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

Daniel Beránek

doi:10.5281/zenodo.23269322

AI summary · DOI: 10.5281/zenodo.23269322 · Decision Sciences

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

Daniel Beránek

Original paper Published on 09 Oct. 2026 Zenodo (CERN European Organization for Nuclear Research) preprint License: CC BY

How to read this summary? Illustrated guide

The essentials

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

Based on the abstract only: check the details in the original paper.

Question

How can reconstruction failures in Digital Identity Optimization be classified with greater analytical precision? How should the taxonomy distinguish realized failures, Identity Collapse, and robustness-related properties?

Method

The note proposes a non-exclusive, multi-level taxonomy with four domains: Referential Reconstruction Failures, Semantic Coherence Failures, Temporal Reconstruction Failures, and Contextual Adequacy Failures. It assigns named anomalies to these domains, retains Identity Collapse as a phenomenon-level concept, and treats Semantic Vulnerability as a robustness-related property with Semantic Robustness as its counterpart.

Findings

Result The taxonomy separates Reconstruction Failure Modes into four analytical domains.
See the passage in the paper
The taxonomy distinguishes four analytical domains: Referential Reconstruction Failures, Semantic Coherence Failures, Temporal Reconstruction Failures, and Contextual Adequacy Failures.
Result Entity Substitution, Merge Failure, Split Failure, and Entity Omission are classified as referential failures.
See the passage in the paper
Referential failures include Entity Substitution, Merge Failure, Split Failure, and Entity Omission.
Result Semantic Fragmentation is assigned to semantic coherence, while Temporal Discontinuity and Temporal Misalignment are assigned to temporal reconstruction.
See the passage in the paper
Semantic Fragmentation is treated as a Semantic Coherence Failure; Temporal Discontinuity and Temporal Misalignment as Temporal Reconstruction Failures; and Contextual Displacement as a Contextual Adequacy Failure.
Authors’ interpretation Identity Collapse remains a phenomenon-level concept rather than a category in the failure taxonomy.
See the passage in the paper
The note preserves Identity Collapse as a phenomenon-level concept rather than redefining it as a branch of the failure taxonomy.
Authors’ interpretation Semantic Vulnerability is treated as a robustness-related property, not as a realized failure, and its conceptual counterpart is Semantic Robustness.
See the passage in the paper
It also removes Semantic Vulnerability from the hierarchy of realized failures and treats it instead as a robustness-related property, whose direct conceptual counterpart is Semantic Robustness.

Limitations

The note presents a taxonomy intended to support future empirical work, but the supplied abstract reports no empirical validation.

Why it matters

The authors argue that the taxonomy increases analytical resolution by separating realized reconstruction failures from susceptibility to destabilization. It is intended to provide a clearer basis for future diagnostic and empirical work within Digital Identity Optimization.

Written by AI from the paper. Passages are checked word for word against the text we analysed; the rest may contain errors.

AI-generated keywords: Digital Identity Optimization identity reconstruction failure taxonomy semantic robustness entity resolution

Read further

Comprehensive Summary
Layman's Summary
Blog article
Original abstract

The paper examines a conceptual question in Digital Identity Optimization (DIO): how should failures in digital identity reconstruction be classified, and how can they be distinguished from anomalies or vulnerabilities identified in earlier work? Building on the vocabulary of Entity Resolution Anomalies and an adversarial reduction developed in a related DIO paper, it aims to refine the terminology used to analyze identity reconstruction in heterogeneous AI environments. The paper offers a taxonomic framework rather than an empirical study. It groups reconstruction failures into four non-exclusive domains: Referential Reconstruction Failures, Semantic Coherence Failures, Temporal Reconstruction Failures, and Contextual Adequacy Failures. Because the categories are not mutually exclusive, a single case may involve several types of failure. The referential domain includes Entity Substitution, Merge Failure, Split Failure, and Entity Omission. These categories describe problems in identifying the entity being represented or in associating records and references. Semantic Fragmentation falls under semantic coherence. Temporal Discontinuity and Temporal Misalignment belong to the temporal domain, distinguishing breaks in an identity’s continuity from mismatches in its timing. Contextual Displacement falls under contextual adequacy and describes cases in which an identity representation is placed or interpreted in an unsuitable context. The abstract names these categories but provides no operational definitions, diagnostic thresholds, or examples. As a result, their practical application cannot be assessed from the supplied text. The paper also distinguishes among Identity Collapse, Semantic Vulnerability, and Semantic Robustness. Identity Collapse remains a phenomenon-level concept rather than a branch of the failure taxonomy. Semantic Vulnerability is treated not as a realized failure, but as a property indicating susceptibility to destabilization. Semantic Robustness is its conceptual counterpart. This distinction separates an actual reconstruction failure from a system’s potential exposure to one. The paper’s main contribution is a proposed vocabulary and classification structure, not a set of measured findings. The taxonomy aims to improve analytical precision, clarify relationships among failure concepts, and support future diagnostic and empirical research in DIO. The author presents it as an extension of the earlier anomaly vocabulary, not a replacement for it. The proposal’s limitations are substantial. The supplied material includes only the title and abstract, and the paper is described as a taxonomic note. The abstract reports no empirical validation or evidence about the frequency, severity, or real-world consequences of the categories. It also does not explain how to choose among categories in ambiguous cases or how to measure robustness and vulnerability. The taxonomy should therefore be understood as a conceptual framework whose usefulness and boundaries remain to be tested.

From Entity Resolution Anomalies to Reconstruction Failure Modes

When an AI system brings together information from different sources, it must do more than match records. It must reconstruct an identity: decide which references belong together, preserve the meaning of that identity over time, and interpret it in the right context. What can go wrong in that process—and how should those failures be described?

Daniel Beránek’s paper, “From Entity Resolution Anomalies to Reconstruction Failure Modes: A Taxonomic Note Following Minimum Viable Digital Identity Optimization (DIO),” takes up this conceptual question. It proposes a vocabulary for classifying failures in Digital Identity Optimization (DIO), building on earlier work on Entity Resolution Anomalies and an adversarial reduction developed in a related DIO paper. Its contribution is a framework for thinking and talking about failures, not an empirical account of how often they occur.

A taxonomy of reconstruction failures

The paper organizes failures into four broad, non-exclusive domains. “Non-exclusive” matters: a single case may involve more than one kind of failure. For example, a system could associate information with the wrong entity while also placing that identity in an unsuitable context.

Referential Reconstruction Failures: Problems identifying the entity being represented or connecting records and references to it.
Semantic Coherence Failures: Problems preserving the coherence of an identity’s meaning.
Temporal Reconstruction Failures: Problems with continuity or timing across an identity’s history.
Contextual Adequacy Failures: Problems that arise when an identity is placed or interpreted in an unsuitable context.

Within the referential domain, the proposed labels are Entity Substitution, Merge Failure, Split Failure, and Entity Omission. Together, they point to different ways reconstruction can go wrong: a representation may stand in for the wrong entity, records may fail to come together or be separated appropriately, or an entity may be left out.

Semantic Fragmentation is assigned to the semantic coherence domain. The temporal domain distinguishes Temporal Discontinuity from Temporal Misalignment: the first concerns a break in an identity’s continuity, while the second concerns a mismatch in timing. Contextual Displacement names a failure of contextual adequacy, in which an identity representation is interpreted or situated where it does not fit.

Failures, vulnerabilities, and collapse

A useful feature of the proposed framework is its effort to distinguish concepts that might otherwise be treated as interchangeable. Identity Collapse remains a phenomenon-level concept; it is not presented as another branch of the failure taxonomy. The distinction leaves room to describe the broader phenomenon separately from the specific failure modes that may contribute to it.

The paper also separates an actual failure from a system’s susceptibility to one. Semantic Vulnerability describes a property that makes a system susceptible to destabilization. Semantic Robustness is its conceptual counterpart. In this framing, vulnerability does not itself mean that reconstruction has failed: it indicates potential exposure. A failure, by contrast, is a realized problem.

That distinction could help researchers be more precise. Saying that a system is vulnerable is not the same as documenting a reconstruction failure, just as naming a failure mode does not by itself show that a system is vulnerable to it. Keeping these ideas apart may make later analysis easier to interpret.

A vocabulary, not a measurement study

The paper’s central contribution is a proposed classification structure. It aims to sharpen analytical language, clarify how related concepts fit together, and provide a starting point for diagnostic and empirical research in DIO. Importantly, the taxonomy is presented as an extension of the earlier anomaly vocabulary, not as a replacement for it.

That ambition should be understood alongside the limits of the available description. The supplied material includes the title and abstract, and the work is described as a taxonomic note. The abstract names the categories but does not provide operational definitions, diagnostic thresholds, or examples. Without those details, readers cannot assess how the labels would be applied in practice or how consistently different analysts might classify the same case.

Nor does the abstract report empirical validation. It offers no evidence about the frequency, severity, or real-world consequences of the proposed failure modes. It also leaves open how to choose between categories when a case is ambiguous, and how Semantic Robustness or Semantic Vulnerability might be measured.

Why the proposal matters—and what comes next

Even at this conceptual stage, the taxonomy points to an important challenge: identity reconstruction is not a single matching task. It involves reference, meaning, time, and context. A system might connect the right records but still represent their meaning incoherently, break a person’s history into disconnected parts, or interpret an identity in a setting where it does not belong. A vocabulary that makes these distinctions visible could help researchers describe such cases more clearly.

For now, however, the framework is best read as a map of questions rather than a tested diagnostic tool. Future work would need to define each category precisely, show how to identify it in concrete cases, and test where the categories overlap or prove difficult to distinguish. It would also need methods for evaluating vulnerability and robustness.

Beránek’s proposal offers a structured starting point for that work. Its value will ultimately depend on whether researchers can apply the terms consistently and whether the distinctions help explain real reconstruction problems. Until those questions are tested, the taxonomy remains a promising conceptual framework—not a set of measured findings.

Created on 01 Nov. 2026

Was this synthesis useful?

Score: 1

Ask questions about this paper to our AI assistant

How to chat with this paper? Illustrated guide

You can also chat with multiple papers at once here.

AI assistant instructions?

Tools for this paper

Explain it differently 3 free rewrites left today

Save to a collection Group papers in collections to compare them, chat with them and export them. Create a free account Log in

Export BibTeX · RIS (Zotero, Mendeley, EndNote) · Markdown (Notion, Obsidian)

Advanced tools Premium

For researchers who follow a field closely: citation alerts, journal-club slides, version comparison and Zotero export. Discover Premium

Zotero

Citation alerts Citation alerts guide

Who works on it? The people and institutions who publish on its topic

Journal club Premium+ Slides to present it

Talk about it in public Premium+ Press kit: release, questions, hype check Press kit guide

Papers around this one

See them on a map

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

Closest papers

Close Groundwork for this paper
Digital Identity Optimization (DIO): A Conceptual Framework for Entity-Based Visibility in the Age of AI-Mediated Search
Daniel Beránek · 2026 · Zenodo (CERN European Organization for Nuclear Research) preprint · AI summary available

Digital Identity Optimization defines entity-based visibility and identity optimization, the framework whose reconstruction failures this note classifies.

In short
The paper proposes Digital Identity Optimization (DIO), a conceptual framework for making entities consistently identifiable and recommendable across human and AI-mediated systems.
Related Groundwork for this paper
Manifest of Digital Identity Optimization (DIO) and Ontology of Digital Identity (ODI): Canonical Multilingual Edition
Daniel Beránek · 2026 · Zenodo (CERN European Organization for Nuclear Research) · AI summary available

The canonical DIO and Ontology of Digital Identity edition establishes the identity framework that this note refines with reconstruction-failure categories.

In short
The abstract presents DIO and ODI as a multilingual framework for conceptualizing and maintaining digital identity, but reports no empirical evaluation.
Related Broader context
Demand-Driven Context: A Methodology for Building Enterprise Knowledge Bases Through Agent Failure
Raj Navakoti, Saideep Navakoti · 2026 · Artificial Intelligence · AI summary available

Demand-Driven Context builds enterprise knowledge bases from agent failures, addressing a separate kind of failure in LLM systems.

Abstract
Large language model agents demonstrate expert-level reasoning, yet consistently fail on enterprise-specific tasks due to missing domain knowledge -- terminology, operational procedures, system interdependencies, and institutional decisions that exist largely as tribal knowledge. Current approaches fall into two categories: top-down knowledge engineering, which documents domain knowledge before agents use it, and bottom-up automation, where agents learn from task experience. Both have fundamental limitations: top-down efforts produce bloated, untested knowledge bases; bottom-up approaches cannot acquire knowledge that exists only in human heads. We present Demand-Driven Context (DDC), a prob…
Related Broader context
The Role of Entropy and Reconstruction in Multi-View Self-Supervised Learning
Borja Rodríguez-Gálvez, Arno Blaas, Pau Rodríguez et al. · 2023 · Machine Learning · AI summary available

The study analyzes entropy and reconstruction in self-supervised learning, where reconstruction is an objective rather than a digital-identity failure taxonomy.

Abstract
The mechanisms behind the success of multi-view self-supervised learning (MVSSL) are not yet fully understood. Contrastive MVSSL methods have been studied through the lens of InfoNCE, a lower bound of the Mutual Information (MI). However, the relation between other MVSSL methods and MI remains unclear. We consider a different lower bound on the MI consisting of an entropy and a reconstruction term (ER), and analyze the main MVSSL families through its lens. Through this ER bound, we show that clustering-based methods such as DeepCluster and SwAV maximize the MI. We also re-interpret the mechanisms of distillation-based approaches such as BYOL and DINO, showing that they explicitly maximize th…
Related Broader context
Recover: A Neuro-Symbolic Framework for Failure Detection and Recovery
Cristina Cornelio, Mohammed Diab · 2024 · Artificial Intelligence · Not summarized yet

Recover detects and recovers from robotics task failures, unlike this note’s taxonomy of digital-identity reconstruction failures.

Abstract
Recognizing failures during task execution and implementing recovery procedures is challenging in robotics. Traditional approaches rely on the availability of extensive data or a tight set of constraints, while more recent approaches leverage large language models (LLMs) to verify task steps and replan accordingly. However, these methods often operate offline, necessitating scene resets and incurring in high costs. This paper introduces Recover, a neuro-symbolic framework for online failure identification and recovery. By integrating ontologies, logical rules, and LLM-based planners, Recover exploits symbolic information to enhance the ability of LLMs to generate recovery plans and also to d…
Related Broader context
Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis
Akarsh Kumar, Jeff Clune, Joel Lehman et al. · 2025 · Computer Vision and Pattern Recognition · AI summary available

The hypothesis examines fractured neural representations and challenges performance-based assumptions, rather than classifying digital-identity reconstruction failures.

Abstract
Much of the excitement in modern AI is driven by the observation that scaling up existing systems leads to better performance. But does better performance necessarily imply better internal representations? While the representational optimist assumes it must, this position paper challenges that view. We compare neural networks evolved through an open-ended search process to networks trained via conventional stochastic gradient descent (SGD) on the simple task of generating a single image. This minimal setup offers a unique advantage: each hidden neuron's full functional behavior can be easily visualized as an image, thus revealing how the network's output behavior is internally constructed ne…
Related Broader context
Digital Twin sensors in cultural heritage applications
Franco Niccolucci, Achille Felicetti · 2024 · Sensors 2024, 24, 3978 · Not summarized yet

The paper extends an ontology for cultural-heritage digital twins, a different application of semantic representation and identity.

Abstract
The paper concerns the extension of the Heritage Digital Twin Ontology introduced in previous work to describe the reactivity of digital twins used for cultural heritage documentation by including the semantic description of sensors and activators and all the process of interacting with the real world. After analysing previous work on the use of digital twins in cultural heritage, a summary description of the Heritage Digital Twin Ontology is provided, and the existing applications of digital twins to cultural heritage are overviewed, with references to reviews summarizing the large production of scientific contributions on the topic. Then a novel ontology, named Reactive Digital Twin Ontolo…
Related Review
AI-powered Fraud Detection in Decentralized Finance: A Project Life Cycle Perspective
Bingqiao Luo, Zhen Zhang, Qian Wang et al. · 2023 · Computational Engineering, Finance, and Science · AI summary available

The paper surveys AI methods for detecting decentralized-finance fraud, a separate topic from digital-identity reconstruction failures.

Abstract
In recent years, blockchain technology has introduced decentralized finance (DeFi) as an alternative to traditional financial systems. DeFi aims to create a transparent and efficient financial ecosystem using smart contracts and emerging decentralized applications. However, the growing popularity of DeFi has made it a target for fraudulent activities, resulting in losses of billions of dollars due to various types of frauds. To address these issues, researchers have explored the potential of artificial intelligence (AI) approaches to detect such fraudulent activities. Yet, there is a lack of a systematic survey to organize and summarize those existing works and to identify the future researc…

Go further

How are these papers found?

We compare the title and abstract of this paper with those of every paper summarized on this site, and with the papers Semantic Scholar recommends, those it cites and those citing it (for a much-cited paper, its most recent citations and, from OpenAlex, the most cited ones). Among the prior work and the follow-ups, the papers that use each other in depth, a method it uses and the much-cited follow-ups come a little higher. The levels (very close, close, related) come from the similarity of the texts, not from a judgment of quality; * marks a paper without an abstract, compared by its title. The sentence under a paper is written by an AI from the two abstracts: check it in the papers. A paper marked not relevant by three readers leaves the list.

Updated on 1 November 2026.

Disclaimer: The AI-based summarization tool and virtual assistant provided on this website may not always provide accurate and complete summaries or responses. We encourage you to carefully review and evaluate the generated content to ensure its quality and relevance to your needs.

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

The essentials

Question

Method

Findings

Limitations

Why it matters

Read further

Definitions

From Entity Resolution Anomalies to Reconstruction Failure Modes

A taxonomy of reconstruction failures

Failures, vulnerabilities, and collapse

A vocabulary, not a measurement study

Why the proposal matters—and what comes next

Ask questions about this paper to our AI assistant

Tools for this paper

Advanced tools Premium

Papers around this one

Closest papers

Go further

Cite this paper (BibTeX)