Paper proposes verifier engineering for improving foundation models.
problem Challenges in providing effective supervision signals for foundation models.
method Leverages automated verifiers to perform verification tasks and deliver feedback.
result Verifier engineering can enhance foundation models' capabilities.
This paper proposes a new algorithmic framework, predictor-verifier training, to train neural networks that are verifiable, i.e., networks that provably satisfy some desired input-output properties. The key idea is to simultaneously train two networks: a predictor network that performs the task at hand,e.g., predicting…
Study on TVL computation in DeFi protocols, proposing verifiable metrics.
problem Lack of standardization and verifiability in TVL computation.
method Systematic study of 939 DeFi projects, analyzing methodologies and proposing vTVL.
result 240 protocols use repeated balance queries, limiting verifiability.
Verify spiral minimal product structure using Takahashi Theorem.
problem Verify spiral minimal product structure.
method Using Takahashi Theorem with full computational details.
result Verify spiral minimal product structure.
IBP-R improves verified adversarial robustness with simple, effective interval bound propagation.
problem Improving verifiability of adversarially trained networks.
method Coupling adversarial attacks with interval bound propagation for minimized verification gap.
result State-of-the-art verified robustness-accuracy trade-offs for small perturbations on CIFAR-10.
Making neural networks robust against adversarial inputs has resulted in an arms race between new defenses and attacks. The most promising defenses, adversarially robust training and verifiably robust training, have limitations that restrict their practical applications. The adversarially robust training only makes the…
The study examines how verifier imperfections impact test-time scaling techniques.
problem Understanding how verifier imperfections affect test-time scaling methods.
method Proves the instance-level accuracy of Best-of-N and Rejection Sampling methods using the geometry of the verifier's ROC curve.
result RS outperforms BoN for fixed compute, but both converge to the same accuracy in the infinite-compute limit.
Researchers find floating point errors can mislead neural network verifiers.
problem Floating point arithmetic inaccuracies mislead neural network verifiers.
method Efficiently searches inputs and constructs neural network architectures to exploit verification errors.
result Floating point errors can systematically mislead neural network verifiers.
Efficient verified double auctions improve matching speed and detect errors.
problem Improving the efficiency and reliability of double auctions in financial markets.
method Formally verified implementation using Coq proof assistant, reducing time complexity and improving error detection.
result Improved efficiency with O(nlogn) time complexity, reducing runtime from days to minutes. This study extends verifiable learning to boosted tree ensembles, enabling efficient security verification.
problem Efficiently verifying the robustness of boosted tree ensembles against norm-based attackers.
method Formal verification of robustness for large-spread boosted tree ensembles, considering L∞-norm and pseudo-polynomial time for Lp-norm verification. result Polynomial time verification for L∞-norm attackers, NP-hard for other norms, and pseudo-polynomial time for Lp-norm verification. We give a remarkably elementary proof of the Brouwer fixed point theorem. The proof is verifiable for most of the mathematicians.
Efficiently verifies neural networks by handling neuron splits, improving speed and accuracy.
problem Handling neuron split constraints in incomplete neural network verification.
method β-CROWN, which optimizes parameters β to encode neuron splits and uses them in bound propagation.
result β-CROWN significantly speeds up verification while maintaining high accuracy.
Develops verifiers to check if machine learning models treat similar individuals equally.
problem Ensuring fairness in machine learning models by checking if similar individuals are treated differently.
method Constructs verifiers for proving individual fairness of machine learning models, considering relaxations of the problem.
result Developed verifiers for linear and kernelized polynomial/radial basis function classifiers.
New method verifies formulas for causal interventional distributions.
problem Deciding if a given formula correctly identifies an interventional distribution.
method Proposed a falsifier to check if a formula is identifying.
result Falsifier can induce an almost-surely correct verifier for certain models.
Trade-R1 bridges verifiable rewards to stochastic financial markets via process-level reasoning verification.
problem Extending RL to financial markets where rewards are verifiable but noisy.
method A verification method that transforms reasoning over financial documents into a structured RAG task, using a triangular consistency metric.
result DSR achieves superior cross-market generalization while maintaining reasoning consistency.
Cactus improves auto-regressive decoding speed without sacrificing quality.
problem Accelerating auto-regressive decoding while maintaining output quality.
method Formalizes speculative sampling as constrained optimization and proposes Cactus for controlled divergence from the verifier distribution.
result Empirically validated effectiveness across various benchmarks.
In this paper, we propose a verified numerical method for obtaining a sharp inclusion of the best constant for the embedding H01(Ω)↪Lp(Ω) on bounded convex domain in R2. We estimate the best constant by computing the corresponding extremal function using a verified numerical com…
We show how to compute the Bayes error-rate for speaker verifiers.
problem How many errors does a speaker verifier make in a hundred trials?
method We compute the Bayes error-rate using calibrated likelihood ratios and user-supplied prior probabilities.
result The Bayes error-rate is upper bounded by the minimum of EER, P, and 1-P.
New algorithm verifies Anosov condition for surface groups efficiently.
problem Verifying Anosov condition for surface groups in higher dimensions.
method Finite criteria to certify projective Anosov subgroups, practical algorithm.
result Practical algorithm reduces verification from 2 million to 8-length words.
Formally verifies fairness and uniformity in financial market trades.
problem Ensuring fairness and uniformity in automated trading systems.
method Formal definition and verification in Coq proof assistant.
result Properties of double-sided auction mechanisms verified.
New approach verifies tree ensembles efficiently, making them more robust.
problem Verifying robustness of decision tree ensembles against evasion attacks is NP-hard.
method Identified large-spread ensembles, proposed verifiable learning, designed training algorithm.
result Large-spread ensembles can be verified in polynomial time and are more robust.
Deep neural networks are widely used for nonlinear function approximation with applications ranging from computer vision to control. Although these networks involve the composition of simple arithmetic operations, it can be very challenging to verify whether a particular network satisfies certain input-output propertie…
Paper tackles model collapse in synthetic data retraining.
problem Iterative retraining of generative models on synthetic data can lead to performance deterioration.
method Integrates an external synthetic data verifier to prevent model collapse.
result Synthetic retraining with a verifier can improve model performance initially but may lead to convergence to the verifier's knowledge center.
Generalizes neural network verification by adding arbitrary cutting planes.
problem Handling general cutting plane constraints in neural network verification.
method Generalized bound propagation method (GCP-CROWN) that allows arbitrary cutting plane constraints.
result GCP-CROWN significantly improves neural network verification performance.
Verification of neural networks enables us to gauge their robustness against adversarial attacks. Verification algorithms fall into two categories: exact verifiers that run in exponential time and relaxed verifiers that are efficient but incomplete. In this paper, we unify all existing LP-relaxed verifiers, to the best…
Verifies a conjecture for the figure eight knot.
problem Relates A-ideal and recurrence ideal of knots.
method Uses quantum A-ideals, q-holonomicity, and AJ conjecture.
result Strong AJ conjecture verified for figure eight knot.
Researchers compute quantum invariant for four-puncture sphere, verifying volume conjecture.
problem Verifying the Bonahon-Wong-Yang volume conjecture for a specific case.
method Representation theory of the Checkov-Fock algebra to compute quantum invariant.
result Verification of the volume conjecture for four-puncture sphere bundles with technical conditions.
Verified numerics prove existence of a curvature solution with known symmetries.
problem Existence of a curvature solution for the Nirenberg problem.
method Verified numerics and computer assistance.
result Existence of a genuine solution with known symmetry groups.
Revel tackles safe exploration in RL with verified symbolic policies.
problem Computational infeasibility of verifying neural networks in RL learning loops.
method Two policy classes: neurosymbolic with approximate gradients and symbolic policies for efficient verification. Mirror descent over policies to safely update and project policies.
result Revel discovers policies that outperform prior approaches to verified exploration.
Understanding properties of deep neural networks is an important challenge in deep learning. In this paper, we take a step in this direction by proposing a rigorous way of verifying properties of a popular class of neural networks, Binarized Neural Networks, using the well-developed means of Boolean satisfiability. Our…
Verifies knot conjecture for 24-crossing knots.
problem Jones Unknot Conjecture for knots up to 24 crossings.
method Described method of verification with complexity analysis.
result Jones Unknot Conjecture verified for 24 crossings.
Neural networks are part of many contemporary NLP systems, yet their empirical successes come at the price of vulnerability to adversarial attacks. Previous work has used adversarial training and data augmentation to partially mitigate such brittleness, but these are unlikely to find worst-case adversaries due to the c…
In this paper, we diagnose deep neural networks for 3D point cloud processing to explore utilities of different intermediate-layer network architectures. We propose a number of hypotheses on the effects of specific intermediate-layer network architectures on the representation capacity of DNNs. In order to prove the hy…
New algorithms verify and search causal graphs with minimal interventions.
problem Recovering causal graphs from interventional data.
method Characterization of minimal intervention sets for verification, and adaptive graph separator algorithm for search.
result First provable algorithms for efficient verification and search of causal graphs.
FUSE improves verification quality without ground truth labels.
problem Verification of model outputs using imperfect judges and reward models.
method Ensembling verifiers without ground truth labels using spectral algorithms.
result FUSE matches or improves upon semi-supervised alternatives in test-time scaling experiments.
Verify conjecture for special Hermitian manifolds.
problem Conjecture about space forms for canonical metric connections.
method Verify conjecture for complex nilmanifolds and Bismut torsion-parallel manifolds.
result Verify conjecture for two special types of Hermitian manifolds.
Study improves understanding of why agentic theorem provers succeed.
problem Understanding which components of agentic theorem provers improve proof success.
method Statistical provability theory and finite-horizon reachability MDP model.
result Bounds provability gap and explains components' effectiveness.
New approach uses interpolation models and error bounds for verifiable scientific machine learning.
problem Challenges in verifying and validating modern scientific machine learning workflows.
method Combines multiple standard interpolation techniques with error bounds for efficient computation and comparative performance analysis.
result Error bounds for interpolation techniques can be computed or estimated efficiently, aiding in validation goals.
Formal methods verify continuous auctions at exchanges.
problem Ensuring fairness and correctness in continuous auctions.
method Formal specification, design, and verification of continuous double auctions.
result A verified algorithm satisfies natural properties of auctions.
Fast BATLLNN speeds up verification of TLL NNs by 400x.
problem Verifying output constraints for TLL NNs.
method Uses TLL architecture and decoupled box constraints to improve verification performance.
result 400x faster than state-of-the-art verifiers.
VERAFI improves financial AI by verifying calculations and compliance.
problem Financial AI systems generate errors and violations during reasoning.
method VERAFI combines dense retrieval, reranking, and automated reasoning policies.
result VERAFI achieves 94.7% factual correctness, 81% relative improvement.
We introduce a general framework to handle structured models (sparse and block-sparse with possibly overlapping blocks). We discuss new methods for their recovery from incomplete observation, corrupted with deterministic and stochastic noise, using block-ℓ1 regularization. While the current theory provides promis…
In this manuscript we analyse the leading statistical properties of fluctuations of (log) 3-month US Treasury bill quotation in the secondary market, namely: probability density function, autocorrelation, absolute values autocorrelation, and absolute values persistency. We verify that this financial instrument, in spit…
We formalize and verify double auctions for multiple-quantity trades.
problem Matching multiple-quantity trade requests in double auctions.
method Formalized algorithms, correctness proofs, Coq proof assistant, verified OCaml and Haskell programs.
result Automatic detection of violations in exchange systems.
The paper uses RL to verify hypotheses, overcoming existing limitations.
problem Verifying hypotheses using reinforcement learning.
method Formulated hypothesis verification as an RL problem, exploiting hypothesis structure.
result RL agents can successfully verify hypotheses, even those not factorizable.
Training neural networks with verifiable robustness guarantees is challenging. Several existing approaches utilize linear relaxation based neural network output bounds under perturbation, but they can slow down training by a factor of hundreds depending on the underlying network architectures. Meanwhile, interval bound…
E-valuator converts verifier scores into reliable decision rules.
problem Ensuring the correctness of agent trajectories based on heuristic scores.
method Sequential hypothesis testing framework for online monitoring of agent trajectories.
result E-valuator provides better false alarm rate control and statistical power than other strategies.
For a given cusped 3-manifold M admitting an ideal triangulation, we describe a method to rigorously prove that either M or a filling of M admits a complete hyperbolic structure via verified computer calculations. Central to our method are an implementation of interval arithmetic and Krawczyk's Test. These techni…