arXiv:2607.11098v3 Announce Type: replace
Abstract: Tool-using LLM agents are mostly evaluated assuming all tools work. When a tool times out, returns a week-stale value, or has its description poisoned in deployment, the developer needs a controlled way to reproduce the failure, test a fix, and confirm the fix worked before deployment. We present AgentCheck, an open-source web workbench that turns an MCP server into an intervention surface. AgentCheck runs an agent against its real tools and records every tool response, then re-runs the agent with the response perturbed by a fault (12 types) injector. Matching tool calls are replayed from cache, and later tool calls go live after the agent diverges. This yields a reproduce-intervene-confirm loop: the developer toggles a mitigation, re-runs against the identical fault, and sees if the failure goes away. Scoring has two parts: deterministic pass/fail rules, plus an LLM judge for interpretive labels, validated against human annotations. Across five agents, the best passes 105/120 scenarios and the weakest only 77. The failures are usually silent, confident use of incorrect tool outputs rather than crashes. On the weakest agent, a retry mitigation raises success on timeout error faults from as few as 30% of cases to 100%, whereas stale-data faults remain near 3-4 of 10 regardless of the mitigation. AgentCheck makes these failure modes reproducible, comparable, and verifiable before deployment.
Science Journals
arXiv:2607.11192v3 Announce Type: replace
Abstract: A large share of day-to-day work in professional domains happens inside PDF files: benefits packets, leases, datasheets, clinical guidelines, construction plans. Benchmarks for document AI have generally measured the required capabilities in isolation: OCR, layout analysis, chart reasoning, table QA, document VQA. A high score on any one of them does not necessarily reveal whether a model can answer a realistic question that someone in the field would actually ask about a specific PDF. GDP_pdf is a benchmark built to measure this directly. It consists of question-document pairs authored by working professionals in ten fields, and a candidate question was kept only when at least two frontier multimodal models failed it in a way that mattered: a wrong answer, missed decisive evidence, or a fabricated claim, rather than a superficial difference such as style. Each item comes with a rubric of atomic criteria, so we can report a graded rubric score as well as a strict task-level pass rate, and each item is tagged against a taxonomy of eleven capabilities in three tiers, spanning text extraction and grounding, table and chart comprehension, cross-referencing, spatial reasoning, and abstention on unsupported queries. We report results for seventeen frontier models on the 100-item benchmark: the best model passes only 30.7% of the items and the worst passes 2%. Most errors trace back to a small set of recurring loss patterns: misaligned tables, misread charts, skipped footnotes and exclusions, miscounted floor-plan symbols, scan noise, and amendments that supersede earlier text.
arXiv:2607.13339v1 Announce Type: new
Abstract: Composable data systems promise to let developers combine languages, engines, and catalogs without sacrificing a coherent user experience. In practice, however, pipeline-node boundaries remain weakly specified: transformations exchange tables through schemas that are often checked late, enforced unevenly across languages, and disconnected from the semantics business users care about. Based on over a year of operating millions of jobs in Bauplan, we share the design principles behind our new SDK, which treats data contracts as types for a composable, multi-language lakehouse. Users, whether humans or agents, annotate input and output tables with schema objects that encode column types, constraints, documentation, and lineage; Bauplan then interprets these annotations at different points in the execution lifecycle. We show how this design addresses common production failures, and how an ''everything-as-code'' philosophy enables both deterministic and non-deterministic reasoning over data flows across languages and engines.
arXiv:2607.13872v1 Announce Type: cross
Abstract: The free-particle and square-well potentials are two of the most emblematic problems in quantum mechanics, illustrating essential concepts such as matter waves, energy quantization, and bound states. It is therefore natural to consider how the free-particle solutions emerge from the square well as the width approaches infinity. In this work, we present a systematic procedure to demonstrate this transition by applying a Fourier transform to the wave equation.
arXiv:2607.11285v2 Announce Type: replace
Abstract: Reconstructing 3D scenes from unordered images remains bottlenecked by expensive Structure-from-Motion (SfM) preprocessing and frozen pose interfaces. We present SalientGS, a unified SfM-to-3D Gaussian Splatting (3DGS) pipeline. Its central contribution is importance-guided Markov Chain Monte Carlo (MCMC) Gaussian allocation, which aggregates multi-view residuals into per-Gaussian underfit and redundancy signals. These signals define a smooth importance-weighted sampling distribution that biases both birth and relocation toward underfit regions. This reallocates capacity from well-fit areas without altering the underlying stochastic gradient Langevin dynamics (SGLD). SalientGS achieves end-to-end reconstruction in 15 minutes with state-of-the-art perceptual quality. The supplementary material provides dedicated sections for Per-Scene Qualitative Comparisons and Per-Image Learned Perceptual Image Patch Similarity (LPIPS) Analysis, including failure cases. Code and evaluation scripts are available at https://github.com/Six-Bit-TX/SalientGS.
arXiv:2607.11334v2 Announce Type: replace
Abstract: Large language models can produce superficially legal twelve-tone scores that collapse into degenerate textures. We introduce a neuro-symbolic harness that wraps a language-model proposer in a generate-verify-repair-trace loop with symbolic verification. The complete pipeline improves event-local consistency without claiming whole-piece legality. Across 40 controlled tasks and four paired models, constraint-checked delivery rises from 13.3% under raw generation to 48.1% with the harness; it abstains on the remaining 51.9% of runs. The pass rate of a narrower collision and serialisation-consistency check rises from 33.5% to 58.3%, while degeneracy remains near 0.05, including under adversarial prompting. A blinded evaluation by five experts also shows a descriptive aggregate preference for harness candidates over raw generation in adherence, perceived legality, coherence, and overall quality.
arXiv:2607.11506v2 Announce Type: replace
Abstract: Reinforcement learning with verifiable rewards (RLVR) optimizes LLMs using sparse verifiable final-answer rewards. This sparse anchor reliably verifies whether a trajectory succeeds but provides no direct feedback on the reasoning path that produced it. Before success, prerequisite progress on hard problems receives no reward signal; after success, outcome rewards cannot distinguish well-organized correct trajectories from redundant or locally flawed ones. We introduce SCOPE-RL (Scaffolded Chain Optimization with Process Efficiency), a two-stage framework that densifies this anchor while retaining the GRPO update: Adaptive Scaffolded RL adds prefix-decomposed verifiable rewards on answer-hidden sub-question chains before success, and Quality-Aware Process RL applies correctness-gated process-shape rewards to refine correct trajectories after success. An expert-validated Step-Quality Evaluation Protocol evaluates useful-step density, error localization, and token efficiency beyond final-answer accuracy. On Qwen3-8B-Instruct trained on DAPO-Math and Big-Math, SCOPE-RL improves average accuracy by up to 11.2 pp and reduces reasoning tokens by up to 27.1% over outcome-only GRPO; the gains hold under GSPO and on Qwen3-0.6B-Instruct, indicating that reward-signal densification is complementary to policy-update-level RLVR advances. Code and data are available at https://github.com/tokencraft-lab/SCOPE-RL.
arXiv:2607.11588v3 Announce Type: replace
Abstract: We present FoundationGeo, a two-stage framework that explicitly bridges relative and metric prediction via spatial calibration and principled data design. Stage 1 learns a high-fidelity, affine-invariant geometry model by initializing with DINOv3 and training on a curated 10.2M-sample multi-domain corpus with complementary local-detail supervision, yielding sharp boundaries and strong cross-domain generalization. Stage 2 moves beyond global scaling by introducing lightweight pixel-wise calibration fields for metric estimation: a scale field for spatially varying metric alignment and a ray-direction correction field that mitigates directional bias in point-map geometry, together producing metrically consistent 3D point maps. Beyond model design, we identify camera intrinsic coverage, especially focal length distribution mismatch between training and test data, as a key bottleneck for zero-shot metric generalization: performance drops sharply when test intrinsics fall outside the training distribution. To address this, we synthesize additional training data across diverse focal lengths using a Blender-based data engine, repairing under-covered focal regimes and improving robustness under intrinsic shift. Extensive zero-shot evaluations across seven benchmarks show that FoundationGeo significantly strengthens cross-domain robustness, staying near the top across diverse domains while avoiding the sharp cross-domain performance drops observed in other methods. This consistency translates into the best overall performance, surpassing heavier baselines by over 5.2% on average.
arXiv:2607.11707v2 Announce Type: replace
Abstract: Following the rapid progress of generative Artificial Intelligence, there is a growing threat posed by conversational scams. These scams often span over multiple weeks or months, gradually build trust and request for money or sensitive information. Existing scam-detection systems mainly focus on isolated messages, which renders them inadequate against this evolving threat. This paper extends single-message phishing detection and presents an explainable agentic system for detecting sophisticated conversational scams. It also introduces ConScamBench-278, an initial public multi-category benchmark for conversational scam detection spanning eight scam types, released to support reproducible evaluation and future expansion. On isolated messages the single-message detector attains 100% phishing recall, while the conversation-level detector identifies all conversational scams in the public LoveFraud02 corpus (83/83) and reaches 97.8% accuracy (95% CI [95.4, 99.0]) on ConScamBench-278. Two user studies (N = 100 and N = 45) further motivate the system: participants report frequently experiencing uncertainty when judging suspicious conversations. In an uncontrolled pre/post comparison, users self-reported trust, self-confidence, and perceived need for AI-based scam detection all increased (p < 0.001, Wilcoxon signed-rank). The system also receives a System Usability Scale score of 74.7 (95% CI [72.5, 76.9]), above the established usability benchmark.
arXiv:2607.11715v2 Announce Type: replace
Abstract: Large-scale, richly annotated career trajectory data underpins workforce planning, job recommendation, and labour market analysis, yet publicly available datasets are either small, closed to independent use, or built from pre-standardized occupational codes with LLM-synthesized rather than authentic free text. We present JobHop~v2, an improved version of the publicly available JobHop dataset, constructed through end-to-end large language model (LLM) extraction from a corpus of ${\sim}440{,}000$ pseudonymized, multilingual resumes provided by VDAB, the Flemish Public Employment Service. The released dataset comprises $355{,}315$ career trajectories annotated with ESCO occupational codes, quarter-level temporal information, and normalized five-level education attainment, broadening both the coverage and the annotation richness of the original release. Relative to v1, JobHop~v2 introduces a redesigned extraction pipeline based on reasoning-controlled LLM inference with a retry mechanism (achieving a 100% JSON parse rate), a richer extraction schema, and a revised evaluation protocol scored against three complementary annotation baselines. Evaluated against these baselines, our best extractor comes closest to the inter-annotator agreement ceiling among all compared models, trailing it by only 1.1-2.7 percentage points. The dataset and code are publicly released to support reproducible career-trajectory research.
arXiv:2607.11722v2 Announce Type: replace
Abstract: Career paths encode decades of skill acquisition, role transitions, and educational investment, and understanding them at scale underpins workforce planning, labor market policy, and job recommendation. Resumes are a rich source of information about career paths: they contain detailed descriptions of work experience, education, and skills. Yet their unstructured, heterogeneous, and multilingual nature has long prevented large-scale systematic analysis. With the advent of large language models (LLMs), it is now possible to source rich career trajectory data containing temporal and educational signals from unstructured resumes, enabling new opportunities for career-path recommendation. Exploiting this opportunity, we present STEP (Sequential Trajectory of Employment Prediction), a novel career-path recommendation system that leverages temporal and educational signals to predict the next job in a career trajectory. STEP integrates a time-decay Gated Recurrent Unit (GRU) cell to model temporal dynamics, Feature-wise Linear Modulation (FiLM) conditioned on educational attainment, and attention-based sequence pooling to select relevant features for next job prediction. To improve internal occupation representation for STEP, we introduce ROUTE, a two-stage contrastive procedure that first adapts a multilingual encoder to the career domain via unsupervised denoising autoencoding, then performs supervised contrastive fine-tuning with guided negative selection. We evaluate STEP on four datasets of career trajectories, including an improved version of our publicly available JobHop dataset, and show that it outperforms state-of-the-art baselines in next job prediction. The dataset and code are publicly released to support reproducible career-trajectory research.
arXiv:2607.11808v2 Announce Type: replace
Abstract: This paper proposes a human-centered artificial intelligence (HCAI) framework for AI-assisted lexicography. While generative AI offers significant opportunities to enhance lexicographic work, it also raises concerns regarding the future role of lexicographers and the preservation of linguistic and cultural diversity. Drawing on HCAI principles and previous applications in other language professions, the paper identifies four interrelated dimensions through which AI integration in lexicography can be understood and critically examined: the augmented lexicographer, the sociotechnical context of AI integration, bias, and the design of AI-powered lexicographic tools. The framework argues that AI should augment rather than replace lexicographers, combining automation with meaningful human control. It further emphasizes the importance of preserving professional agency, mitigating AI-generated biases, and designing tools around the needs of lexicographers. By doing so, the paper provides a foundation for future research and the beneficial integration of AI into lexicographic workflows.
arXiv:2607.11895v2 Announce Type: replace
Abstract: AI scientist systems are beginning to automate parts of scientific research, but social science poses a distinct challenge: its objects of inquiry are not merely datasets or laboratory protocols, but integrated social processes involving situated participants, interaction contexts, interventions, and outcomes. Yet a critical link is missing: existing systems either assist isolated research tasks or simulate agents as experimental subjects, leaving the research workflow and simulated society decoupled. Here we introduce AgentSociety 2, an Integrated Research Environment for executable social science. It couples two roles of LLM agents in the same runtime: AI social scientists that coordinate literature grounding, hypothesis generation, experiment design, simulation execution, result interpretation, and manuscript drafting; and silicon participants that generate behavioral responses within configurable social environments. This dual-role design turns hypotheses into auditable agent behaviors, environment rules, interventions, and measurements, thereby supporting an end-to-end workflow. Across seven illustrative studies spanning micro-level social-science laboratory experiments, meso-level dynamics in social media, and macro-level urban scenarios, we demonstrate its capacity to support diverse disciplinary questions, reproduce major qualitative patterns from prior studies, identify informative deviations, and enable large-scale simulations through optimized agent-environment interactions. By preserving human researchers' high-level agency while delegating procedural orchestration to agentic systems, it provides a human-in-the-loop and controllable infrastructure for next-generation computational social science, with broader applications in scalable computational social experimentation and AI-enabled social governance platforms.
arXiv:2607.11947v2 Announce Type: replace
Abstract: Typical semi-supervised learning (SSL) methods rely on distributional assumptions, and their performance degrades when these are violated. While PNU learning, a risk rewriting method, offers a distribution-free alternative, it is restricted to binary classification and its variance optimality remains unclear. In this paper, we propose a generalized framework that constructs unbiased risk estimators using linear combinations of component risks, subsuming PNU learning and extending to multiclass classification. We derive the minimum achievable variance, demonstrating our estimator can attain lower variance than PNU in asymmetric loss scenarios. Furthermore, we establish a generalization bound directly linking this variance reduction to improved learning performance. Based on these theoretical insights, we introduce two practical SSL methods that empirically match or outperform existing approaches on binary and multiclass benchmarks.
arXiv:2607.11953v2 Announce Type: replace
Abstract: Does a reinforcement-learning agent that earns high reward represent its task's latent state, or only a reward-correlated shortcut? Usually this is unanswerable: the "true state" is undefined. We make it exactly answerable with a white-box instrument: express the task as a hidden deterministic finite automaton (DFA), let the agent observe a symbol stream and intermittently choose the next symbol under partial control, with a sparse terminal reward for acceptance. Knowing the automaton gives two things for free: the optimal return (so reward becomes an interpretable normalized score) and the exact latent state at every step (so we can probe the agent's representation without ever showing it). Reward success and latent-state learning become separately measured quantities whose coupling is governed by three axes. Optimizer strength: under weak on-policy RL the agent can lock onto a reward-shortcut, earning reward with the state probe at chance; whether it escapes is set by optimizer strength, budget, and task structure -- a pre-registered control isolates the optimizer (PPO+GAE), which escapes fastest but only partially and with high seed variance. Task structure: permutation (group-language) structure is a warning sign computable from the transition function before any training, and held out on 153 capacity-controlled fresh automata it flags perception gaps at precision 0.86 (89 of 103), in one direction only. Observation informativeness: a label-free auxiliary is vacuous when observations carry no state and recovers it sharply once they carry any (a threshold, saturating near beta=0.1). The payoff is a distinction reward-only evaluation cannot make: a perception gap (state not linearly recoverable, though representable) versus a planning gap (state recoverable but not exploited). Reward alone cannot localize which; high reward alone is not evidence the state was learned.
arXiv:2607.11976v2 Announce Type: replace
Abstract: Indexer-TopK, the operation to compute the scores and select the top-k candidates, is widely used by sparse attention kernels in large language models and vector retrieval in recommendation systems and vector databases. However, existing GPU-based Indexer-TopK kernels like DeepSeek Sparse Attention (DSA) remain inefficient due to excessive global memory traffic, costly synchronization, and prohibitive memory overhead. In this work, we exploit the curse of dimensionality in high-dimensional spaces, where distances between high-dimensional vectors tend to concentrate within a narrow range, to design LITETOPK, a novel and efficient fused Indexer-TopK kernel. LITETOPK first samples a small subset of data to estimate query-data score ranges, then uses these estimates to partition candidate results into bins online. This organization allows the LITETOPK kernel to maintain a tight approximate threshold, write back only promising candidates, reduce unnecessary I/O, substantially lower memory overhead, and still preserve exact Top-k correctness. Experimental results show that LITETOPK accelerates the prefill stage of GLM 5.2 by 1.2x in real-world deployment scenarios while incurring lower memory overhead.
arXiv:2607.11997v2 Announce Type: replace
Abstract: Multi-task model merging combines separately trained expert models into a single model that handles all tasks without co-training. Standard practice merges experts at their optimal validation loss. We challenge this convention by systematically studying how training duration of domain experts affects the quality of the merged model. We fine-tune experts on five domains (Math, Code, Instruction Following, Multilingual, and Safety) across three model sizes (Qwen 3.5 0.8B, 2B, and 4B), saving checkpoints from 25% to 500% of the optimal training steps and evaluating five merging methods at each duration. Our findings reveal a striking method-dependent pattern: simple averaging degrades sharply with overfitting, while sparsification-based methods achieve their best performance well past the validation optimum. We formalize this through bias-variance decomposition analysis, drawing a parallel to random forests where averaging benefits from high-variance individual learners. These results suggest that training duration and merging method should be chosen jointly rather than independently.
arXiv:2607.13459v1 Announce Type: new
Abstract: Probabilistic programs are important for many applications. For security applications in particular, one is interested in establishing properties that hold in the presence of arbitrary adversaries, i.e., unknown pieces of code. We present Elton, a higher-order separation logic for reasoning about higher-order probabilistic programs utilizing unknown adversarial code. Elton incorporates novel logical facilities for specifying invariants over distributional properties using delayed samplings at the language level, and a new kind of separation-logic predicate called urn resources at the logic level. We show that these extensions are sound and can be erased back to a standard call-by-value semantics. Combined with other features, e.g. invariants and ghost resources, Elton is expressive enough to prove error bounds on a wide range of security examples, some of which are beyond the scope of previous techniques. All proofs are mechanized with the Rocq proof assistant and the Iris separation logic framework.
arXiv:2509.10986v2 Announce Type: replace
Abstract: A semi-empirical model is presented for the thermalized temperature $T$ and mean momentum in the direction of laser propagation <$p_{fz}$> of electrons released from O$_{2}$ after the passage of a focused $800$ nm ultrashort pulsed laser pulse vs. peak laser intensity $I_{0}$ to provide initial conditions for electrodynamic fluid simulations. For this, theoretical kinetic energy spectra in different directions are modified with two adjustable parameters representing the effects of electron rescatter off its parent ion during the optical cycle subsequent to ionization. The classical kinematics of rescatter, in conjunction with the spectral fits, is used to estimate <$p_{fz}$>.
arXiv:2607.13889v1 Announce Type: new
Abstract: Voltage-source converter high-voltage direct current (VSC-HVDC) links offer controllable active and reactive power output, making them a promising asset for emergency voltage support. This paper presents an analytical method for adjusting the active power setpoint of a VSC-HVDC station to maximise loadability during voltage-stressed conditions. By exploiting the geometric structure of converter capability limits, a closed-form expression for the optimal setpoint is derived under combined current and voltage constraints. The method requires local voltage measurements and an estimate of a wide-area voltage angle difference, making it suitable for real-time emergency control without global optimisation. Validation on the Nordic Test System confirms that the analytically predicted optimum is consistent with the setpoint yielding the highest loadability, and that adjustments of active power setpoint can yield a more-than-proportional increase in loadability. The results further indicate robustness to angle estimate uncertainty.
arXiv:2607.13891v1 Announce Type: new
Abstract: Multi-object detection and tracking from noisy point clouds remain challenging in many data-scarce radar applications. Current Bayesian trackers based on Poisson measurement models offer a training-free solution but struggle to achieve accuracy and efficiency under severe clutter, large object populations, and full-resolution Doppler point clouds. We address this with PiVoT, a fast, clutter-resilient multi-object tracker for both positional and Doppler measurements. PiVoT performs end-to-end detection and tracking of a large and time-varying number of objects without external clustering or detectors, through joint inference of object states, shapes, existence probabilities, data association, and measurement rates. Its efficiency is driven by several variational inference innovations, such as theoretically justified birth pruning, quadratic-to-linear complexity reductions for exact updates, and a computationally efficient Doppler Poisson model. Experiments show that PiVoT substantially outperforms existing Bayesian trackers in challenging scenes, while also demonstrating exceptional scalability to a thousand objects, robustness to clutter visually inseparable from objects, and real-time operation on full-scale modern automotive radar datasets, where it attains performance comparable to a deep-learning detection benchmark as a training-free joint detector and tracker.
arXiv:2607.13468v1 Announce Type: new
Abstract: Recently, a line of works can generate impressive 3D objects from a single image, but they are limited by restricted representation resolution, making them unsuitable for 3D scene generation. In this work, we introduce HIVE-3D, a novel method for high-quality 3D scene generation based on hierarchical voxel enhancement framework. Specifically, given a single scene image as input, we first produce a coarse initial scene, then introduce image segmentation and attention-based retrieval to align 2D image components with 3D scene components. Subsequently, we organize these scene relations into a hierarchical component tree, where nodes closer to the leaves denote finer-grained components. Finally, we propose a voxel super-resolution model that generates refined voxels for the target instance while maintaining strong consistency with the coarse voxels. Equipped with this model, we perform coarse-to-fine hierarchical super-resolution on images and voxels for each component, producing a high-resolution and high-quality 3D scene. Extensive experiments demonstrate that our method significantly outperforms previous approaches, achieving state-of-the-art performance.
arXiv:2607.13474v1 Announce Type: new
Abstract: We present MyAG, a graph-based framework for designing and analyzing composable LLM agent systems. Our framework separates agent system construction into three graph abstractions: a component graph for agents, environments, and modules; a workflow graph for execution control; and a search graph for runtime execution. This separation allows users to flexibly reuse the same components with different strategies. We further support hierarchical composition through recursive system nodes and provide monitoring and visualization tools for inspecting agent execution. Experiments on representative agent applications show that our framework supports flexible agent system design and helps analyze performance-efficiency tradeoffs. Our framework is publicly available and fully open-source.
arXiv:2607.13631v1 Announce Type: new
Abstract: The Hessian matrix is an important quantity of interest when it comes to studying the loss landscape and optimization dynamics in deep learning, as well as designing measures of generalization, second-order learning algorithms, etc. Prior works have focused on empirical results or pursued a theoretical treatment under overly simplified settings. In this work, we derive the eigenvalues of the Hessian of linear networks with arbitrary widths and depths, and datasets with an arbitrary number of samples, features, and labels. Importantly, for classification tasks with MSE loss, we identify that the sharpness of the solution is directly related to the maximum proportion of samples belonging to any class. We empirically validate our predictions and systematically analyze the effects of shedding the impractical assumptions one at a time, as well as incorporating nonlinearities. We observe that our predictions are considerably robust in most cases, allowing us to extend our conclusions to more practical learning setups.
arXiv:2607.12441v2 Announce Type: replace
Abstract: Wikipedia plays a key role in shaping public understanding of science, and its openly accessible revision history is a unique record of how scientific knowledge evolves over time. Yet scientifically meaningful revisions are obscured by the sheer volume of routine edits, leaving each article's scientific history hidden. We present WikiSTAR (Scientific Tracking of Article Revisions), an interactive system for exploring scientifically meaningful changes across an article's revision history. Using an LLM classifier with an expert-designed multi-label taxonomy, WikiSTAR first tags edit types such as the addition of technical terms, new research findings, and changes in scientific narrative. Then, through interactive views, an article's full revision history can be traced at any granularity - from aggregate trends that reveal when and in which sections scientific content was added or refined, down to individual edits - showing how scientific knowledge develops at a scale previously impossible. In a user study, experts from three domains found that WikiSTAR surfaced new patterns and research questions and enabled previously impractical analyses. We release our system, code and a human-annotated benchmark.