concepts and strategies for big data, whereas this paper specifies an authorization boundary for agentic entity resolution.

   Abstract

   One of the most critical tasks for improving data quality and increasing the reliability of data analytics is Entity Resolution (ER), which aims to identify different descriptions that refer to the same real-world entity. Despite several decades of research, ER remains a challenging problem. In this survey, we highlight the novel aspects of resolving Big Data entities when we should satisfy more than one of the Big Data characteristics simultaneously (i.e., Volume and Velocity with Variety). We present the basic concepts, processing steps, and execution strategies that have been proposed by database, semantic Web, and machine learning communities in order to cope with the loose structurednes…