Large language models (LLMs) show promise for clinical reasoning and decision support, but evaluation in structured, electronic health record-congruent settings remains limited. Existing benchmarks often rely on static datasets or unstructured inputs that do not reflect the interoperable data formats used in clinical systems. We introduce a reusable pipeline for generating terminology-grounded HL7 FHIR R4 bundles from unstructured text, enabling controllable evaluation of clinical decision support systems over structured inputs. The pipeline combines staged LLM generation with terminology-grounded validation and repair to eliminate hallucinated codes and enforce structural and semantic consistency. Applying this approach to MedCaseReasoning, we construct MedCase-Structured, a synthetic dataset of 1,732 FHIR bundles derived from clinician-authored diagnostic cases, producing complete, valid bundles for 97.1% of attempted cases. Evaluation on MedCase-Structured reveals consistently lower diagnostic accuracy for LLMs on structured FHIR inputs than with plain text, highlighting the importance of deployment-aligned benchmarking.
How reliably can structured intent representations preserve user goals across different AI models, languages, and prompting frameworks? Prior work showed that PPS (Prompt Protocol Specification), a 5W3H-based structured intent framework, improves goal alignment in Chinese and generalizes to English and Japanese. This paper extends that line of inquiry in three directions: cross-model robustness across Claude, GPT-4o, and Gemini 2.5 Pro; controlled comparison with CO-STAR and RISEN; and a user study (N=50) of AI-assisted intent expansion in ecologically valid settings. Across 3,240 model outputs (3 languages x 6 conditions x 3 models x 3 domains x 20 tasks), evaluated by an independent judge (DeepSeek-V3), we find that structured prompting substantially reduces cross-language score variance relative to unstructured baselines. The strongest structured conditions reduce cross-language sigma from 0.470 to about 0.020. We also observe a weak-model compensation pattern: the lowest-baseline model (Gemini) shows a much larger D-A gain (+1.006) than the strongest model (Claude, +0.217). Under the current evaluation resolution, 5W3H, CO-STAR, and RISEN achieve similarly high goal-alignment s
The Lovász hinge is a convex loss function proposed for binary structured classification, in which k related binary predictions jointly evaluated by a submodular function. Despite its prevalence in image segmentation and related tasks, the consistency of the Lovász hinge has remained open. We show that the Lovász hinge is inconsistent with its desired target unless the set function used for evaluation is modular. Leveraging the embedding framework of Finocchiaro et al. (2024), we find the target loss for which the Lovász hinge is consistent. This target, which we call the structured abstain problem, is a variant of selective classification for structured prediction that allows one to abstain on any subset of the k binary predictions. We derive a family of link functions, each of which is simultaneously consistent for all polymatroids, a subset of submodular set functions. We then give sufficient conditions on the polymatroid for the structured abstain problem to be tightly embedded by the Lovász hinge, meaning no target prediction is redundant. We experimentally demonstrate the potential of the structured abstain problem for interpretability in structured classification tasks. Fina
Does structured intent representation generalize across languages and models? We study PPS (Prompt Protocol Specification), a 5W3H-based framework for structured intent representation in human-AI interaction, and extend prior Chinese-only evidence along three dimensions: two additional languages (English and Japanese), a fourth condition in which a user's simple prompt is automatically expanded into a full 5W3H specification by an AI-assisted authoring interface, and a new research question on cross-model output consistency. Across 2,160 model outputs (3 languages x 4 conditions x 3 LLMs x 60 tasks), we find that AI-expanded 5W3H prompts (Condition D) show no statistically significant difference in goal alignment from manually crafted 5W3H prompts (Condition C) across all three languages, while requiring only a single-sentence input from the user. Structured PPS conditions often reduce or reshape cross-model output variance, though this effect is not uniform across languages and metrics; the strongest evidence comes from identifying spurious low variance in unconstrained baselines. We also show that unstructured prompts exhibit a systematic dual-inflation bias: artificially high co
This study compares the impact of natural and synthetic data on training and evaluating large language models (LLMs), using the case of passive verb alternation in French and Italian. We use Blackbird Language Matrices (BLMs), structured datasets designed to probe linguistic knowledge of underlying patterns across sentence sets. We compare structured templates instantiated with natural sentences extracted from Universal Dependencies to structured templates of synthetic sentences. Experiments show that while models achieve ceiling performance when trained and tested on synthetic datasets, they do not reliably generalize to natural sentences. In contrast, models trained on natural data exhibit robust performance across both natural and synthetic test suites, demonstrating their superior ability to capture abstract linguistic patterns. These results corroborate the value of natural data and of structured set ups in linguistic evaluation for probing LLMs' syntactic and semantic knowledge.
We introduce \emph{TAPO-Structured Description Logic} (TAPO--DL), a formal extension of classical description logic designed to model \emph{information behavior} as a structured, dynamic process. TAPO--DL extends the standard T--Box/A--Box architecture with two additional layers: a \emph{Procedural Box} (P--Box), which supports concept-driven, imperative-style programs such as conditional and iterative actions, and an \emph{Oracle Box} (O--Box), which formalizes controlled interaction with external information sources. While the terminological and assertional components capture static conceptual and factual knowledge, the procedural and oracle-based components enable the explicit representation of information-generating actions and external validation. We provide a unified semantic framework for TAPO--DL based on a co-generative, sheaf-theoretic interpretation, in which local informational states are modeled as sections and informational stability corresponds to the existence of coherent global structures. Within this setting, informational truth is characterized as stability under repeated agentive interaction rather than correspondence to a fixed global state. By integrating desc
Structured optical beams possess rich spatial features that are commonly characterized using entropic measures of field complexity. However, such measures do not directly quantify the operational usefulness of optical structure for parameter estimation and sensing. Here we introduce Fisher information as an operational metric to assess the metrological content of structured optical fields. By treating the measured intensity distribution as a statistical object, we define Fisher information with respect to physically relevant parameters, such as transverse displacement. We demonstrate that optical modes with comparable Shannon entropy can exhibit markedly different Fisher information, revealing sensitivity features associated with nodal structure and local curvature. Using Hermite--Gaussian modes as minimal test cases, we show that increasing modal order systematically enhances Fisher information. We then extend the analysis to two widely used families in structured light: Laguerre--Gaussian vortex beams and finite-energy Bessel--Gauss beams. Across these representative families, Fisher information provides a unified and experimentally accessible criterion for comparing structured o
In this work we present a LLM powered, evolutionary code synthesis system for structured data translation in a Medical Internet of Things settings. A key challenge in this domain is ensuring that the synthesized code is trustworthy and reliable. To this end, we integrate a formal verification step into our code synthesis pipeline to ensure that any generated code is guaranteed to satisfy predefined requirements. In particular, we present a case study of integrating a novel device (a pulse oximeter) into the existing network of devices. Our system generates a formally verified translation between the device's JSON schema and the Fast Healthcare Interoperability Resources (FHIR) format used by the wider system. This formal verification stage ensures structured data translated by the generated code will always be in the target output schema. We provide a set of experimental results which demonstrate that our system is able to consistently generate correct translation at low cost.
A credit rating of AAA asserts near-certainty of repayment. This paper asks whether the pre-crisis information environment could have supported that assertion for structured products. Bayes' theorem implies that any reliability target requires a minimum level of statistical discrimination between instruments that will repay and those that will not. At structured-finance base rates, a four-nines reliability target demands discrimination on the order of 10,000 to 1. A three-nines target demands 1,000 to 1. Nothing in the published credit-prediction literature provides an affirmative basis for believing that discrimination of this magnitude was achievable with the data available at rating time. Retrospectively, the realized system fell short of the four-nines benchmark by roughly 90,000-fold. The framework accommodates the historical feasibility of corporate AAA ratings, where high base rates and rich information produce low required discrimination. Illustrative calibrations for contemporary collateralized loan obligations suggest that material tension between the precision target and the information environment persists. The central implication is that the AAA precision claim itself
Standard machine learning training presents data as discrete endpoint pairs, omitting the structure of the space between them. This paper introduces Transition Information Density (TID) -- the information content recoverable from structured intermediate states between categorically distinct training endpoints -- and Positional Identity, the defined location of an intermediate state on the A-to-B continuum. Both constructs are grounded in three empirical contexts: grapheme-color synesthesia, the Synesthesia Grid (a boundary-contour morphing algorithm instantiating TID in visual morphological space), and a four-condition training experiment across four representational mediums. Probes trained on structured interpolation at defined Positional Identities (C3) exhibit substantially lower intrinsic dimensionality than volume-matched controls (C2) in Phonetic/Linguistic (C3: 3.33 vs. C2: 10.81) and Semantic Description (C3: 4.59 vs. C2: 8.67) mediums. Visual and cross-modal mediums do not show this effect, establishing a modality boundary condition. A fixed-N=50 comparison confirms that Positional Identity structure, not sample count, drives the effect. Resolution N scales monotonically w
While motivated by structural problems in mathematical music theory, this article introduces a novel combinatorial framework that advances the classification of cyclic cubic bipartite graphs. We extend the classical study of Levi graphs by endowing their vertices with an internal algebraic anatomy -- specifically, treating them not as empty geometric nodes, but as defined subsets of a cyclic base space Z_n. This internal structure allows us to formalize and classify a highly restricted class of graph isomorphisms: those strictly induced by global affine bijections f(x) = ax+b (mod n) operating directly on the underlying base set. By applying this framework to generalized tone networks (Tonnetze) unrolled via the Chinese Remainder Theorem in composite dimensions -- specifically the classic 12-TET (3x4) and the decaphonic 10-TET (2x5) -- we reveal absolute geometric anchors for these spaces, namely the (9,4) and (6,5) systems respectively. We completely classify the topological orbits of these structured graphs, proving a fundamental architectural dichotomy: while the isomorphic landscape of 12-TET splits into an orientation-preserving family and an orientation-reversing chiral mirro
Holistic evaluation scores capture overall output quality but do not distinguish whether a model reproduced the structural form of a user's request from whether it preserved the user's specific intent. We propose a dimension-level intent fidelity evaluation framework, applied here through a structured prompt ablation study across 2,880 outputs spanning three languages, three task domains, and six LLMs, that separately measures structural recovery and intent fidelity for each semantic dimension. This framework reveals a systematic structural-fidelity split: among Chinese-language outputs with complete paired scores, 25.7% received perfect holistic alignment scores (GA=5) while exhibiting measurable dimensional intent deficits; among English-language outputs, this proportion rose to 58.6%. Human evaluation confirmed that these split-zone outputs represent genuine quality deficits and that dimensional fidelity scores track human judgements more reliably than holistic scores do. A public-private decomposition of 2,520 ablation cells characterises when models successfully compensate for missing intent and when they fail, while proxy annotation distinguishes prior inferability from defau
Modern large language models (LLMs) reach 60-70% diagnostic accuracy on complex clinical case benchmarks, but accuracy alone cannot distinguish stable clinically-grounded reasoning from pattern matching. We introduce clinical reasoning graphs, structured graph representations extracted from free-text LLM diagnostic traces using a domain-grounded ontology with 5 node types and 7 edge types. We apply this pipeline to 750 traces from five LLMs across 50 New England Journal of Medicine Clinicopathological Conference cases and three prompt conditions, and test whether diagnostic traces show stable structured reasoning patterns, or diagnostic schemas, for clinically similar cases. We operationalize this as higher graph similarity among clinically similar cases than among clinically dissimilar ones. Across 15 model-condition comparisons, within-cluster and between-cluster composite similarity are nearly equal, and no comparison survives multiple-testing correction; a component-level analysis finds any residual content signal far below schema scale. Graph similarity is also nearly identical for pairs of models that are both correct (0.488) and both incorrect (0.484), suggesting that graph
The core component of attention is the scoring function, which transforms the inputs into low-dimensional queries and keys and takes the dot product of each pair. While the low-dimensional projection improves efficiency, it causes information loss for certain tasks that have intrinsically high-dimensional inputs. Additionally, attention uses the same scoring function for all input pairs, without imposing a distance-dependent compute bias for neighboring tokens in the sequence. In this work, we address these shortcomings by proposing new scoring functions based on computationally efficient structured matrices with high ranks, including Block Tensor-Train (BTT) and contiguous Multi-Level Low Rank (MLR) matrices. On in-context regression tasks with high-dimensional inputs, our proposed scoring functions outperform standard attention for any fixed compute budget. On language modeling, a task that exhibits locality patterns, our MLR-based attention method achieves improved scaling laws compared to both standard attention and variants of sliding window attention. Additionally, we show that both BTT and MLR fall under a broader family of efficient structured matrices capable of encoding e
We report a structural convergence among four influential theories of mind: Kahneman dual-system theory, Friston predictive processing, Minsky society of mind, and Clark extended mind, emerging unintentionally within a practical AI architecture known as Agentic Flow. Designed to address limitations of large language models LLMs, Agentic Flow comprises five interlocking modules - Retrieval, Cognition, Control, Action, and Memory - organized into a repeatable cognitive loop. Although originally inspired only by Minsky and Clark, subsequent analysis showed that its structure echoes computational motifs from all four theories. This suggests that theoretical convergence may arise from implementation constraints rather than deliberate synthesis. In controlled evaluations, the structured agent achieved 95.8 percent task success compared to 62.3 percent for baseline LLMs, demonstrating stronger constraint adherence and more reproducible reasoning. We characterize this convergence through a broader descriptive meta-architecture called PEACE, highlighting recurring patterns such as predictive modeling, associative recall, and error-sensitive control. Later formalized as the Structured Cognit
Text-to-image (T2I) generation has advanced rapidly, yet faithfully capturing spatial relationships described in natural language prompts remains a major challenge. Prior efforts have addressed this issue through prompt optimization, spatially grounded generation, and semantic refinement. This work introduces a lightweight approach that augments prompts with tuple-based structured information, using a fine-tuned language model for automatic conversion and seamless integration into T2I pipelines. Experimental results demonstrate substantial improvements in spatial accuracy, without compromising overall image quality as measured by Inception Score. Furthermore, the automatically generated tuples exhibit quality comparable to human-crafted tuples. This structured information provides a practical and portable solution to enhance spatial relationships in T2I generation, addressing a key limitation of current large-scale generative systems.
In this paper, we study how to improve the zero-shot reasoning ability of large language models~(LLMs) over structured data in a unified way. Inspired by the study on tool augmentation for LLMs, we develop an \emph{Iterative Reading-then-Reasoning~(IRR)} approach for solving question answering tasks based on structured data, called \textbf{StructGPT}. In our approach, we construct the specialized function to collect relevant evidence from structured data (\ie \emph{reading}), and let LLMs concentrate the reasoning task based on the collected information (\ie \emph{reasoning}). Specially, we propose an \emph{invoking-linearization-generation} procedure to support LLMs in reasoning on the structured data with the help of the external interfaces. By iterating this procedures with provided interfaces, our approach can gradually approach the target answer to a given query. Extensive experiments conducted on three types of structured data demonstrate the effectiveness of our approach, which can significantly boost the performance of ChatGPT and achieve comparable performance against the full-data supervised-tuning baselines. Our codes and data are publicly available at~\url{https://githu
We replace the familiar Stokes vector by a tensor. This allows us to introduce, for example, polar-coordinate components of the Stokes vector. From the tensor we can derive the skyrmion field for mapping the polarization in structured light beams. These ideas have wider application in optics and in electromagnetic theory. We illustrate this with an example from non-paraxial optics and for Poynting's vector.
Real-world processes often involve interdependent objects that also carry data values, such as integers, reals, or strings. However, existing process formalisms fall short to combine key modeling features, such as tracking object identities, supporting complex datatypes, handling dependencies among them, and object-aware synchronization. Object-centric Petri nets with identifiers (OPIDs) partially address these needs but treat objects as unstructured identifiers (e.g., order and item IDs), overlooking the rich semantics of complex data values (e.g., item prices or other attributes). To overcome these limitations, we introduce data-aware OPIDs (DOPIDs), a framework that strictly extends OPIDs by incorporating structured data manipulation capabilities, and full synchronization mechanisms. In spite of the expressiveness of the model, we show that it can be made operational: Specifically, we define a novel conformance checking approach leveraging satisfiability modulo theories (SMT) to compute data-aware object-centric alignments.
Advances in manipulating the structure of optical beams enable the study of interaction between structured light and low-dimensional semiconductor systems. We explore the photocurrents in two-dimensional systems excited by such inhomogeneous radiation with structured field. Besides the contribition associated with the intensity gradient, the photocurrent contains contributions driven by the gradients of the Stokes polarization parameters and the phase of the electromagnetic field. We develop a microscopic theory of the photocurrents induced by structured light and derive analytical expressions for all the photocurrent contributions at intraband transport of electrons. The theory is applied to analyze the radial and azimuthal photocurrents excited by twisted light beams carrying orbital angular momentum, and possible experiments to detect the photocurrents are discussed.