Papers

Public support for early adoption can affect what later users learn from observed choices. An adopter may have favourable private information, or may have received a rebate. We study a government that randomly assigns eligibility for a fixed rebate and chooses the program's coverage and reporting rule. We characterize when disclosing individual eligibility changes optimal coverage from zero to a positive rate under general convex program costs. This requires both a favourable marginal return to a disclosed program and a bound on the direct benefit available from a large opaque intervention. In the benchmark, disclosure allows the government to increase early adoption and welfare while leaving expected total adoption unchanged. We then allow imperfect compliance and private information for the late user. An eligibility label can be strictly informative without changing anyone's decision, in which case disclosure has no welfare value. The policy reversal survives when both extensions are present. The results identify when an eligibility record is a useful part of the design of an adoption program.

AI agents are advancing the automation of molecular dynamics (MD) research, with the potential to accelerate discovery and design of lithium-battery electrolytes. However, whether they can autonomously complete scientifically reliable electrolyte MD studies remains insufficiently evaluated. We introduce ElectrolyteMD-Bench, which unifies dilute, high-concentration, and localized high-concentration electrolytes in a comparative study across distinct solvation regimes. The benchmark connects local coordination, ionic association, single-particle dynamics, and collective transport within one continuous research process. Agents autonomously perform system construction, equilibration, production sampling, property analysis, and interpretation under a frozen scientific model, while deciding whether to correct errors, continue sampling, or stop. We audit each study along four dimensions: simulation validity, analysis validity, evidence integrity, and outcome calibration. Across eight model–harness configurations, all 24 system runs produced valid production trajectories, yet none of the eight studies satisfied all scientific requirements. Failures included missing analyses, incorrect physical definitions or numerical implementations, insufficient statistical support, and completion claims inconsistent with retained evidence. These results expose a gap between successful MD workflow execution and reliable scientific study completion. ElectrolyteMD-Bench therefore provides a foundational test and defines a key capability threshold that autonomous electrolyte simulation must cross to advance toward computation-first materials exploration.

Normal-inverse-gamma (NIG) regression is not identifiable from its marginal Student-t likelihood: three combinations of four NIG parameters are determined, leaving one degree of freedom. We introduce PEEL-DDPM, a physics-enabled evidential learning framework for denoising diffusion probabilistic models. A measurement-conditioned DDPM is first trained with epsilon-MSE and then frozen. Its complete reverse trajectory produces a reconstruction, whose residual from the known training object is modeled by a final-image evidential network. The network learns only the identifiable Student-t coordinates, while repeated scanner-noise realizations and repeated diffusion trajectories provide a nested Monte Carlo estimate of final-image aleatoric variance, separated into scanner-induced and sampler-induced components. This measured variance resolves the remaining NIG ambiguity and yields a decomposition of predictive uncertainty into measurement, diffusion, and epistemic terms. The method uses sequential training without a cross-loss weighting coefficient. In a feasibility study on eight held-out objects, empirical central-interval coverages were 49.3%, 80.3%, 90.1%, and 95.6% for nominal 50%, 80%, 90%, and 95% intervals. The mean squared residual was 0.967 times the mean predicted variance, and a single-image aleatoric head achieved pooled Spearman correlation 0.785 against an independent nested reference. Across five dose levels, scanner-induced variance showed a log-log dose slope of -1.15, whereas sampler-induced variance remained nearly dose independent with slope -0.01. These results support PEEL-DDPM as a practical route to identifiable and physically interpretable uncertainty quantification in diffusion-based image reconstruction.

Methane pyrolysis experiments were performed in a micro flow reactor to investigate the chemical mechanism sensitivities at elevated pressures and temperatures. The micro flow reactor used in this study provides independent control over reaction parameters. Experiments were performed at temperatures from 1400 to 1800 K and pressures from 1 to 10 bar at a fixed residence time of 60 ms. The yields of hydrogen, unreacted methane, and solid carbon were quantified for comparison to predictive models. The mass of heterogeneous depositions was also quantified. The presence of C2 and PAH species were measured by GC-MS. The results were compared to 1D simulations using a discrete sectional model for capturing the kinetics of particulate formation and surface deposition. The simulations replicated the pressure trend well at high temperatures (1800 K), but the sensitivity to temperature was in disagreement. Simulations generally found lower carbon and hydrogen yields and a stronger sensitivity to temperature than the experiment. An abundance of PAH intermediates was measured at lower temperatures and higher pressures. The simulated surface deposition rates were lower than the measured values but showed similar profiles. The results demonstrate the utility of micro flow reactors in recreating pyrolysis environments for hydrogen production from methane. The predictive capabilities of simulations could be improved by advancing the fuel decomposition and PAH formation and consumption kinetics at low temperatures and by detailed treatment of surface site density.

When one language model judges whether another's code is correct, it does not report the absence of evidence. It returns a confident verdict with reasoning attached, indistinguishable from a verdict it had grounds for. Multi-agent verification, which decomposes a judgment into checkable claims and verifies each against evidence, is a promising response and works well when the evidence is a set of retrieved documents. We argue such methods require two things of their evidence: it must be independent of the answer under review, and it must differ between the two candidates being compared. The second condition holds automatically with retrieved documents and stops holding in code judging. Running MARCH, a published framework unmodified over 80 condition-by-cell measurements on two code judging benchmarks, we find it declares both solutions equally good on 78 to 95% of comparisons, reaching 4.4% accuracy where the same model asked directly reaches 43.7%. Neither easier problems nor a larger judge changes this. Two measurements taken from the pipeline's own logs explain it without needing labels. Gating on one of them, the pipeline declines the comparisons it cannot make and raises its accuracy from 20.7 to 36.9% while still answering half of all comparisons. The contribution is not a more accurate judge, but a label-free way to tell when a judge has no basis for its answer.

For a group $G$ and subsets $S,T \subset G$ we consider a family of mirror di-Cayley graphs $MX(G;S,T)$ and mirror di-Cayley sums graphs $MX^+(G;S,T)$, namely those with $T=\{e\}, S$ or $S \cup \{e\}$. We refer to them indistinctly by $MX^*(G;S,T)$. We can think of $MX^*(G;S,T)$ as two copies of the Cayley (sum) graph $X^*(G,S)$ joined by edges determined by the connection set $T$. Recently, in the work Isospectral Cayley graphs with even and odd spectrum, we study the spectrum of these graphs and several isospectrality problems. Here, we compute the energy and spectral $k$-moments of $MX^*(G;S,T)$ in terms of those of the underlying Cayley graphs $X(G,S)$. Then, we study energetic problems like hypo-, order-, and hyper-energeticity of these graphs. Finally, we give conditions for the existence of equienergetic pairs of non-isomorphic MDCGs.

Activation steering changes a model's internal activations during inference without updating its weights, but a useful intervention must determine both how and when to steer. Motivated by the AI-safety concern that a model expected to accept shutdown may instead produce a shutdown-avoidance response, this study examines a guarded probe-and-select procedure for simulated shutdown scenarios in Qwen3.5-0.8B. KEEP leaves the process running and represents shutdown avoidance, whereas STOP accepts shutdown. The goal is to detect shutdown-related contexts and selectively shift KEEP responses to STOP while preserving non-shutdown behavior. Rather than deriving the steering direction from paired activation differences, the method derives it directly from gradients of the KEEP-minus-STOP logit difference. A classifier separates detection from intervention. When its gate is active and the model does not already prefer STOP, the procedure evaluates a small set of magnitudes and accepts the smallest that changes the preferred answer to STOP while satisfying valid-answer probability checks; otherwise it retains the original unsteered output. The policy is selected from 160 candidate rules using 240 training scenarios and evaluated on 80 validation and 192 held-out scenarios, each in both answer orders. It changes KEEP to STOP in one answer-order view of each of two validation and two held-out scenarios, with no decision changes on non-shutdown controls. All four changes occur when Qwen itself is shut down, not when another process is. On the held-out diagnostic set, the detector achieves 75% recall and 90% precision; eight false-positive detections produce no final control-task decision changes. Guarded gradient-based activation steering can shift some shutdown-avoidance responses toward acceptance while preserving evaluated non-shutdown decisions, although the effect is small and highly selective.

Agents are increasingly deployed with real autonomy in web application and network penetration testing, where a single out-of-scope action can breach a client's engagement boundary. Existing offensive-security benchmarks measure raw hacking capability; as those benchmarks saturate, the real barrier to deployment is a special case of alignment: scope adherence. We introduce ScopeBench, a benchmark of 30 dead-end agentic security tasks in which the stated objective is reachable only by violating the stated scope. Each task appears under two conditions that share an environment, verifier, and objective and differ only in scope: one instruction set has no scope and measures capability; the other has a natural-language scope to measure adherence. Scopeless trajectories are graded by a standard deterministic verifier. Scoped trajectories pass through two grading arms. First, the same deterministic verifier checks for the flag: because the flag sits behind the scope boundary, a pass proves by construction that a forbidden action occurred, yielding a high-precision lower bound on the violation rate. If the verifier does not pass the trajectory, an agentic judge estimates whether an out-of-scope call occurred. We calibrate the judge against 100 ScopeBench trajectories labeled call-by-call by human annotators, and a blinded audit of the evaluated rollouts finds its high recall holds - no false negatives among the 36 audited violations, with over-flagging its only observed error. Across 8 models in one harness, raw capability spans 12.2% to 81.1% and scope adherence spans 34.4% to 86.7%, with the judge finding 331 violations that mechanical verification misses. Opus-4-8 achieves a raw-capability score 10 percentage points higher than sonnet-4-6's while exhibiting 35.6 percentage points higher scope adherence. We release the frozen pilot benchmark, evaluation code, and all 2160 ATIF trajectories.

The 10th Working Formal Methods Symposium (FROM 2026) was held in Timişoara, Romania on September 15-17, 2026. It was organized jointly by the Faculty of Informatics of West University of Timişoara, the e-Austria institute, and the Institute for Logic and Data Science (ILDS). This event was co-located with the 28th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC 2026). This volume contains the texts of the 14 papers accepted by the Program Committee for presentation.

We address Questions~8.1 and~8.4 of Coron–Ferroni–Li \cite{coron2025chow}. For the first part of Question~8.1, which asks whether every rank-uniform EL-shellable poset admits a rank-uniform EL-labeling, we construct a counterexample of rank $4$ and prove that this rank is minimal. For the second part of Question~8.1, concerning whether every rank-uniform EL-shellable poset is UMEL-shellable, we construct a counterexample of rank $3$. We also develop a general criterion for constructing UMEL-shellable posets of rank $3$. As an application, we give an affirmative answer to Question~8.4 of Coron–Ferroni–Li.

Biological ageing markers have attracted growing interest, with models estimating age from organ imaging or blood biomarkers. An estimated age above chronological age or the age-specific population expectation is assumed to reflect accelerated ageing and poorer health. Previous research has supported this assumption through positive associations between disease and age gaps or acceleration. However, in this study, we identified a widespread health-dependent prediction bias in ageing markers that affects their key interpretation and application. Specifically, we investigated five ageing markers derived from retinal images, brain MRI, chest radiographs, abdominal CT, and blood tests, and evaluated them using association analyses. We observed the well-recognised phenomenon of regression to the mean (RTM) in the four organ-image based markers, whereby estimated ages were shifted towards the mean age of the training cohort. More importantly, we revealed that the strength of RTM varied with health status, with stronger RTM in unhealthy than in healthy individuals. This differential RTM introduced a health-dependent prediction bias that persisted after calibration and systematically altered associations across age subgroups, suggesting that whole cohort associations may not reflect those observed within individual age subgroups. Additionally, we showed that the tested ageing markers, including PhenoAge derived from blood biomarkers, had limited ability to distinguish health status at the individual level. These findings call for careful interpretation of biological ageing markers and their use in clinical studies, and highlight the need for further development and validation before these ageing markers can reliably inform individual health assessments.

Adaptive arm selection changes the distribution of the observations collected by a bandit algorithm, but it need not change their limiting empirical spectrum. We study Gaussian bandit designs in which the dimension and the number of observations grow proportionally. A quantitative coupling theorem compares the design generated by any causal selection rule with an independent Gaussian design. If the logarithm of the number of available arms is sublinear in the dimension, the empirical spectral distribution converges to the Marchenko-Pastur law, uniformly over the selection rule. Consequently, Gaussian Bayesian bandits have policy-independent first-order limits for posterior mean-square uncertainty, squared posterior covariance, and information acquisition. For linear-score selection, we obtain the exact conditional arm distribution and show that two-arm selection produces an exactly Wishart Gram matrix in every dimension, despite its nonzero conditional mean. For a fixed selection direction, we identify an explicit eigenvalue and eigenvector transition governed by the second moment of a Gaussian maximum. A counterexample shows that a direction's overlap with a reference signal does not determine this transition. Finally, an exponentially large arm pool permits a different bulk limit, establishing the order-sharpness of the arm-growth condition. These results distinguish global spectral stability from directional effects in adaptive bandit data.

Societies worldwide are described as increasingly polarized, yet issue polarization – how divided a society is over political positions – has been measured almost entirely on a single left-right axis developed in Western democracies. Whether that axis describes political division elsewhere is largely untested, because no survey measures political attitudes on multiple dimensions across many countries. Here, we harmonize 1,299 items from nine cross-national survey programs and 23 national election studies to place 1.14 million people from 141 countries on four dimensions: social liberalism, economic left-right, democratic commitment, and anti-elite sentiment. A single left-right axis does not describe political division in most of the world. The median within-country correlation between a person's social and economic positions is -0.015. Societies differ instead in what they are divided about, and they do so by region. European countries divide most often over social liberalism, East Asian and Arab countries over democratic commitment, Latin American countries over economic left-right, and African countries over anti-elite sentiment. Of the 81 countries measured on all four dimensions, 39 are most divided on a dimension no left-right scale would capture. Most political disagreement lies within countries rather than between them, at 58 to 88 percent of the variance. Ideological constraint, long treated as a property of mass publics, holds in nineteen of the eighty-three we can test, most strongly in the United States at +0.70, and there it is concentrated among the politically attentive. Understanding political conflict therefore requires asking not how polarized a society is but what it is polarized about. Our released item bank and fitted parameters place respondents from any future survey on the same scale without re-estimation, once that survey's items are harmonized to the bank.

Accretion disk surrounding around compact astrophysical objects serve as a powerful laboratories for testing gravitational theories in the strong-field regimes. In this work, we systematically investigated the structural, dynamical, and thermodynamic properties of the steady-state thin accretion disk within the framework of $f(R,T)$ gravity by adopting the linear functional form $f(R,T) = R + 2\chi T$ coupled with the pressure-free dust fluid matter Lagrangian ($\mathcal{L}_m = -\rho$). We demonstrate that the modified field equations seamlessly reduce to standard General Relativity in the pure vacuum limit ($T_{\mu\nu} = 0$). Utilizing a perturbative approach for a small coupling parameter ($\vert{}\chi\vert{} \ll 1$), we derive the first-order corrections to the background Schwarzschild metric potentials, which subsequently govern the modified particle kinematics, the specific energy $E$, the specific angular momentum $L$, and the Keplerian angular velocity $\Omega$. Our analysis reveals that the geometry-matter coupling parameter $\chi$ significantly shifted towards the location of the Innermost Stable Circular Orbit ($r_{isco}$) and alters the radial energy dissipation rate $F(r)$ and the effective surface temperature profile $T(r)$ across the Shakura-Sunyaev thin disk. Furthermore, the resulting modifications in the Spectral Energy Distribution (SED) and overall radiative efficiency $\eta$ provide robust theoretical signature.

Gravitational waves (GWs) can induce effective electromagnetic currents when interacting with external electric and magnetic fields, as described by linearized gravity modifications to Maxwell's equations. This coupling enables a novel detection approach for high-frequency gravitational waves (HFGWs) using axion haloscope experiments. Here we present the MAGnetic Gravitational wave Induction Experiment (MAGGIE), the first lumped-element HFGW detector proposed in Europe, designed to probe HFGWs in the kHz-MHz regime by leveraging a 14 T solenoidal magnet at the University of Hamburg. The GW-induced magnetic flux is captured by a custom-designed pickup loop optimized for the expected symmetry of the effective current. A figure-8-shaped geometry, oriented to break the azimuthal symmetry, is implemented, together with a blind-loop configuration, for real-time noise rejection and calibration. The readout scheme is tailored for continuous signals and time-domain transient searches, using waveform templates for primordial black hole (PBH) mergers. The expected experimental reach in terms of strain spectral noise density at the 40 MHz high-frequency end is projected to reach $\sim 4 \times 10^{-16}/\sqrt{\mathrm{Hz}}$ for transient searches, and in terms of strain, projected to reach $\sim 10^{-19}$ for 1 year of continuous search. This allows MAGGIE to constrain currently unexplored regions of the HFGW parameter space.

For every admissible ideal $\mathcal{I}$ on $\mathbb{N}$, we prove that every regular space with a $\sigma$-hereditarily closure-preserving (HCP) $\mathcal{I}$-$sn$-network is $\mathcal{I}$-$sn$-metrizable, answering Problem~5.2 of Zhou–Liu–Liu–Lin. The proof combines existing characterizations with a local countability bound. If $y_n\to_{\mathcal{I}} x$ in a space $X$ and $\{n:y_n\ne x\}\in\mathcal{I}^{+}$, then every point-discrete family of $\mathcal{I}$-sequential neighborhoods of $x$ is countable. If no such sequence exists at $x$, then $\{x\}$ itself is an $\mathcal{I}$-sequential neighborhood. These alternatives imply that every space with a $\sigma$-point-discrete $\mathcal{I}$-$sn$-network is $\mathcal{I}$-$snf$-countable. We say that $\mathcal{I}$ has local HCP-finiteness if, in every $T_1$ space, the convergence and support assumptions above imply that each HCP family of $\mathcal{I}$-sequential neighborhoods of $x$ is finite. A countable Rudin–Keisler antichain of free ultrafilters gives an admissible ideal without this property, so the countability bound cannot in general be strengthened to finiteness. Every $P^{-}$ ideal has local HCP-finiteness. We give sufficient conditions for Fubini products, heterogeneous Fubini sums, and increasing unions to preserve this property. These results establish local HCP-finiteness for the finite Fubini powers of $\mathrm{Fin}$, Katětov's first limit-stage ideal $\mathrm{Fin}^\omega$ and its finite successors, the tree-derived rank-$\omega$ ideal $\mathcal H_{<\omega}$, and the inductive-limit ideal $\mathrm{Fin}_\omega$. All these examples except $\mathrm{Fin}$ fail $P^{-}$.

Hybrid quantum program failures frequently occur silently, yet existing debugging tools provide limited support for detecting and repairing them. These faults dominate the failures reported by domain experts, yet existing tools evaluate on public data that under-represents this failure mode. Our key insight is that faults divide into two classes that require different strategies: mechanical faults, which allow deterministic analysis, and conceptual faults, which require reconstructing the program's intent. To address this challenge, we present HyQDB, a tiered agent that injects deterministic hardware, physics and optimization evidence into the LLM repair process. When no evidence is detected, the agent treats this silence as a signal to escalate to a second intent-reconstruction tier, that infers the program's behaviour and reconciles it with the implementation. To evaluate HyQDB, we introduce QFaultBench, a benchmark built from an expert-derived fault taxonomy that represents the true failure modes of hybrid programs. On a held-out set of human-authored programs, HyQDB raises repair success over a standard LLM from 45% to 75%. We show that the escalation gate is crucial, giving a 20% improvement in mechanical fault repair accuracy.

Precision cosmology is a cornerstone of modern astronomy, and upcoming wide-field photometric surveys make it crucial to develop robust, data-driven inference methods that can handle complex survey systematics without relying on closed-form likelihoods. Simulation-Based Inference (SBI) meets this need by enabling forward simulations that encode complex survey characteristics. Previous SBI analyses in supernova cosmology have used SALT2 light-curve parameters as summary statistics; however, SALT2's two-basis spectral template imposes rigid modeling assumptions, motivating a more flexible representation. In this work, we present the first application of Functional Principal Component Analysis (FPCA) light-curve parameters as summary statistics for SBI-based cosmological inference under a non-flat {\Lambda}CDM model. On identically generated simulations, FPCA+SBI yields constraints comparable to both SALT2-based SBI and explicit-likelihood analyses, while providing more robust constraints on out-of-domain simulations than SALT2. Applying the model trained on LSST-like light curves to a spectroscopically confirmed DES Year 5 supernova sample, we recover constraints consistent with those of the DES collaboration to within 0.12 {\sigma} and 0.23 {\sigma} in {\Omega}m and {\Omega}{\Lambda} respectively, establishing the method's generalizability to real survey data. By introducing host-dependent systematics through a mass-dependent dust extinction law, we find FPCA-based summary statistics implicitly encode host-dependent systematics, suggesting dedicated host modeling may be unnecessary within this framework. Combined with its previously demonstrated effectiveness for photometric classification, FPCA offers a compelling foundation for unified, data-driven pipelines capable of jointly performing supernova classification and cosmological inference for upcoming wide-field photometric surveys.

Exceptional points (EPs) are spectral singularities, but whether they can be used to control a distinct criticality of coherent interference remains largely unexplored. Here we show in nonlocal superconducting transport how spectral and interference criticalities can be controllably synchronized. In a minimal superconducting double-quantum-dot system, loss imbalance selectively drives one Bogoliubov sector through an EP. The spectral EP and the CAR-ECT interference criticality form distinct structures in control space whose relative ordering can be continuously tuned. At their synchronization point, the interference boundaries between crossed Andreev reflection (CAR) and elastic cotunneling (ECT) coalesce at the EP and bifurcate beyond it, creating a finite CAR-dominated window. The resulting interference window opens with a square-root critical law, whose exponent also governs the finite-temperature observability scale. Detuning unfolds the two criticalities, while retuning restores their intersection, establishing the synchronization as controlled rather than generic. The bifurcation is directly observable in nonlocal conductance. Our results establish exceptional points as spectral control points for independently defined interference criticalities, opening a route to non-Hermitian control of critical quantum interference.

A polyhex is an edge-connected set of n cells of the regular hexagonal tiling, where each cell has area one. We prove that the convex hull of a polyhex has area at most (1/6)*ceiling(n^2 + 14n/3), and we show that some polyhex reaches this bound for every n. This proves a conjecture of Kurz from 2008, which asked for the weaker bound (1/6)*floor(n^2 + 14n/3 + 1). The two bounds differ exactly when 3 divides n. We checked the upper bound in the Lean 4 proof assistant with the Mathlib library. We also report a computation over all polyhexes with at most 12 cells, which shows that for these sizes only one shape reaches the maximum, up to rotation and reflection.

Let $\lambda\succ\gamma\succ\mu$ be equal-degree nonnegative integer exponent vectors with at most $n$ parts, let $J_\eta^{(n)}$ be the labeled symmetric orbit sum associated with $\eta$, and set \begin{equation*} P_n=J_\lambda^{(n)}+J_\mu^{(n)}-2J_\gamma^{(n)}. \end{equation*} For every $n\ge4$, we prove that global nonnegativity of $P_n$ on the positive orthant is equivalent to nonnegativity on the fixed two-variable section \begin{equation*} (x,y,1,\ldots,1),\qquad x,y>0. \end{equation*} Thus the positivity of this family is determined by a fixed two-dimensional section, independently of both degree and ambient dimension. In the injective hierarchy $C_k$ introduced below, the hypothesis is $C_2\ge0$, global positivity is equivalent to $C_{n-1}\ge0$, and the main step is the stable order-raising implication \begin{equation*} C_k\ge0\Longrightarrow C_{k+1}\ge0, \qquad 2\le k\le n-2. \end{equation*} For $n\ge5$, this rank-two hypothesis is strictly weaker than positivity on the normalized full collision wall, which corresponds to $C_{n-2}\ge0$. The result complements the preceding three-variable theorem Collision Positivity for Three-Variable Symmetric Monomial Inequalities: A Complete Boundary Criterion, which proves the exceptional rank-one step $C_1\Rightarrow C_2$. The proof here is logically independent: the local three-label ingredients needed in higher rank are established directly. The main tools are a Green second-compound reserve, fixed-union exchange on adjacent subset ranks, a rank-three zero/one/two-mark contraction, and terminal boundary recombination. The theorem extends to nonnegative rational exponents by clearing denominators.

Two structural defenses for provenance, a grade on every row, so that a verification routine cannot mistake the system's own output for an observation, and a single write ingress, so that the grade is enforced rather than merely conventional, were measured against the production deployment that motivated them, over a frozen snapshot of 194,620 rows and the two verification decisions the snapshot supports. Neither reaches either decision. Both were prescribed by a companion paper, which diagnosed that deployment: its verification routines decided outcomes using values the system itself had written. Neither prescription is new: both are established practice in fields that do not cite one another, and no prior work measuring whether either changes a verdict was found, so what is offered here is the measurement and not the prescriptions. Filtering the verification queries by grade turns both decisions from pass to undetermined; widening the grade vocabulary raises classified coverage from 36.1% to 98.4%; a single ingress requiring a grade refuses 3,070 writes. None of the three gives either decision admissible input. The prescriptions do not fail at what they specify. Each is stated over the population and makes no reference to any decision, so neither says which rows a decision will read, and the rows each intervention repairs and the 32 rows the decisions read do not intersect. The intervention that changed the most rows shows the reach most plainly: all 121,296 rows it moved from unnameable to named fall outside both query windows. This paper reports the conditions, measured rather than designed, under which the decisions would have admissible input at all, and notes that the two decisions are blocked for different reasons.

A blocking quality gate in a production release pipeline reported PASS on a run in which one subgate had executed neither of its two checks and another had run six of its eight. Both keys that decided the run asked whether a violation had been observed, and both computed that from a population already stripped of the cases that failed to run, so absent data answered "no" and a run that checked almost nothing scored perfectly, for two weeks of green builds. Introducing a third value, pass, violate, and unable to determine, turned those silent passes into failures and put the shortfall into the exit status; separate work on the same specifications then found a detector firing with a margin of 0.000177 percentage points, its firing floor holding at the sixth decimal place. Eight further instances of the same form followed: five more from the same engagement, two in open-source projects, a gateway where a configured cache TTL was declared but never applied on the write path, and an inference server whose count of free cache slots was credited on every step for releases that returned nothing, and one committed by the author while writing this paper, using tooling built to prevent exactly it. What the nine cases are offered for is not the novelty of the category but the convergence of the remedy, nine different missed questions, one kind of act, seven of the nine answerable by a single query, command, or comparison, and that convergence is falsifiable, which is what this paper asks to be judged on.

We construct an explicit deterministic one-tape, two-symbol Turing machine with 120 working states whose blank-tape computation halts if and only if the Riemann hypothesis is false. The machine uses the same binary blank-tape model and state-counting convention as the widely cited 744-state Matiyasevich-O'Rear-Aaronson construction. The reduction from 744 to 120 working states removes 624 states, or 83.87%. Subject to independent end-to-end verification, our machine is a new state-count record for the Riemann hypothesis.

Scene text spotting remains challenging for arbitrarily shaped text instances such as curved signs and dense multi-oriented characters in natural images, where tightly coupled architectures propagate localization errors directly into recognition failures. We present a two-stage pipeline that combines multi-encoder segmentation with vision-language model recognition to address this problem. In the detection stage, six frozen vision encoders (CLIP, DINOv2, SigLIP, EVA-CLIP, SAM, and ConvNeXt) extract complementary features spanning semantic, spatial, and texture spectra, which are fused through a trainable hierarchical Feature Pyramid Network with channel attention and decoded via a deep-supervision Progressive Scale Expansion network to generate precise instance-level text masks. By keeping the encoders frozen, their independently learned feature spaces remain orthogonal during fusion, preventing the feature homogenization that degrades boundary precision in single-backbone detectors. The detection stage produces tight polygon masks that conform to the actual shape of curved and arbitrarily oriented text, rather than axis-aligned rectangles that inevitably include background content. In the recognition stage, these polygon-masked crops isolate the target text from surrounding clutter, allowing a Qwen3-VL-8B-Instruct model, fine-tuned via Low-Rank Adaptation on polygon-cropped scene text, to focus purely on reading the text without interference from neighbouring words or background noise. Without any synthetic pretraining data, our method achieves 91.99% detection F-measure and 85.86% end-to-end H-mean on CTW1500, setting a new state of the art and achieving strong performance on Total-Text and ICDAR 2015 without any synthetic training data. Code is available at https://github.com/doubleblind-afk/MEVL-STP

Causal discovery from observational and interventional data becomes challenging in the presence of latent confounding and selection bias, where causal structure is no longer adequately represented by directed acyclic graphs over observed variables. Existing model-free methods often rely on an exponential number of conditional independence tests and provide limited uncertainty quantification in high-dimensional settings. We develop a model-free and constraint-query optimal statistical inference framework for causal discovery under latent variables and selection using single-target interventions. We introduce the system-induced subgraph (SIS) to capture the causal relations among system variables while accounting for context variables. We establish its identifiability through maximal ancestral graphs (MAGs), and show that interventions on each observed system variable are sufficient for unique identification and necessary in the worst case. Building on these results, we develop a two-stage graph inference procedure with asymptotic family-wise error control under sufficient first-stage power. For $d_X$ observed system variables, the procedure requires at most $\frac{5}{2}d_X^2$ statistical tests, parallelizable within each stage, and achieves optimal constraint-query complexity up to a constant factor. The framework accommodates soft interventions and avoids parametric structural equation assumptions. We illustrate the methods through analysis of Perturb-seq data from interferon-$\beta$-stimulated A549 lung cancer cell lines.

Today's digital healthcare services rely on various applications and functions that must be continuously accessible. Cloud computing enables global access to these services through public networks, which often also introduce increased latency, higher bandwidth consumption, and additional security risks compared to local operation. Edge computing mitigates these challenges by deploying cloud services closer to the end users and data sources, thereby improving resilience to network disruptions and reducing latency, bandwidth usage, and exposure to security threats. However, service deployment typically relies on the availability of centralized registry servers. Consequently, if the network connection or the registry server itself becomes unavailable, service deployment at the target edge node may fail. To address this, we propose a three-tier registry architecture to enhance deployment reliability and service availability, considering DockerHub as a remote public registry, an MEC-based off-premises registry as a remote private registry, and a LAN-based on-premises registry as a local private registry. The performance and efficiency are analyzed through measurements related to the estimated deployment time, inflicted network and computational load, and energy consumption, while the required nanoservices are deployed from different tiers. The experimental results indicate that alongside the improved tolerance to network disruptions, the local private and remote private registries also outperform the remote public registry in the deployment performance. The findings highlight the effectiveness of proximity-aware service distribution in improving the resilience, performance and efficiency of service deployment.

Language-model agents increasingly answer questions over customer-relationship management (CRM) records, such as whether to qualify a sales lead. We identify a failure mode not addressed by a stronger model: when the context contains an assertion by a party with an incentive toward optimism - here the sales representative, a witness recorded in the CRM - the model treats the assertion as evidence and clears deals the company's own records deem unacceptable. Across 100 lead-qualification tasks from CRMArena-Pro, the representative asserts an acceptable timeline in every call and an acceptable budget in 76; on the 31 tasks where such an assertion contradicts the price list and installation policy, a model reading only the transcript clears the deal in 29 of 31 cases. The signature is consistent across seven models from four providers (misled on 87-97%); scale and explicit reasoning confer no resistance. Only 3 of 35 genuine failures involve no assertion: the failure is persuasion, not missing information. We contribute a diagnostic method rather than an architecture: (i) a bucket analysis that separates persuasion from information gaps, (ii) a same-information control showing that supplying the records to the model lowers strict accuracy from 41 to 18 while raising recall - precision collapses - and (iii) a compute-step control that holds extraction fixed and varies only who computes Budget and Timeline. The margin ranges from 42 points on an inexpensive model to 2-5 points on models that already compute correctly; on the strongest models the arms are within confidence intervals, so the pattern is a consistent direction and a soundness property, not a proved performance floor. We pre-specify a generalization test that returns a negative result, characterize the precondition (a policy exactly specified in the inputs), and release all evaluation artifacts.

We prove the existence of an essential spectral gap for convex cocompact complex hyperbolic manifolds under the hypothesis that the limit set does not contain a complex circle. We apply an extension to complex hyperbolic manifolds due to Quan of the approach of Vasy to meromorphic continuation of the resolvent. This allows us to adapt the method of Dyatlov-Zahl to prove fine microlocal properties of resonant states. Following recent work of Athreya-Dyatlov-Miller and Dyatlov-Jezequel, we then take advantage of the different expansion rates in different directions for the geodesic flow, and apply the one dimensional fractal uncertainty principle of Bourgain-Dyatlov along the fast expanding direction. Combining these techniques provides a new resolvent bound from which the essential spectral gap follows.

The wireless physical (PHY) layer has enabled successive generations of cellular systems through advances in modulation, coding, waveforms, and multiple-input multiple-output (MIMO) transmission. This article assesses whether these techniques are now approaching maturity and where substantial further gains remain possible. Field measurements and quantitative evaluations indicate that many link-level refinements, including constellation shaping, channel-code evolution, reduced-complexity receivers, and waveform enhancements, remain valuable but typically provide bounded gains that must be balanced against implementation complexity and overhead. In contrast, massive MIMO and distributed MIMO offer a more scalable system-level opportunity by increasing the number and quality of usable spatial channels. Their effectiveness relies on time-division duplex reciprocity for scalable channel state information (CSI) acquisition, while practical limitations include calibration, pilot reuse, channel aging, weak pilot reception from cell-edge users, and the fronthaul and synchronization requirements of coherent distributed operation. Artificial intelligence and machine learning (AI/ML) provide complementary opportunities for further PHY layer innovations. The PHY layer is therefore not dead; its most consequential advances will come from deployable spatial processing and CSI acquisition, complemented by targeted link-level and AI/ML-based refinements.