From Entity Resolution Anomalies to Reconstruction Failure Modes: A Taxonomic Note Following Minimum Viable Digital Identity Optimization (DIO)
Authors: Daniel Beránek
Abstract
This taxonomic note refines the vocabulary of Entity Resolution Anomalies developed in The Crisis of Entity Resolution in Heterogeneous AI Environments and follows the adversarial reduction introduced in Minimum Viable Digital Identity Optimization (DIO): From Adversarial Reduction to the Semantic Field Dynamics of Digital Identity. It proposes a non-exclusive, multi-level diagnostic taxonomy of Reconstruction Failure Modes. The taxonomy distinguishes four analytical domains: Referential Reconstruction Failures, Semantic Coherence Failures, Temporal Reconstruction Failures, and Contextual Adequacy Failures. Referential failures include Entity Substitution, Merge Failure, Split Failure, and Entity Omission. 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. The note preserves Identity Collapse as a phenomenon-level concept rather than redefining it as a branch of the failure taxonomy. 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. The purpose is not to replace the earlier anomaly vocabulary retroactively, but to increase analytical resolution, distinguish realized reconstruction failure from susceptibility to destabilization, and create a clearer basis for future diagnostic and empirical work within Digital Identity Optimization (DIO).
The papers around it, by date and closeness
Higher is closer to this paper; left is older. Lines join papers close to each other: groups of lines are sub-topics. Select a point to see why it is there. Back to the summary of this paper
Papers around this one
Ranked by how close their title and abstract are to this paper’s. Select some to read them together.
Closest papers
-
Digital Identity Optimization (DIO): A Conceptual Framework for Entity-Based Visibility in the Age of AI-Mediated SearchDaniel 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.
-
Manifest of Digital Identity Optimization (DIO) and Ontology of Digital Identity (ODI): Canonical Multilingual EditionDaniel 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.
-
Demand-Driven Context: A Methodology for Building Enterprise Knowledge Bases Through Agent FailureRaj 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…
-
The Role of Entropy and Reconstruction in Multi-View Self-Supervised LearningBorja 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…
-
Recover: A Neuro-Symbolic Framework for Failure Detection and RecoveryCristina 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…
-
Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation HypothesisAkarsh 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…
-
Digital Twin sensors in cultural heritage applicationsFranco 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…
-
AI-powered Fraud Detection in Decentralized Finance: A Project Life Cycle PerspectiveBingqiao 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.