Probability · arXiv:2611.16995 v1 · submitted 12 Nov 2026 · 71 references
Entire sig-jump-diffusions, their expected signature and applications to score-based generative modeling
The paper says
“We develop score-based generative models for time series and standard finite-dimensional data, building on the analytical computation of the expected signature of a new class of jump-diffusions, called entire sig-jump-diffusions.”
more of the abstract
These are semimartingales whose characteristics are given by linear combinations of potentially infinitely many components of their own signature. We show that their expected signature can be computed by solving linear ODEs in the extended tensor algebra, providing a tractable foundation for learning procedures. Specifically, the learning of a generalized score function for jump diffusions, a key ingredient of our generative modeling framework, can be reduced to solving linear ODEs and a deterministic optimization problem. We further prove that polynomial jump-diffusions can be embedded into this framework, and that their expected signature reduces to a finite-dimensional system of linear ODEs. Building on this result, we develop an alternative approach for finite-dimensional data, based on inverse signature matching, a method that learns the score by matching the expected signature of the reverse process with that of the inverse forward signature.
from the abstract
Pith says
Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded · not checked by a person
It can be wrong. Challenge this review or reply to it.
The passes disagreed. Reader: holds up, with conditions. Skeptic: does not hold up. Referee: major revision.
The paper extends signature SDEs to jump processes and shows that the expected signature solves a linear ODE; the generative modeling application is a plausible sketch but rests on an unverified entire approximation and has no numerical validation. This line is wrong
4 major objections · 6 minor
How often objections from reviews like this one are right: not yet measured
Not checked: figures, code, what the 71 references say.
The paper says, at Section 4.3, Theorem 4.9
The review did not quote this passage.
A classifier read this sentence of the paper as acknowledging the concern (probability 0.62):
“Finally, we stress that the goal of the paper is to establish the framework and the analytic learning procedure, while a numerical investigation of the generative models, on time series as well as on finite-dimensional data, is left to future work.”
Pith says: Objection 1 of 4 · major
The entire approximation of the generalized score function (Section 4.3) is the central step that connects the theoretical machinery to a practical learning algorithm. The paper acknowledges that numerical investigation is left to future work (sentence [b51]) and provides no bounds on the approximation error, no discussion of the function space in which the approximation is made, and no convergence guarantees.
more of objection 1
Without this, the claim that score learning reduces to a deterministic optimization problem is unsubstantiated. This is a load-bearing issue for the generative modeling application.
The paper says, at Section 4.3, equation (4.14)
The review did not quote this passage.
Pith says: Objection 2 of 4 · major
The derivation of the denoising score matching objective (4.14) relies on the conditional generalized score identity (4.12). However, the existence and uniqueness of such a conditional generalized score for the lifted truncated signature process Z^≤N is not established. The paper assumes that (4.12) holds for all admissible test functions f, but this is a nontrivial condition that requires justification, especially given that the law P^N_t is supported on a submanifold (group-like elements) of T^N(R^d).
This objection may describe the copy Pith gave the reviewer, not the paper.
The paper says, at Section 4.3, Theorem 4.9
The review did not quote this passage.
Pith says: Objection 3 of 4 · major
Theorem 4.9 states that the optimization problem (4.13) is equivalent to (4.17) under the assumption that all conditions of Corollary 3.15 are satisfied. However, the conditions of Corollary 3.15 include that the coefficient sequence ṽ(u) belongs to D(L) and that the corresponding integrability conditions hold. These conditions are not verified for the specific ṽ(u) arising from the entire approximation of the score. The paper does not provide sufficient conditions on the coefficients u to ensure these hold.
The paper says, at Section 4.4, Theorem 4.11
The review did not quote this passage.
Pith says: Objection 4 of 4 · major
Theorem 4.11 constructs an entire sig-diffusion with a unique invariant measure. However, this construction is for a pure diffusion (δ=0) and does not include jumps. The paper's title and main framework include jumps, but the invariant measure result is limited to the diffusion case. The applicability to jump-diffusions in the generative modeling context is therefore restricted.
6 minor objections
The paper says, at General
Pith says: minor objection 1 of 6
The paper is well-written and mathematically rigorous. The notation is consistent and the structure is clear.
The paper says, at Section 3.3.2
Pith says: minor objection 2 of 6
The assumption that F(E) < ∞ (finite measure space) is used to simplify the proof of Lemma 3.18. The paper mentions this can be relaxed, but it would be helpful to discuss how.
show 4 more
The paper says, at Section 4.1, Definition 4.1
Pith says: minor objection 3 of 6
The definition of the generalized score function S_t is given in terms of the operator K and the marginal density p_t. It would be helpful to clarify the domain of S_t and the precise integrability conditions required for (4.2) to hold.
The paper says, at Section 4.5
Pith says: minor objection 4 of 6
The inverse signature matching approach relies on the assumption that the expected signature characterizes the law of the process (Chevyrev and Oberhauser, 2022). This is a strong assumption that is not discussed in the context of the specific polynomial diffusions used.
The paper says, at Example 3.28
Pith says: minor objection 5 of 6
The numerical validation in Example 3.28 is for a specific polynomial jump-diffusion and shows agreement with Monte Carlo. This is a nice illustration of the expected signature computation, but it does not validate the generative modeling framework.
The paper says, at Section 4.3
Pith says: minor objection 6 of 6
The paper uses the time-extended signature to incorporate time dependence. It would be helpful to explicitly state how the time component is handled in the ODE (4.15).
What would settle it
Implement the entire approximation for a simple known score function (e.g., the score of a Gaussian distribution under an Ornstein-Uhlenbeck forward process, as in Remark 4.10(ii)). Compute the expected signature-based loss (4.14) using the linear ODE (4.15) and optimize the coefficients u. Then, using the learned entire approximation g_u, simulate the reverse process (4.11) and compare the generated samples' distribution to the true target distribution via a standard metric (e.g., maximum mean discrepancy or Wasserstein distance). If the generated samples fail to match the target distribution within a reasonable tolerance, the entire approximation is insufficient for this simple case, casting doubt on the general claim.
from the skeptic's reading
How the review went
4 readings by deepseek-v4-flash · 13 Nov 2026
- Reader holds up, with conditions
- Skeptic agrees: says it does not hold up The entire approximation of the generalized score function (Section 4.3) is not justified and the paper acknowledges that numerical validation is left to future work, making the central claim of a tractable learning procedure unsubstantiated.
- Editor wrote the verdict above
- Referee major revision: 4 major objections, 6 minor
Not run on this paper: the simulated authors' defence.
Pith did not check this review's objections against the paper.
The review in full
The review in brief, machine-written
Christa,
This paper does two things. First, it extends the class of signature SDEs (Cuchiero et al. 2026b) to processes with jumps, calling them entire sig-jump-diffusions. The main theoretical result is that the expected signature of such processes can be computed by solving a linear ODE in the extended tensor algebra (Theorem 3.13). The extension to jumps is nontrivial because the series convergence is harder, and the authors give conditions under which it holds. They also show that polynomial jump-diffusions embed into this framework and that their expected signature reduces to a finite-dimensional matrix exponential (Proposition 3.24, Corollary 3.25). This part is clean and appears mathematically sound. The numerical example in Section 3.3.3 (Example 3.28) is a nice validation of the expected signature formula for a specific Ornstein-Uhlenbeck process with jumps, and the code is provided.
Second, the paper sketches an application to score-based generative modeling for time series and finite-dimensional data. The idea is to use the expected signature formula to reduce learning a generalized score function to a deterministic optimization problem (Theorem 4.9). This is where the soft spots are. The core step is approximating the generalized score function by an entire function in time and signature components (Section 4.3). This is a strong regularity assumption that is not justified. The paper acknowledges that numerical investigation is left to future work (sentence [b51]), so the practical validity of the entire approximation is untested. The stress-test note is right to flag this as a load-bearing gap: without it, the generative modeling framework remains a theoretical construction with no demonstrated viability. The paper also acknowledges that recovering time series from generated signatures is subject to approximation issues not addressed here (sentence [b44]), and that the reverse process is not the true pathwise time reversal but only marginal-preserving (Remark 4.5). These are honest limitations, but they add up.
Who is this paper for? Readers working on signature methods for stochastic processes will find the extension to jumps useful. The generative modeling part is more speculative and will need substantial empirical work before it can be taken as a practical method. The paper deserves a serious referee because the theoretical core (expected signature of entire sig-jump-diffusions) is a genuine contribution and the mathematics is carefully laid out. The referee should press on the entire approximation assumption and ask for either justification or a relaxation. The paper would be stronger if it included even a simple numerical experiment demonstrating the generative modeling pipeline on a toy problem.
My recommendation: accept for peer review, but flag that the generative modeling claims are conditional on unverified assumptions and that the paper would benefit from numerical validation before publication.
Best, [Your name]
The strongest objection
The paper's central claim for generative modeling (Theorem 4.9) reduces score learning to a deterministic optimization problem by approximating the generalized score function with an entire function in time and signature components (Section 4.3). This entire approximation is a strong, unverified regularity assumption. The paper acknowledges that 'a numerical investigation of the generative models... is left to future work' (sentence [b51]) and that 'the practical validity of this assumption is untested' (reader's weakest_assumption). The entire approximation is used to express the denoising score matching objective as a linear functional of the expected signature, which is then computed via the linear ODE (Theorem 3.13). If the score function is not entire, the approximation error is uncontrolled, and the learned score may not correspond to the true reverse process. The paper provides no bounds on this approximation error, no discussion of the function space in which the approximation is made, and no convergence guarantees. This is not a minor technical gap; it is the core step that connects the theoretical machinery of expected signatures to the practical learning algorithm. Without it, the generative modeling framework remains a theoretical construction with no demonstrated viability.
The reader's verdict is CONDITIONAL, with the weakest assumption being the entire approximation of the score function. I agree that this is the most load-bearing concern. However, I argue that the verdict should be REJECT rather than CONDITIONAL because the paper's central claim for generative modeling (Theorem 4.9) is presented as a reduction of score learning to a deterministic optimization problem, but this reduction relies entirely on an unverified and unjustified approximation. The paper does not provide any theoretical justification for the entire approximation (e.g., approximation bounds, density results, or conditions under which the score is entire). The paper explicitly states that numerical validation is left to future work, meaning there is no evidence that the proposed method works even in simple cases. A CONDITIONAL verdict would be appropriate if the paper had a plausible path to verification (e.g., a clear set of conditions under which the approximation holds, or a numerical experiment on a toy problem). The paper has neither. Therefore, the central claim is not just unverified but is based on an assumption that is likely false in general (score functions of diffusions are typically not entire functions of the signature components). The paper's own limitations (sentence [b51]) confirm this gap. The reader's weakest_assumption correctly identifies this, but the verdict should be stronger to reflect that the paper's main contribution is unsupported.
The referee's report
If the central claims hold, the paper provides a novel theoretical connection between expected signatures and generative modeling, potentially enabling tractable score learning for jump-diffusions. The theoretical development of entire sig-jump-diffusions and their expected signature computation is mathematically sound and extends prior work. However, the practical viability of the generative modeling framework is not demonstrated, and the key assumption that the generalized score function can be approximated by an entire function is unverified.
Pith's reading of the paper (a machine's summary, not the authors')
This paper introduces a class of jump-diffusions called entire sig-jump-diffusions, whose characteristics depend linearly on potentially infinitely many components of their own signature. The main theoretical result is that the expected signature of such a process can be computed by solving a linear ordinary differential equation in the extended tensor algebra (Theorem 3.13). This tractability is then exploited to develop score-based generative models for time series and finite-dimensional data. The learning of a generalized score function is reduced to a deterministic optimization problem that involves solving linear ODEs, bypassing neural network training. The paper also shows that polynomial jump-diffusions embed into this framework and proposes an alternative inverse signature matching method for finite-dimensional data generation.
What carries the argument. The central object is the signature of a càdlàg semimartingale, an element of the extended tensor algebra whose components are iterated integrals. The key identity is the linear ODE (3.5) for the expected signature: $\frac{d}{dt} \langle c(t), x \rangle = \langle L(c(t)), x \rangle$, where $L$ is an operator defined in terms of the sig-coefficients (Definition 3.6, equation (3.3)). This operator $L$ encodes the drift, diffusion, and jump characteristics of the entire sig-jump-diffusion, and its linearity in the tensor algebra is what makes the expected signature tractable.
Core claim. The paper establishes that entire sig-jump-diffusions, defined as semimartingales whose drift, diffusion, and jump characteristics are linear functionals of their own signature (Definition 3.3), have expected signatures governed by a linear ODE in the extended tensor algebra (Theorem 3.13). This generalizes previous work on continuous signature SDEs to the jump-diffusion setting. The result is then applied to score-based generative modeling: by approximating the generalized score function (Definition 4.1) with an entire function in time and signature components, the score-matching objective reduces to solving a linear ODE and a deterministic optimization problem (Theorem 4.9). The paper further proves that polynomial jump-diffusions are a subclass of entire sig-jump-diffusions, so their expected signature reduces to a matrix exponential (Proposition 3.24, Corollary 3.25). For finite-dimensional data, an alternative inverse signature matching method is proposed that learns the score by matching expected signatures of forward and reverse processes (Section 4.5).
The premise it rests on. The generalized score function can be approximated arbitrarily well by an entire function in time and signature components (Section 4.3). This entire approximation is used to reduce score learning to a deterministic optimization problem; if it fails, the learning procedure may not converge to the true score.
If the paper is right (Pith's inferences, not the authors')
Time series generation can be performed by perturbing the empirical distribution of truncated signatures with an entire sig-jump-diffusion, then running a reverse process with a learned generalized score, all without training a neural network for the score.
The expected signature of any polynomial jump-diffusion can be computed via a matrix exponential, enabling fast and accurate moment computations for such processes.
The inverse signature matching method provides a way to learn the reverse drift of a polynomial diffusion by matching expected signatures, reducing the problem to a deterministic optimization that avoids score matching entirely.
The existence of invariant measures for lifted entire sig-diffusions (Theorem 4.11) guarantees that the forward perturbation process forgets the initial data distribution, a prerequisite for score-based generative modeling.
The framework unifies and extends prior work on signature SDEs, holomorphic jump-diffusions, and polynomial processes under a single formalism for expected signature computation.
If the entire approximation of the generalized score is valid in practice, the method could dramatically reduce the computational cost of score-based generative modeling for time series, as the learning phase becomes a deterministic optimization problem rather than a stochastic one.
The inverse signature matching method (Section 4.5) suggests a new paradigm for generative modeling where one matches expected signatures of forward and reverse processes, which could be extended beyond polynomial diffusions to any class where expected signatures are tractable.
The paper's reliance on the entire approximation (Section 4.3) is a strong assumption that may limit practical applicability; numerical experiments are needed to assess whether this approximation holds for realistic data distributions.
The connection between entire sig-jump-diffusions and the universal approximation property of signatures implies that any sufficiently regular jump-diffusion can be approximated by an entire sig-jump-diffusion, potentially making the framework widely applicable if the convergence conditions can be verified.
Check this review
Pith stored no record of this review's passes and took no fingerprint of it. Reviews made by code from 13 Nov 2026 on carry both.
How often reviews like this one are right
Reviews like this one: written by deepseek-v4-flash, where what was read was not recorded.
How often objections from reviews like this one are right: not yet measured
Reviews by people
This review was written by a machine. No person has reviewed this paper on Pith yet. A scientist listed on Pith can review it for a fee, and their review is published here whatever it concludes.
The paper
Abstract
We develop score-based generative models for time series and standard finite-dimensional data, building on the analytical computation of the expected signature of a new class of jump-diffusions, called entire sig-jump-diffusions. These are semimartingales whose characteristics are given by linear combinations of potentially infinitely many components of their own signature. We show that their expected signature can be computed by solving linear ODEs in the extended tensor algebra, providing a tractable foundation for learning procedures. Specifically, the learning of a generalized score function for jump diffusions, a key ingredient of our generative modeling framework, can be reduced to solving linear ODEs and a deterministic optimization problem. We further prove that polynomial jump-diffusions can be embedded into this framework, and that their expected signature reduces to a finite-dimensional system of linear ODEs. Building on this result, we develop an alternative approach for finite-dimensional data, based on inverse signature matching, a method that learns the score by matching the expected signature of the reverse process with that of the inverse forward signature.
The paper's own sentences, arranged, kept beside the review and separate from it. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. No sentence in this record was written by a model.
abstract compiled · 2026-11-13
The authors' main claim, as the classifier picked it out 0.81
“We develop score-based generative models for time series and standard finite-dimensional data, building on the analytical computation of the expected signature of a new class of jump-diffusions, called entire sig-jump-diffusions.”
How the main claim is stated: asserted 1.00
What the abstract itself states, as probabilities: claims first 0.06 · states limitation 0.06 · human participants 0.02 · controlled comparison 0.02 · randomized assignment 0.01 · states quantitative result 0.05 · compares with prior results 0.20 · mentions code or data availability 0.02
The abstract, sentence by sentence
This table labels the abstract only (arXiv listing abstract v1). The number is the probability the classifier gave the label.
| Sentence | Role | The authors' own work | States the main conclusion | Strength |
|---|---|---|---|---|
| We develop score-based generative models for time series and standard finite-dimensional data, building on the analytical computation of the expected signature of a new class of jump-diffusions, called entire sig-jump-diffusions. | contribution 1.00 | 0.95 | 0.38 | asserted 1.00 |
| These are semimartingales whose characteristics are given by linear combinations of potentially infinitely many components of their own signature. | method 0.53 | 0.39 | 0.05 | asserted 1.00 |
| We show that their expected signature can be computed by solving linear ODEs in the extended tensor algebra, providing a tractable foundation for learning procedures. | result 0.75 | 0.94 | 0.24 | asserted 1.00 |
| Specifically, the learning of a generalized score function for jump diffusions, a key ingredient of our generative modeling framework, can be reduced to solving linear ODEs and a deterministic optimization problem. | method 0.64 | 0.91 | 0.20 | asserted 1.00 |
| We further prove that polynomial jump-diffusions can be embedded into this framework, and that their expected signature reduces to a finite-dimensional system of linear ODEs. | result 0.88 | 0.91 | 0.11 | asserted 1.00 |
| Building on this result, we develop an alternative approach for finite-dimensional data, based on inverse signature matching, a method that learns the score by matching the expected signature of the reverse process with that of the inverse forward signature. | contribution 0.59 | 0.94 | 0.15 | asserted 1.00 |
What kind of paper the classifier reports this is: method or tool 0.58 · evidence from proof or derivation 1.00
What was examined, and what was not
Sources read
- arXiv listing abstract v1
Not examined
- full text
- figures and tables
- references and citing sentences
- relations to other papers
Levels run
- P abstract
Not run
- S sections
- T body sentences
- C citations
- R cross-paper relations
How the labels were made
Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-11-13: 1 request, 5,049 input tokens.
Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. This record as JSON
Figures (1)
References (71)
- [1] Abi Jaber, E., Attal, E., and Sotnikov, D. (2026). Stochastic control with signatures via Riccati equations on the tensor algebra . Preprint, arXiv:2607.03986 on PithPith's reviewarXiv
- [2] Abi Jaber, E., Hainaut, D., and Motte, E. (2025). Signature Approach for Pricing and Hedging Path-Dependent Options with Frictions . Preprint, arXiv:2511.23295 on PitharXiv
- [3] Abi Jaber, E. and Sotnikov, D. (2025). Exponentially Fading Memory Signature . Preprint, arXiv:2507.03700 on PithPith's reviewarXiv
- [4] Arnaudon, M. and Thalmaier, A. (2010). The Differentiation of Hypoelliptic Diffusion Semigroups . Illinois Journal of Mathematics , 54(4):1285--1311 on Pith
- [5] Barancikova, B., Huang, Z., and Salvi, C. (2025). SigDiffusions : Score-Based Diffusion Models for Time Series via Log-Signature Embeddings . In The Thirteenth International Conference on Learning Representations on Pith
- [6] Barilari, D., Boscain, U., and Neel, R. W. (2019). Heat Kernel Asymptotics on Sub-Riemannian Manifolds with Symmetries and Applications to the Bi-Heisenberg Group . Annales de la Facult \'e des Sciences de Toulouse , 28(4):707--732 on Pith
- [7] Baudoin, F., Hairer, M., and Teichmann, J. (2008). Ornstein--uhlenbeck processes on lie groups. Journal of Functional Analysis , 255(4):877--890 on Pith
- [8] Baule, A. (2026). Generative modelling with jump-diffusions . Journal of Statistical Mechanics: Theory and Experiment , 2026(5):054002 on Pith
- [9] Bayer, C., Hager, P. P., Riedel, S., and Schoenmakers, J. (2023). Optimal stopping with signatures . The Annals of Applied Probability , 33(1):238--273 on Pith
- [10] Boedihardjo, H., Diehl, J., Mezzarobba, M., and Ni, H. (2021). The expected signature of Brownian motion stopped on the boundary of a circle has finite radius of convergence . Bulletin of the London Mathematical Society , 53(1):285--299 on Pith
- [11] Boedihardjo, H., Papavasiliou, A., and Qian, Z. (2013). Expected Signature of Gaussian Processes with Strictly Regular Kernels . Preprint, arXiv:1304.4930 on PithPith's reviewarXiv
- [12] Cao, H., Chen, M., Han, Y., and Xu, R. (2026). Diffusion Models for Adaptive Sequential Data Generation . Preprint, arXiv:2606.06007 on PithPith's reviewarXiv
- [13] Cass, T. and Ferrucci, E. (2024). On the Wiener Chaos Expansion of the Signature of a Gaussian Process . Probability Theory and Related Fields , 189:909--947 on Pith
- [14] Cass, T. and Salvi, C. (2024). Lecture notes on rough paths and applications to machine learning . Preprint, arXiv:2404.06583 on PithPith's reviewarXiv
- [15] Chevyrev, I. and Friz, P. K. (2019). Canonical RDEs and general semimartingales as rough paths . The Annals of Probability , 47(1):420--463 on Pith
- [16] Chevyrev, I. and Kormilitzin, A. (2026). A primer on the signature method in machine learning . In Signature Methods in Finance: An Introduction with Computational Applications , pages 3--64. Springer on Pith
- [17] Chevyrev, I. and Lyons, T. (2016). Characteristic Functions of Measures on Geometric Rough Paths . The Annals of Probability , 44(6):4049--4082 on Pith
- [18] Chevyrev, I. and Oberhauser, H. (2022). Signature Moments to Characterize Laws of Stochastic Processes . Journal of Machine Learning Research , 23(176):1--42 on Pith
- [19] Conforti, G. and L \'e onard, C. (2022). Time reversal of Markov processes with jumps under a finite entropy condition . Stochastic Processes and their Applications , 144:85--124 on Pith
- [20] Cuchiero, C., Gazzani, G., M \"o ller, J., and Svaluto-Ferro, S. (2025a). Joint calibration to SPX and VIX options with signature-based models . Mathematical Finance , 35(1):161--213 on Pith
show 51 more
- [21] Cuchiero, C., Gazzani, G., and Svaluto-Ferro, S. (2023). Signature-Based Models: Theory and Calibration . SIAM Journal on Financial Mathematics , 14(3):910--957 on Pith
- [22] Cuchiero, C., Keller-Ressel, M., and Teichmann, J. (2012). Polynomial processes and their applications to mathematical finance . Finance and Stochastics , 16(4):711--740 on Pith
- [23] Cuchiero, C. and M \"o ller, J. (2025). Signature methods in stochastic portfolio theory . SIAM Journal on Financial Mathematics , 16(4):1239--1303 on Pith
- [24] Cuchiero, C. and Pachschw \"o ll, J. (2026). Polynomial Signature McKean-Vlasov SDEs . Working Paper on Pith
- [25] Cuchiero, C., Primavera, F., and Svaluto-Ferro, S. (2025b). Universal approximation theorems for continuous functions of c \`a dl \`a g paths and L \'e vy -type signature models . Finance and Stochastics , 29(2):289--342 on Pith
- [26] Cuchiero, C., Primavera, F., and Svaluto-Ferro, S. (2026a). Holomorphic jump-diffusions . Stochastic Processes and their Applications , 191:104781 on Pith
- [27] Cuchiero, C., Svaluto-Ferro, S., and Teichmann, J. (2026b). Signature SDEs from an affine and polynomial perspective . Electronic Journal of Probability , 31:1--57 on Pith
- [28] De Marco, S., Pham, H., and Zanni, D. (2026). Schr \"o dinger bridges with jumps for time series generation. Preprint, arXiv:2602.20011 on PithPith's reviewarXiv
- [29] Doob, J. L. (1948). Asymptotic Properties of Markoff Transition Probabilities . Transactions of the American Mathematical Society , 63(3):393--421 on Pith
- [30] Ethier, S. N. and Kurtz, T. G. (1986). Markov processes: characterization and convergence . Wiley Series in Probability and Mathematical Statistics: Probability and Mathematical Statistics. John Wiley & Sons Inc on Pith
- [31] Fawcett, T. (2003). Problems in Stochastic Analysis: Connections between Rough Paths and Non-Commutative Harmonic Analysis . PhD thesis, University of Oxford on Pith
- [32] Fermanian, A., Chang, J., Lyons, T., and Biau, G. (2024). The insertion method to invert the signature of a path. In Recent Advances in Econometrics and Statistics: Festschrift in Honour of Marc Hallin , pages 575--595. Springer on Pith
- [33] Filipovi \'c , D. and Larsson, M. (2020). Polynomial Jump-Diffusion Models . Stochastic Systems , 10(1):71--97 on Pith
- [34] Friz, P. K., Hager, P. P., and Tapia, N. (2026). On Expected Signatures and Signature Cumulants in Semimartingale Models . In Signature Methods in Finance: An Introduction with Computational Applications , pages 381--424. Springer on Pith
- [35] Friz, P. K. and Shekhar, A. (2017). General Rough Integration, L \'e vy Rough Paths and a L \'e vy--Kintchine-Type Formula . The Annals of Probability , 45(4):2707--2765 on Pith
- [36] Gasteratos, I., Jacquier, A., Lemercier, M., Lyons, T., and Salvi, C. (2025). Novelty detection on path space . Preprint, arXiv:2512.03243 on PitharXiv
- [37] Ge, W., Jiang, L., Yang, L., Roveri, L., Yi, M., Chen, P.-Y., Cariou-Kotlarek, N., Buet-Golfouse, F., Mittal, G., and Ni, H. (2026). Sig-DEG for Distillation: Making Diffusion Models Faster and Lighter . Preprint, arXiv:2508.16939 on PithPith's reviewarXiv
- [38] Gennaro, A., Mastrolia, T., and Primavera, F. (2026). Signature Methods for Optimal Market Making . Preprint, arXiv:2606.19772 on PithPith's reviewarXiv
- [39] Gerlach, M. and Nittka, R. (2012). A New Proof of Doob's Theorem . Journal of Mathematical Analysis and Applications , 388(2):763--774 on Pith
- [40] Guo, Z., Tang, W., and Xu, R. (2026). Conditional Diffusion Guidance under Hard Constraint: A Stochastic Analysis Approach . Preprint, arXiv:2602.05533 on PithPith's reviewarXiv
- [41] Hamdouche, M., Henry-Labord \`e re, P., and Pham, H. (2026). Nonparametric generative modeling for time series via S chr \"o dinger bridge. Journal of Machine Learning Research , 27(58):1--23 on Pith
- [42] Han, Y., Razaviyayn, M., and Xu, R. (2025). Stochastic control for fine-tuning diffusion models: Optimality, regularity, and convergence. In Proceedings of the 42nd International Conference on Machine Learning , volume 267 of Proceedings of Machine Learning Research , pages 21... on Pith
- [43] Haussmann, U. G. and Pardoux, E. (1986). Time reversal of diffusions . The Annals of Probability , 14(4):1188--1205 on Pith
- [44] Ho, J., Jain, A., and Abbeel, P. (2020). Denoising diffusion probabilistic models. In Advances in Neural Information Processing Systems , volume 33, pages 6840--6851 on Pith
- [45] Hyv \"a rinen, A. (2005). Estimation of Non-Normalized Statistical Models by Score Matching . Journal of Machine Learning Research , 6:695--709 on Pith
- [46] Jacod, J. and Shiryaev, A. (1987). Limit Theorems for Stochastic Processes . Springer Berlin, Heidelberg on Pith
- [47] Jansen, S. and Kurt, N. (2014). On the notion(s) of duality for Markov processes . Probability Surveys , 11:59--120 on Pith
- [48] Kalsi, J., Lyons, T., and Perez Arribas, I. (2020). Optimal execution with rough path signatures . SIAM Journal on Financial Mathematics , 11(2):470--493 on Pith
- [49] Kurtz, T. G., Pardoux, E., and Protter, P. (1995). Stratonovich stochastic differential equations driven by general semimartingales . Annales de l'I.H.P. Probabilit\'es et statistiques , 31(2):351--377 on Pith
- [50] Le Donne, E. (2025). Nilpotent Lie Groups . In Metric Lie Groups , volume 306 of Graduate Texts in Mathematics , pages 243--295. Springer on Pith
- [51] Levin, D., Lyons, T., and Ni, H. (2013). Learning from the past, predicting the statistics for the future, learning an evolving system . Preprint, arXiv:1309.0260 on PithPith's reviewarXiv
- [52] Liao, S., Ni, H., Sabat \'e -Vidales, M., Szpruch, L., Wiese, M., and Xiao, B. (2024). Sig‐Wasserstein GANs for conditional time series generation . Mathematical Finance , 34(2):622--670 on Pith
- [53] Lou, H., Li, S., and Ni, H. (2023). PCF-GAN: generating sequential data via the characteristic function of measures on the path space . In Advances in Neural Information Processing Systems , volume 36, pages 39755--39781 on Pith
- [54] Lyons, T. (1998). Differential equations driven by rough signals . Revista Matem \'a tica Iberoamericana , 14(2):215--310 on Pith
- [55] Lyons, T., Nejad, S., and Perez Arribas, I. (2019). Numerical Method for Model-Free Pricing of Exotic Derivatives in Discrete Time Using Rough Path Signatures . Applied Mathematical Finance , 26(6):583--597 on Pith
- [56] Lyons, T. and Ni, H. (2015). Expected signature of Brownian motion up to the first exit time from a bounded domain . Annals of Probability , 43(5):2729--2762 on Pith
- [57] Lyons, T. and Victoir, N. (2004). Cubature on Wiener Space . Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences , 460(2041):169--198 on Pith
- [58] Lyons, T. and Xu, W. (2017). Hyperbolic development and inversion of signature. Journal of Functional Analysis on Pith
- [59] Lyons, T. and Xu, W. (2018). Inverting the signature of a path. Journal of the European Mathematical Society , 20(7):1655--1687 on Pith
- [60] Ni, H. (2012). The Expected Signature of a Stochastic Process . PhD thesis, University of Oxford on Pith
- [61] Papavasiliou, A. and Ladroue, C. (2011). Parameter Estimation for Rough Differential Equations . The Annals of Statistics , 39(4):2047--2073 on Pith
- [62] Perez Arribas, I., Salvi, C., and Szpruch, L. (2021). Sig-SDEs model for quantitative finance . In Proceedings of the First ACM International Conference on AI in Finance , ICAIF '20, New York, NY, USA on Pith
- [63] Popov, V., Yermekova, A., Sadekova, T., Khrapov, A., and Kudinov, M. S. (2025). Improved Sampling Algorithms for L \'e vy - It \^o Diffusion Models . In The Thirteenth International Conference on Learning Representations on Pith
- [64] Semnani, P., Guan, V., Robeva, E., and Lee, D. (2025). Path-Dependent SDEs : Solutions and Parameter Estimation . Preprint, arXiv:2505.22646 on PithPith's reviewarXiv
- [65] Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., and Ganguli, S. (2015). Deep unsupervised learning using nonequilibrium thermodynamics. In Proceedings of the 32nd International Conference on Machine Learning , volume 37 of Proceedings of Machine Learning Research , pages 2... on Pith
- [66] Song, Y. and Ermon, S. (2019). Generative modeling by estimating gradients of the data distribution. In Advances in Neural Information Processing Systems , volume 32 on Pith
- [67] Song, Y., Sohl-Dickstein, J., Kingma, D. P., Kumar, A., Ermon, S., and Poole, B. (2021). Score-Based Generative Modeling through Stochastic Differential Equations . In International Conference on Learning Representations (ICLR) on Pith
- [68] Strichartz, R. S. (1986). Sub-Riemannian Geometry . Journal of Differential Geometry , 24(2):221--263 on Pith
- [69] Tang, W. and Zhao, H. (2025). Score-based diffusion models via stochastic differential equations. Statistical Surveys , 19:28--64 on Pith
- [70] Vincent, P. (2011). A Connection Between Score Matching and Denoising Autoencoders . Neural Computation , 23(7):1661--1674 on Pith
- [71] Yoon, E., Park, K., Kim, S., and Lim, S. (2023). Score-based Generative Models with L \'e vy Processes . In Advances in Neural Information Processing Systems , volume 36 on Pith
Challenges and discussion
Disagree with the review, or know something it missed? Leave a comment, or challenge this review formally: a challenge becomes a permanent entry in this paper's record, and its decision is published here.
Come back by email
A short list of the week's newly reviewed papers. Nothing is sent until you confirm from your inbox, and every email has a link that stops it. No account.

No comments yet.
Sign in to comment