Frequency-domain thermoreflectance (FDTR) is a laser pump-probe technique widely used to measure thermal properties at the micro- and nanoscale; however, it relies on a complex data analysis procedure that demands substantial domain expertise and is susceptible to subtle human errors. Here, we present Vibe-FDTR, an agent-oriented framework that enables large language model (LLM) agents to perform reliable and reproducible FDTR analyses directly from natural language requests. This framework couples a configuration-driven FDTR code package, which enforces physical and parametric consistency, with procedural agent skills that translate user intentions into organized and verifiable analysis steps. We evaluate Vibe-FDTR using a controlled benchmark with two levels: synthetic single-step tasks and real-data multi-step tasks based on measurements of gold-coated graphite samples. Across the two levels, agents using Vibe-FDTR achieve success rates of 100% and 98.9%, respectively. In sharp contrast, ablating skills (Code-agent) reduces performance to 91.4% and 36.7%, which drops further to 38.6% and 0% when the domain package is also omitted (Agent-only). Beyond success rate, Vibe-FDTR also reduces computational cost by 87.7% relative to the Code-agent variant and cuts execution time by more than 60%. Finally, an optional expert mode supports experimental planning via autonomous sensitivity and uncertainty evaluations, and formulates physically grounded recommendations for underspecified tasks. These results demonstrate that encapsulating domain code and expert knowledge into agent skills offers a promising route toward low-barrier, autonomous, and trustworthy thermal metrology.
Numerous unsupervised domain adaptation (UDA) algorithms exist, but for clinical practice, selecting the best-suited one along with proper hyperparameters often remains unclear, as the unlabeled deployment (target) domain prevents direct evaluation. We propose a label-free criterion that jointly selects the algorithm and hyperparameters for UDA. Given a pool of candidate models from multiple algorithms trained with different hyperparameters, our approach scores each candidate against an agreement reference, and selects the one with the highest score. The agreement reference is constructed in two levels without using target labels. First, we leverage multiple label-free selection signals, using each to nominate a model within every algorithm. Second, the nominated models are aggregated across algorithms to form a reference prediction for each unlabeled target sample. The candidate whose predictions agree most with this reference is then selected for deployment. Experimental results on four brain MRI and four chest X-ray datasets across seven clinically relevant transfer scenarios show that our method achieves better selection performance than individual validators and remains effective across different algorithm pools. Our approach takes a step towards practical, label-free algorithm selection for clinical deployment of UDA. Our code is open sourced at https://github.com/xiongyiheng/Complete-Unsupervised-Domain-Adaptation-Pipeline/tree/main/two-level-algorithm-selection.
Accurate Surface Solar Irradiance (SSI) estimation is increasingly important for photovoltaic energy monitoring and forecasting. The recently introduced Meteosat Third Generation (MTG) satellite constellation provides imaging data with higher spatial resolution compared to the Meteosat Second Generation (MSG) satellite constellation, but its benefits for machine-learning-based SSI retrieval are not well established. We compare multi-resolution convolutional neural network models for 10-minute SSI retrieval over Northern Europe (Estonia) using either MSG/SEVIRI or MTG/FCI satellite imagery. We evaluate model performance against ground-based pyranometer measurements from eight Estonian meteorological stations using site-based cross-validation with a temporally independent test year and multiple training seeds. Model performance is also compared with the SARAH-3 physics-based satellite SSI product. The FCI-only model significantly outperformed the SEVIRI-only model under overcast and cloudy conditions, reducing RMSE by 5.1 W/m^2 and 6.5 W/m^2, respectively. However, under partly cloudy or clear skies, there was no statistically significant difference in RMSE between the FCI-only and the SEVIRI-only models. In all-sky conditions, the RMSE of the FCI-only model was 5.1 W/m^2 lower on average, but this difference was not statistically significant after Bonferroni correction. Compared with physics-based SARAH-3, the FCI-only model yielded skill scores of 28% under overcast conditions, 19% under cloudy conditions, and 17% overall. Furthermore, both models underperformed SARAH-3 in clear-sky conditions. These results show that higher-resolution MTG/FCI imagery improves CNN-based SSI retrieval when clouds dominate irradiance variability, but also indicate that higher resolution alone is insufficient to address clear-sky limitations in machine-learning-based SSI retrieval.
Corporate annual reports describe hedging through transactional, policy, accounting, and explicit non-use language. This study presents AWARE-FX, the foreign-exchange application of the Auditable Weak-supervision and Aggregation framework, for constructing traceable firm-year disclosure measures. Professional-source retrieval, evidence-state rules, channel classifiers, and top-three aggregation link each score to supporting passages. The application covers 24,909 Hong Kong firm-years from 2008-2025 and 543,527 candidate snippets. Evaluation combines weak-label held-out tests, three-seed encoder comparisons, a 2023-2025 temporal test, calibration diagnostics, selective prediction, and a stratified 300-snippet audit coded by one researcher. The paired temporal tests do not detect statistically significant differences between FinBERT and ModernBERT. The negation-aware lexicon has higher broad-task audit F1 than strict-gate FinBERT and Qwen3-8B, demonstrating that learned models do not uniformly improve on domain rules. At 80% temporal coverage, retained-sample F1 increases by 0.050-0.077, although the study does not measure human review time or deployment impact. Reproducible Qwen3-8B results show substantial variation across evidence channels. Linked exposure associations provide exploratory external validation, with sensitivity to the multiple-testing family. The scores measure detected hedging disclosure rather than hedge notional or causal effectiveness. The contribution is an evaluated measurement workflow with inspectable evidence and explicit validation limits. Independent duplicate annotation and retrieval-recall assessment remain necessary for stronger reliability claims.
Knowledge graphs change over time, but the effects of actions on them are only partly stated: the ontology entails further consequences, facts that an action needs are often unknown, and an action may make the graph inconsistent. We study these problems for Temporal Dynamic Knowledge Graphs (TDKGs), that is, SROIQ knowledge bases whose actions are rules with delete/insert templates and whose events lie on an intrinsic timeline. We present three tools that use a SROIQ reasoner only through a few operations: temporal projection, which plays the events along the timeline and is the exact test of plans; DDA (Direct-Derivation Abduction), which explains an observation by assuming its negation and negating what the reasoner newly derives; and APT (Abduction and Planning over TDKGs), which plans backwards from a goal, assumes the facts that the plan needs but nobody stated, and lets DDA explain the assumptions, each explanation becoming a new goal for a sub-plan, up to a depth bound. The same machinery synthesises action sequences that end in a chosen contradiction. We prove that projection is decidable and that the indirect effects of an action are exactly the entailments of the updated state; that DDA is sound, terminates and finds every single-assertion explanation; and that APT is sound and terminates, while bounded planning is decidable but 2NExpTime-hard. We compare the tools analytically with hitting-set abduction and classical planning, compare DDA with the abduction solver CATS on shared problems, and run them on six benchmarks. Five reasoners (HermiT, Konclude, Pellet, Openllet, JFact) return identical results. Their incremental modes answered some checks wrongly after removals and gave no speed-up; parallel calls help only when a single call is expensive.
We present, to our knowledge, the first end-to-end FP4 RL post-training, in which both the rollout and training policies, including their forward and backward passes, operate at 4-bit precision. A systematic study reveals that the dominant source of degradation in FP4 RL is not training-side quantization error but rollout activation quantization: outliers stretch the dynamic range so far that a large number of activation values underflow to zero under FP4. Counterintuitively, restoring the training policy to higher precision while keeping the rollout in FP4 makes accuracy worse than full FP4 baseline, exposing rollout--training mismatch as the principal failure mode and ruling out standard pretraining-style fixes. We address this with Rollout Residual Quantization (Rollout-ResQ): a single residual correction term constrained to a hardware-friendly sparsity pattern, added only to the FP4 rollout matmul -- a lightweight correction that recovers most of the precision lost to outlier-driven underflow without inflating the rollout's compute footprint. On Qwen2.5-3B, Rollout-ResQ paired with the HiFloat4 (HiF4) format -- whose three-level hierarchical scaling preserves resolution under FP4's tight 4-bit budget -- closes the accuracy gap to BF16 from 3.59% to 1.39%, bringing fully quantized FP4 RL within close reach of full precision. Applied to the open-standard MXFP4, the same recipe narrows the gap from 13.6% to 5.3%, revealing that FP4 format choice is a key factor that determines the ceiling on recoverable accuracy. The experimental results on Qwen2.5-Math-7B further confirm the recovery benefits of Rollout-ResQ with HiF4. Together, these results establish HiF4 as the enabling format for end-to-end FP4 RL post-training, and Rollout-ResQ as the activation-side mechanism that makes the gap to BF16 closable.
Knowledge graph learning offers a powerful framework for representing and inferring structured knowledge, with broad practical applications. Two obstacles limit current methods: labeled triples are scarce for each entity and relation, which makes expressive models hard to train, and scoring functions are designed ad hoc, which limits their generalizability and leaves them without theoretical grounding. We address both obstacles with a theoretically grounded framework, with end-to-end guarantees, that extends and subsumes existing methods. The framework proceeds in two stages: multi-view unsupervised pretraining that integrates heterogeneous sources of entity side information into a shared representation, followed by supervised learning across multiple relation types. We establish a unified nonasymptotic risk bound that combines the subspace recovery error of pretraining and the sample complexity of the labeled data in a single guarantee, quantifying formally how large-scale unlabeled data from multiple views benefits downstream knowledge prediction. Synthetic experiments validate each component of the theory, and experiments on large-scale real-world knowledge graph benchmarks confirm the effectiveness of our approach.
Web-based navigation and traffic information services depend on accurate forecasts as sensor networks evolve. On checkpoints reused years later, updating only shared weights or adding a low-rank node prompt leaves substantial degradation, whereas, in the evaluated architectures, refreshing node identities recovers most of it while the shared spatio-temporal weights are reused. We propose EvoST, a framework that maintains traffic forecasters by refreshing node identities while keeping shared weights fixed. EvoST updates existing identities using recently released labels and initializes new sensors with identities borrowed from behaviorally similar established sensors. Once enough delayed labels arrive, it jointly refits all identities, and a per-sensor recursive least-squares calibrator corrects forecasts as labels become available. Across twelve PeMS region-year settings, identity refresh reduces the relative one-hour MAE gap between five-year-old STAEFormer checkpoints and target-year models from 17.7% to 2.5%, with all forecasters calibrated, and its MAE is 0.7% above that of full-parameter fine-tuning on the same data. In Graph WaveNet, identity refresh recovers 88% of the five-year MAE gap to calibrated target-year models. Similar recovery holds for STAEFormer checkpoints up to fifteen years old, while refreshing STID recovers 67% of its five-year gap. On an annual benchmark covering nine EvoXXLTraffic districts and Transport for NSW, EvoST has the lowest average MAE, RMSE, and MAPE among the reported non-foundation methods on all ten networks, and calibration accounts for most of its Avg-MAE reduction from the matched frozen checkpoints. Code and the extended version: https://github.com/lixus7/EvoST
Hyperspectral imaging (HSI) is useful for material discrimination, but operational mine screening also depends on how many false alarms must be inspected before targets are found. This paper studies PFM-1 landmine detection in unmanned aerial vehicle (UAV) visible and near-infrared (VNIR) HSI using spectral angle mapper (SAM), matched filter (MF), adaptive coherence estimator (ACE), and constrained energy minimization (CEM). We compare a ground-measured SVC signature, a fully informed in-scene core-pixel signature, and a simulated human-in-the-loop signature bootstrap. Besides receiver operating characteristic area under the curve and average precision, we report target-discovery curves and spatial candidate-review counts. Full-review bootstrapping reaches the fully informed in-scene signature case after all seven target regions are verified, but the required inspection effort varies strongly: ACE confirms all regions in two rounds and nine candidate inspections, whereas the SAM variants need thousands of candidate reviews for their final target locations. Code is available at https://github.com/SagarLekhak/IEEE_WHISPERS_2026_UAV_HSI_PFM1.
Multimodal large language models (MLLMs) hold immense potential to revolutionize clinical practice, yet deploying them in the medical domain is fundamentally a vision-centric challenge: models must absorb knowledge from heterogeneous 2D and 3D medical images, and evaluation protocols must align with radiologists' clinical practice and provide an accurate, fine-grained and factualness-driven assessment. In this paper, we introduce ClinFusion, a vision-centric MLLM designed for holistic medical understanding that systematically addresses these limitations. We propose a compositional and cascaded vision encoder architecture featuring a Cascade Spatial-Aware Locality Fusion operator that unifies diverse 2D and native 3D medical image understanding within a fused encoder. We further introduce a vision-grounded evaluation framework, including MedIF-Bench for instruction-following assessment and a region-of-interest-grounded method for clinically aligned and factualness-driven report generation evaluation. We show that ClinFusion sets a new state-of-the-art across a comprehensive suite of 2D and 3D multimodal medical benchmarks---spanning visual question answering, report generation, and instruction following---as well as textual medical tasks, outperforming leading open-source medical MLLMs (\textit{e.g.}, Hulu-Med, Lingshu) on 20 out of 24 benchmarks and demonstrating multimodal capabilities better than powerful proprietary models such as GPT-5.2 and Gemini-3-Flash on 13 out of 16 benchmarks, and can be further augmented with agentic tool use for retrieval-augmented and tool-assisted clinical workflows. A blinded evaluation by board-certified radiologists confirms that ClinFusion produces the highest-ranked reports, and validates our RoI-grounded metric as achieving the strongest correlation with expert judgment among all automatic evaluation metrics examined.
We prove the population-level identifiability of deep generative models (DGMs) with piecewise-affine (PWA) decoders and Gaussian mixture model (GMM) priors, in a purely unsupervised setting. We introduce three algebraic contrast principles for symmetry breaking: *domain contrast*, which trivializes the mixture symmetry group, a label-free counterpart of the sufficient-variability assumption of nonlinear ICA; *mechanism contrast*, which ensures every decoder branch gets an observational boundary across which it toggles alone; and *interaction contrast*, which forbids parameter conspiracies between latent components and decoder branches. Together they exploit the interplay between the discrete combinatorics of the PWA map and the continuous symmetry structure of the latent GMM. Continuity is replaced by algebraic symmetry conditions; injectivity is decoupled from structural identification and required only for pointwise inversion. Our results form a hierarchy: from *law identifiability* (LID; latent distribution up to a global affine map) through *map identifiability* (MID; decoder up to the same map) to *posterior* and *pointwise identifiability*. The ICA-form ambiguity emerges under conditions on diagonal component covariances. The interaction contrast is the only one of our contrasts required on the estimator side. To our knowledge this is the first to develop algebraic symmetry-breaking into an identifiability engine for a concrete nonlinear model class, the first to admit discontinuous decoders, and the first to handle fully non-injective decoders, where every observation admits multiple latent codes.
Multimodal large language models (MLLMs) excel at visual interpretation but fail on spatial reasoning tasks that humans solve reliably. Existing benchmarks evaluate these models as black boxes, limiting their ability to identify the underlying causes of lower performance: when a model fails a spatial reasoning task, it remains difficult to ascertain whether the hurdle is perceptual, such as recognizing object boundaries, or cognitive, such as reasoning about occlusion to infer hidden geometry. We introduce Spatial-IQ, a hierarchical diagnostic framework that decomposes object counting in stacked 3D structures into 9 perceptual and cognitive sub-tasks organized by the developmental stages of human spatial cognition, with mental rotation as an additional target probe. Using NVIDIA Isaac Sim, we procedurally generated a diverse dataset of roughly 80,000 stacked 3D structures with per-task ground truth. We evaluate models across three output formats (free-response text, multiple-choice images, and image editing) alongside a human baseline. The Spatial-IQ framework shows that top-performing models often succeed at the target task (object counting) without succeeding on the lower-level sub-tasks intended to support it, and that models differ in how much of these hierarchical chains they preserve, often revealing shortcut behavior that raw target-task accuracy alone would obscure. Finally, we demonstrate that training models with chain-of-thought (CoT) supervision over our hierarchical sub-tasks, combined with reinforcement learning with verifiable rewards, significantly improves both spatial consistency across sub-tasks and target-task accuracy, supporting the value of the proposed decomposition as both a diagnostic tool and a training signal.
CEC 2017 applies bias, shift and rotation simultaneously, obscuring their individual effects on algorithm behavior. We introduce a parameterized implementation controlling them independently while preserving the original functions and transformation data. It diagnoses hybrid Marine Predators Algorithm (hMPA), whose predicted-candidate mechanism relies on numerical objective values and coordinate-wise reconstruction. Deep Statistical Comparison (DSC) and extended DSC (eDSC) are adapted from algorithm-level comparison to configuration-level diagnosis. To our knowledge, this is the first exhaustive DSC and eDSC analysis of all eight bias-shift-rotation configurations of a parameterized CEC 2017 benchmark. We examine all 56 three-configuration subsets and comparisons with the untransformed control, using 29 functions, dimensions 10, 30, 50 and 100, 30 independent runs and a fixed budget of 10,000 objective-function evaluations per dimension. DSC and eDSC show statistically significant configuration differences at every dimension, but rankings vary across functions, precluding a consistent ordering. Most individual effect-size confidence intervals include zero. Among those excluding zero, comparisons favor MPA more often at dimension 10 and hMPA at dimensions 50 and 100. Shift generally worsens objective-value outcomes. Isolated rotation causes no systematic deterioration; isolated bias barely changes final-solution distributions. Combined shift and rotation differ most consistently from the control. Convergence plots show function- and dimension-dependent separation, plateaus and late improvement. Numerical findings are limited to hMPA, but the framework can be extended to other continuous optimizers and adapted to related CEC benchmarks, including CEC 2024 and CEC 2025.
Fog degrades autonomous-driving perception across modalities: it lowers image contrast, attenuates and scatters LiDAR returns, and shifts the input distribution of every learned module downstream. Choosing between restoring the degraded input and training on it directly requires the same scenes observed with and without fog at known severities, and enough foggy data to train on. Real-world capture cannot supply this: fog arrives entangled with lighting and traffic, at severities recorded rather than chosen; existing synthetic datasets narrow the sensor suite, the scale, or the severity range. We present FogDrive, a CARLA dataset of ~660 scenes (~133k frames), each released as a clear reference plus three calibrated fog densities, with physics-based fog on camera and LiDAR and 2D/3D annotations consistent across all variants. Every frame carries four cameras (RGB, depth, semantic), LiDAR, semantic LiDAR and radar -- spanning fog's response spectrum from heavily degraded cameras to largely unaffected radar. Experiments trained on FogDrive show that mixing fog densities improves 3D detection at no extra data cost, that PSNR and SSIM poorly predict a dehazer's detection benefit, and that radar improves camera-LiDAR fusion at every density. The dataset and its generation framework will be released.
Mechanistic interpretability (MI) enables monitoring and steering LLMs by operating on their internal state during inference. MI applications remain difficult to develop, expensive to execute, and challenging to manage at runtime. We present OrigaMI, a system that integrates MI applications as first-class components of LLM serving, enabling simplified development, efficient execution, and flexible deployment. Guided by a comprehensive analysis of modern MI applications, OrigaMI streamlines the MI applications development via a simple Python-based Domain Specific Language (DSL) for accessing intra- and inter-layer runtime model state at well-defined trigger points during inference. OrigaMI enables efficient access to ephemeral attention scores via a novel FlashInspect kernel that retains the performance benefits of FlashAttention. OrigaMI's compiler integrates multiple MI applications into the performance-optimized inference execution flow while ensuring conflict-free coexistence. OrigaMI's runtime supports dynamic, per-request activation and deactivation of MI applications without service interruption or performance degradation when inactive, leveraging OrigaMI's dynamic memory management and CUDA graph-compatible execution. We integrate OrigaMI with vLLM and evaluate ten MI applications, including sparse autoencoders, steering, and jailbreak detection, across four state-of-the-art LLMs. OrigaMI incurs negligible execution overhead, up to two orders of magnitude lower than existing frameworks, while enabling per-request activation and deactivation up to 1,000 times faster than alternatives. These results demonstrate that OrigaMI makes MI applications practical for deployment in production LLM serving systems.
Time series foundation models (TSFMs) have emerged as general-purpose models for time series analysis, but pretraining alone is often insufficient for reliable downstream deployment. Bridging this gap requires further intervention to handle domain shift, task heterogeneity, limited supervision, and computational constraints, which motivates post-training as a broad class of methods to adapt, augment, compose, calibrate, or specialize pretrained TSFMs for downstream tasks. In this work, we analyze TSFM post-training methods based on their locus of intervention in the prediction pipeline, yielding five categories: parameter adaptation, context augmentation, model composition, output processing and uncertainty control, and compression and specialization. Within each category, we study main representative methods and discuss their current limitations. We further identify future directions toward controlled adaptation, reliable context construction, uncertainty-aware model composition, calibrated output processing, and deployment-aware specialization. Overall, by providing a unifying framework for the emerging TSFM post-training landscape, this work aims to support future research to navigate the design space between a pretrained TSFM and its reliable downstream deployment.
Fraud detection systems must scale with rising transaction volume while remaining explainable and reviewable. We study a layered pipeline on the PaySim dataset that combines a gradient-boosted classifier, graph-derived structural features, an autoencoder-based anomaly signal, TreeSHAP explanations, and a bounded LLM investigation agent applied to cases the classifier scores uncertainly. Before any model comparison, we identify and remove a simulator-specific balance shortcut that would otherwise inflate baseline performance. After this correction, neither the graph features nor the anomaly signal improves Average Precision on the full test set. Both, however, rank fraud better within the subset of cases receiving intermediate baseline scores. In a controlled experiment with injected multi-account fraud rings, engineered structural features recover all injected test transactions, while the tabular baseline misses roughly a quarter of them. The investigation agent underperforms direct thresholding of the classifier it relies on, reaching 65.0% accuracy against 71.7% on a balanced 60-case sample, despite having access to model explanations, graph context, and retrieved reference cases. Of the eight decisions the agent changed, six replaced correct classifier outputs with errors, and it produced a coherent written rationale in each case. An exploratory disagreement-based escalation rule flagged two of these agent errors for human review without flagging any correct decision. We conclude that each component of a layered fraud system contributes only under specific conditions, and that a plausible rationale from an investigation agent is not evidence of a better decision.
Code corpora mined from the wild cannot change one thing at a time: a program's behaviour, messiness and size vary together, and nothing marks the correct answer. We present Spaghetti Architect, a generator that turns a small JSON description of a program into deliberately messy programs in five languages. It compiles and runs every program, checks the output against a reference computed from the description, and labels each program by problem size and by messiness. This control lets us change one property at a time and still know the correct answer. The generator writes comments into its own output, so we first re-render identical code without them. Removing the comments lowers the refactoring score of all four models we tested, and lowers the weakest model's about ten times as much as the strongest model's; a pre-registered replication confirms the difference at a smaller magnitude. The comments also hide an effect: messiness leaves scores flat while they are present and lowers them on both tasks once they are gone. We therefore recommend evaluating on the comment-free rendering. Changing only problem size drives direct-answer aggregation accuracy to zero for every model, and changing only literal values moves scores by less than 0.012. The generator, the dataset and the evaluation records are open source.
We introduce Signed Rectified Flow (Signed RF), a generalization of Rectified Flow that targets the signed measure $\pi^{sign} = (1+\alpha)\pi^+ - \alpha\pi^-$, where $\alpha>0$, $\pi^+$ is the distribution to promote, and $\pi^-$ is the distribution to suppress. Although direct sampling from a signed measure is not well-defined, Signed RF induces a valid generative process that concentrates probability in regions where the signed measure is positive while provably excluding regions dominated by its negative component. It therefore provides a principled framework for incorporating negative information and exclusion constraints into generative modeling. We analyze the signed continuity equation underlying Signed RF and use a charged-particle interpretation to explain how negative mass forms exclusion barriers. This theory further motivates practical adaptive guidance algorithms. Across several applications, Signed RF improves the fidelity-diversity trade-off on ImageNet, reduces nearest-neighbor similarity in anti-memorization experiments, and reduces nudity induced by adversarial prompts in Stable Diffusion 3.5 while preserving CLIP and aesthetic scores.
The digital substrate - data, algorithms, infrastructure, platforms, applications - is being governed without adequate conceptual foundations. The ability and legitimacy required to govern this substrate, and to govern with it, are simultaneously misaligned, contested, and structurally absent. We introduce digital statecraft as the organising concept for this emerging field, arguing that 'digital' reconstitutes the statecraft question rather than merely extending its domain. The concept operates on two dimensions - statecraft over digital systems, concerning the authority and capacity of the state in relation to the digital substrate itself, and statecraft with digital systems, concerning the deployment of algorithmic tools as instruments of governing authority. And it rests on two foundational requirements, technical coherence and legitimate authority, that are genuinely in tension. We derive ten principles of digital statecraft from these foundations, each naming a condition whose absence produces an identifiable and structural governance failure: public interest first, human-machine complementarity, governability by design, systemic coherence, hybrid institutions, adaptive governance, human centricity and civic agency, accountable and traceable authority, judgment across time, and the non-delegable core. This article takes the state as the starting point, the institutional form that developed historically in response to the problem of effective and legitimate public governance, and the only current candidate for which the full set of legitimacy conditions is institutionally available. But the digital statecraft programme holds open a deeper question than just whether states can reform themselves: governing well in the algorithmic age may require rethinking the boundaries, scale, and affiliative basis of statehood itself.