Searcharxiv⌕ Search

arXiv subjects

Chunyi Zhao

Publications and source records attributed to Chunyi Zhao.

16 recordsLinked to original sources
arXiv2026

Reliability, validity, and diagnostic evidence for multi-model LLM short-answer scoring

Large language models (LLMs) are increasingly used or proposed for educational scoring, but single-model and single-run evaluations provide limited evidence for assessment use. Short-answer scoring requires evidence about reliability, validity, severity, diagnostic value, and failure cases. This study evaluated repeated multi-model OCG-PRES guided LLM scoring for short-answer assessment. The analysis used 996 SciEntsBank responses. GPT, DeepSeek, and Qianwen each scored every response across three independent runs using five OCG-PRES dimensions: concept coverage, relation accuracy, reasoning completeness, contradiction control, and domain relevance. Scores were evaluated against official binary and five-category labels and compared with non-LLM baselines based on answer length, Jaccard keyword overlap, TF-IDF cosine similarity, and a combined traditional logistic model. Repeated-run reliability was high for all models, with ICC(3,k) = .977 for GPT, .992 for DeepSeek, and .981 for Qianwen. DeepSeek was the most stable across runs. GPT showed the strongest official-label alignment by AUC (.909), while Qianwen was stricter, with higher precision but lower recall under the fixed threshold = 3.0 rule. OCG-PRES scores followed expected diagnostic patterns across five official categories and outperformed all non-LLM baselines in AUC and F1. Repeated multi-model OCG-PRES scoring provides reliability, validity, and diagnostic evidence for LLM-assisted short-answer scoring. The findings support cautious, evidence-based use as a scoring support tool rather than a replacement for human judgement.

cs.CL↗
arXiv2026

Qualitative analysis of positive radial singular solutions on hyperbolic space

We investigate positive radial solutions with an isolated nonremovable singularity for the semilinear elliptic equation \begin{align*} \Delta_{\mathbb{H}^N} u+\lambda u+u^p=0 \qquad\text{in }\mathbb{H}^N\setminus\{Q\}, \end{align*} where $N\geq 3$, $p>1$, $\lambda\le \frac{(N-1)^2}{4}$, and $Q\in\mathbb{H}^N$ is a prescribed pole. Our purpose is to describe how the locally Euclidean singular behavior near ${\{Q}\}$ interacts with the genuinely hyperbolic dynamics at infinity, and how this interaction changes across the Serrin and Sobolev critical exponents. For $\frac{N}{N-2}\le p<\frac{N+2}{N-2}$, we construct a family of positive radial singular solutions selecting the fast exponential mode at infinity. At the pole, these solutions exhibit the logarithmically corrected fundamental-solution profile when $p=\frac{N}{N-2}$, and the standard power-law profile when $\frac{N}{N-2} \frac{N+2}{N-2}$ with $\lambda\le\frac{ N(N-2)}{4}$, we prove existence and uniqueness of the global positive radial singular solution, derive its two-term local asymptotic expansion near the pole, and establish a sharp trichotomy for its behavior at infinity.

math.AP↗
arXiv2026

Why Organizational Rules Fail AI: O-I-B-A-R and the Externalization of Decision Boundaries

AI systems increasingly enter organizations through policies, procedures, playbooks, prompts, and other explicit representations of work. Yet formal descriptions often differ from situated practice, and captured know-what can omit the contextual know-how experts use when judgments are uncertain. We argue that a recurring class of organizational AI failures arises partly from a knowledge representation problem at the sociotechnical interface: the AI receives the procedure, while the organization operates on the procedure plus negative boundaries, runtime judgments, responsibility assignments, and learning history. We introduce O-I-B-A-R (OPEN, IS, BUT, ACTION, RESULT), a scaffold for externalizing these missing decision boundaries. IS records when a judgment holds. BUT records a concrete failure containing information beyond the logical negation of IS. Comparable success and failure cases are decomposed toward a minimally sufficient changing variable, which becomes a value-bearing decision dimension. A suspension represents the state in which the dimension is known but its current value is unresolved, specifying what must be measured, asked, retrieved, or escalated to a human. RESULT confirms a boundary, shifts a threshold, or exposes a new dimension. Incidents can generate new dimensions, unresolved values can define human-AI handoffs, and feedback can expand the decision space. We also identify a sociotechnical tension: durable and attributable failure histories can suppress the candor on which useful boundary knowledge depends. Externalization must therefore be designed as an organizational intervention with real costs and incentives.

cs.CY↗
arXiv2026

Structural Dissolution: How Artificial Intelligence Dismantles Coordination Architecture and Reconfigures the Political Economy of Production

This paper introduces the Structural Dissolution Framework to explain how artificial intelligence restructures the coordination architecture of traditional industries. We argue that AI dissolves the boundaries that once separated firms, markets, experts, and consumers by internalizing human multimodal interfaces, including language, vision, and behavioral data, into computational systems. This process is not merely an efficiency gain but a qualitative transformation of production relations. It generates four major shifts: the erosion of firm and industry boundaries; the movement of value creation from physical resources and human collaboration to continuous token flows produced through data refinement loops; the rise of domain-specific data refinement infrastructure as the new basis of positional control; and the emergence of regional data sovereignty entities as organizational forms that replace the coordinating role of firms and markets. We define this mechanism as Interface Internalization, through which inter-agent coordination is absorbed into intra-system computation. The framework challenges the Coasian view that organizational boundaries are determined by transaction cost minimization, arguing instead that AI makes such boundaries economically obsolete. Firms may continue to exist as legal and physical entities, but their coordinating function is displaced as they become data nodes within regionally governed AI infrastructure. Using resource-dependent regional economies as an illustrative case, the paper shows how AI adoption can both transform seasonal industries into continuous economic infrastructure and replace intermediate coordination roles and traditional employment structures.

cs.CY↗
arXiv2026

Domain-Contextualized Inference: A Computable Graph Architecture for Explicit-Domain Reasoning

We establish a computation-substrate-agnostic inference architecture in which domain is an explicit first-class computational parameter. This produces domain-scoped pruning that reduces per-query search space from O(N) to O(N/K), substrate-independent execution over symbolic, neural, vector, and hybrid substrates, and transparent inference chains where every step carries its evaluative context. The contribution is architectural, not logical. We formalize the computational theory across five dimensions: a five-layer architecture; three domain computation modes including chain indexing, path traversal as Kleisli composition, and vector-guided computation as a substrate transition; a substrate-agnostic interface with three operations Query, Extend, Bridge; reliability conditions C1 to C4 with three failure mode classes; and validation through a PHQ-9 clinical reasoning case study. The computational theory including operational semantics, complexity bounds, monad structure, substrate transitions, and boundary conditions is the contribution of this paper.

cs.AI↗
arXiv2026

Domain-constrained knowledge representation: A modal framework

Knowledge graphs store large numbers of relations efficiently, but they remain weak at representing a quieter difficulty: the meaning of a concept often shifts with the domain in which it is used. A triple such as Apple, instance-of, Company may be acceptable in one setting while being misleading or unusable in another. In most current systems, domain information is attached as metadata, qualifiers, or graph-level organization. These mechanisms help with filtering and provenance, but they usually do not alter the formal status of the assertion itself. This paper argues that domain should be treated as part of knowledge representation rather than as supplementary annotation. It introduces the Domain-Contextualized Concept Graph (DCG), a framework in which domain is written into the relation and interpreted as a modal world constraint. In the DCG form (C, R at D, C'), the marker at D identifies the world in which the relation holds. Formally, the relation is interpreted through a domain-indexed necessity operator, so that truth, inference, and conflict checking are all scoped to the relevant world. This move has three consequences: ambiguous concepts can be disambiguated at the point of representation; invalid assertions can be challenged against their domain; cross-domain relations can be connected through explicit predicates. The paper develops this claim through a Kripke-style semantics, a compact predicate system, a Prolog implementation, and mappings to RDF, OWL, and relational databases. The contribution is a representational reinterpretation of domain itself. The central claim is that many practical failures in knowledge systems begin when domain is treated as external to the assertion. DCG addresses that by giving domain a structural and computable role inside the representation.

cs.AI↗
arXiv2026

How should AI knowledge be governed? Epistemic authority, structural transparency, and the case for open cognitive graphs

Through widespread use in formative assessment and self-directed learning, educational AI systems exercise de facto epistemic authority. Unlike human educators, however, these systems are not embedded in institutional mechanisms of accountability, review, and correction, creating a structural governance challenge that cannot be resolved through application-level regulation or model transparency alone. This paper reconceptualizes educational AI as public educational cognitive infrastructure and argues that its governance must address the epistemic authority such systems exert. We propose the Open Cognitive Graph (OCG) as a technical interface that externalizes pedagogical structure in forms aligned with human educational reasoning. By explicitly representing concepts, prerequisite relations, misconceptions, and scaffolding, OCGs make the cognitive logic governing AI behaviour inspectable and revisable. Building on this foundation, we introduce the trunk-branch governance model, which organizes epistemic authority across layers of consensus and pluralism. A case study of a community-governed educational foundation model demonstrates how distributed expertise can be integrated through institutionalized processes of validation, correction, and propagation. The paper concludes by discussing implications for educational equity, AI policy, and sustainability. By shifting attention from access to governance conditions, the proposed framework offers a structural approach to aligning educational AI with democratic accountability and public responsibility.

cs.CY↗
arXiv2024

Highly Efficient and Stable Perovskite Solar Cells via MultiFunctional Curcumin Modified Buried Interface

The buried interface between the electron transport layer and the perovskite layer suffers from severe interface defects and imperfect energy level alignment. To address this issue, this study employs a multifunctional organic molecule, curcumin, to modify the interface between SnO2 and the perovskite layer. The functional groups on curcumin effectively passivate the defects on both sides of the interface, reducing -OH and oxygen vacancy defects on the SnO2 surface and passivating uncoordinated Pb2+ in the perovskite layer. This results in a more compatible energy level alignment and lower defect density at the interface, enhancing carrier transport across it. Consequently, the devices based on curcumin achieve an impressive champion power conversion efficiency (PCE) of 24.46%, compared to 22.03% for control devices. This work demonstrates a simple, green, hydrophobic, and efficient molecular modification method for the buried interface, laying the foundation for the development of high-performance and stable perovskite solar cells.

cond-mat.mtrl-sci↗
arXiv2024

An eco-friendly passivation strategy of resveratrol for highly efficient and antioxidative perovskite solar cells

The stability of perovskite solar cells is closely related to the defects in perovskite crystals, and there are a large number of crystal defects in the perovskite thin films prepared by the solution method, which is not conducive to the commercial production of PSCs. In this study, resveratrol(RES), a green natural antioxidant abundant in knotweed and grape leaves, was introduced into perovskite films to passivate the defect. RES achieves defect passivation by interacting with uncoordinated Pb2+ in perovskite films. The results show that the quality of the perovskite film is significantly improved, and the energy level structure of the device is optimized, and the power conversion efficiency of the device is increased from 21.62% to 23.44%. In addition, RES can hinder the degradation of perovskite structures by O2- and CO2- free radicals, and the device retained 88% of its initial PCE after over 1000 hours in pure oxygen environment. The device retains 91% of the initial PCE after more than 1000 hours at 25°C and 50+5% relative humidity. This work provides a strategy for the use of natural and environmentally friendly additives to improve the efficiency and stability of devices, and provides an idea for the development of efficient, stable and environmentally friendly PSCs.

cond-mat.mtrl-sci↗
arXiv2021

Modelling for Poisson process intensities over irregular spatial domains

We develop nonparametric Bayesian modelling approaches for Poisson processes, using weighted combinations of structured beta densities to represent the point process intensity function. For a regular spatial domain, such as the unit square, the model construction implies a Bernstein-Dirichlet prior for the Poisson process density, which supports general inference for point process functionals. The key contribution of the methodology is two classes of flexible and computationally efficient models for spatial Poisson process intensities over irregular domains. We address the choice or estimation of the number of beta basis densities, and develop methods for prior specification and posterior simulation for full inference about functionals of the point process. The methodology is illustrated with both synthetic and real data sets.

stat.ME↗
arXiv2020

Concentration solutions to singularly prescribed Gaussian and geodesic curvatures problem

We consider the following Liouville-type equation with exponential Neumann boundary condition: $$ -Δ\tilde u = \varepsilon^2 K(x) e^{2\tilde u}, \quad x\in D, \qquad \frac{\partial \tilde u}{\partial n} + 1 = \varepsilon κ(x) e^{\tilde u}, \quad x\in\partial D, $$ where $D\subset \mathbb R^2$ is the unit disc, $\varepsilon^2 K(x)$ and $\varepsilon κ(x)$ stand for the prescribed Gaussian curvature and the prescribed geodesic curvature of the boundary, respectively. We prove the existence of concentration solutions if $κ(x) + \sqrt{K(x)+κ(x)^2}$ ($x\in\partial D$) has a strictly local extremum point, which is a total new result for exponential Neumann boundary problem.

math.AP↗
arXiv2014

Infinitely many solutions to a fractional nonlinear Schrödinger equation

This paper considers the fractional Schrödinger equation \begin{equation}\label{abstract} (-Δ)^s u + V(|x|)u-u^p=0, \quad u>0, \quad u\in H^{2s}(\R^N) \end{equation} where $0<s<1$, $1<p<\frac{N+2s}{N-2s}$, $V(|x|)$ is a positive potential and $N\geq 2$. We show that if $V(|x|)$ has the following expansion: \[ V(|x|)=V_0 + \frac{a}{|x|^m} + o\left(\frac{1}{|x|^m}\right) \qquad \mbox{as} \ |x| \rightarrow +\infty, \] in which the constants are properly assumed, then (\ref{abstract}) admits infinitely many non-radial solutions, whose energy can be made arbitrarily large. This is the first result for fractional Schrödinger equation. The $s=1$ case corresponds to the known result in Wei-Yan \cite{WY}.

math.AP↗
arXiv2012

Infinitely many solutions for the prescribed boundary mean curvature problem on $\mathbb B^N$

We consider the following prescribed boundary mean curvature problem in $\mathbb B^N$ with the Euclidean metric $-Δu =0$, $u>0$ in $B^N, \frac{\partial u}{\partialν} + \frac{N-2}{2} u =\frac{N-2}{2} K(x) u^{N/(N-2)}$ on $S^{N-1}, where $K$ is positive and rotationally symmetric on $\mathbb S^{N-1}$. We show that if ${K}$ has a local maximum point, then the equation has {\bf infinitely many positive} solutions, which are non-radial on $\mathbb S^{N-1}$.

math.AP↗
arXiv2011

Non-compactness of the Prescribed Q-curvature Problem in Large Dimensions

Let $(M, g)$ be a compact Riemannian manifold of dimension $N \geq 5$ and $Q_g$ be its $Q$ curvature. The prescribed $Q$ curvature problem is concerned with finding metric of constant $Q$ curvature in the conformal class of $g$. This amounts to finding a positive solution to \[ P_g (u)= c u^{\frac{N+4}{N-4}}, u>0 {on} M\] where $P_g$ is the Paneitz operator. We show that for dimensions $N \geq 25$, the set of all positive solutions to the prescribed $Q$ curvature problem is {\em non-compact}.

math.DG↗