arXiv research

FAKTA automates fact checking across media sources.

Research aims to make fact-checking models more transparent.

We create a large dataset for fact checking claims and improve prediction accuracy.

Paper tackles stance detection across domains using adversarial domain adaptation.

Paper develops a model for verifying facts in tables without pre-retrieved evidence.

Time-aware fact-checking improves veracity predictions for time-sensitive claims.

Ranked second in fact-checking task, using DRR NN with embeddings.

Task focuses on fact checking in Q&A forums, improving over baseline systems.

A novel fact-checking method using debate dynamics on knowledge graphs.

Online social networking sites are experimenting with the following crowd-powered procedure to reduce the spread of fake news and misinformation: whenever a user is exposed to a story through her feed, she can flag the story as misinformation and, if the story receives enough flags, it is sent to a trusted third party …

The paper proposes a tool to detect invalid inputs in DL models.

Program synthesis is the task of automatically generating a program consistent with a specification. Recent years have seen proposal of a number of neural approaches for program synthesis, many of which adopt a sequence generation paradigm similar to neural machine translation, in which sequence-to-sequence models are …

Analyzed Indian stock market data to find stylized facts with deviations.

Developed a neural topic model for classifying COVID-19 disinformation.

We describe the infinitesimal moduli space of pairs $(Y, V)$ where $Y$ is a manifold with $G_2$ holonomy, and $V$ is a vector bundle on $Y$ with an instanton connection. These structures arise in connection to the moduli space of heterotic string compactifications on compact and non-compact seven dimensional spaces, e.…

Develops LF-PPL for non-differentiable models with automatic boundary checks.

By exploiting standard facts about $N=1$ and $N=2$ supersymmetric Yang-Mills theory, the Donaldson invariants of four-manifolds that admit a Kahler metric can be computed. The results are in agreement with available mathematical computations, and provide a powerful check on the standard claims about supersymmetric Yang…

The paper examines bias in ML models using the Adult dataset.

This work tackles runtime complexity prediction for code, using machine learning and a new dataset.

The paper examines circle graphs of Gauss diagrams and finds counterexamples to previous descriptions.

Geometric deep learning detects fake news on social media.

We investigate the rigidity and asymptotic properties of quantum SU(2) representations of mapping class groups. In the spherical braid group case the trivial representation is not isolated in the family of quantum SU(2) representations. In particular, they may be used to give an explicit check that spherical braid grou…

SMC analysis reveals key transient effects in macroeconomic ABM.

The topological underpinnings are presented for a new algorithm which answers the question: `Is a given knot the unknot?' The algorithm uses the braid foliation technology of Bennequin and of Birman and Menasco. The approach is to consider the knot as a closed braid, and to use the fact that a knot is unknotted if and …

When modelling stock market dynamics, the price formation is often based on an equilbrium mechanism. In real stock exchanges, however, the price formation is goverend by the order book. It is thus interesting to check if the resulting stylized facts of a model with equilibrium pricing change, remain the same or, more g…

We study coordinate-invariance of some asymptotic invariants such as the ADM mass or the Chruściel-Herzlich momentum, given by an integral over a "boundary at infinity". When changing the coordinates at infinity, some terms in the change of integrand do not decay fast enough to have a vanishing integral at infinity; bu…

A new method detects anomalies in images without needing model adjustments.

We introduce a new model in order to describe the fluctuation of tick-by-tick financial time series. Our model, based on marked point process, allows us to incorporate in a unique process the duration of the transaction and the corresponding volume of orders. The model is motivated by the fact that the "excitation" of …

Improves sampling from complex hierarchical models using HMC and automatic marginalization.

Supervised learning is an active research area, with numerous applications in diverse fields such as data analytics, computer vision, speech and audio processing, and image understanding. In most cases, the loss functions used in machine learning assume symmetric noise models, and seek to estimate the unknown function …

Ultrasound diagnosis is routinely used in obstetrics and gynecology for fetal biometry, and owing to its time-consuming process, there has been a great demand for automatic estimation. However, the automated analysis of ultrasound images is complicated because they are patient-specific, operator-dependent, and machine-…

Multifractal analysis and extensive statistical tests are performed upon intraday minutely data within individual trading days for four stock market indexes (including HSI, SZSC, S&P500, and NASDAQ) to check whether the indexes (instead of the returns) possess multifractality. We find that the mass exponent $τ(q)$ is l…

New functions derived from arrow diagrams for spherical curves, invariant under certain deformations.

We develop a method that is based on processing gathered Event Related Potentials (ERP) signals and the use of machine learning technique for multivariate analysis (i.e. classification) that we apply in order to analyze the differences between Dyslexic and Skilled readers. No human intervention is needed in the analysi…

Two geometric tests for forward-flatness are shown to be dual.

This is the first of three articles on the Fibered Isomorphism Conjecture of Farrell and Jones for L-theory. We apply the general techniques developed in [15] and [16] to the L-theory case of the conjecture and prove several results. Here we prove the conjecture, after inverting 2, for poly-free groups. In particular, …

The study develops a logic reasoner to verify MS case management specifications.

This paper deforms complex tori and their mirrors using gerbes.

This paper works out fair values of stock loan model with automatic termination clause, cap and margin. This stock loan is treated as a generalized perpetual American option with possibly negative interest rate and some constraints. Since it helps a bank to control the risk, the banks charge less service fees compared …

Statistical model checking for PCTL on MDPs using reinforcement learning.

Autotune optimizes Lasso tuning parameters efficiently and accurately.

LLMs will inevitably hallucinate due to their mathematical structure.

This research simplifies verification of machine learning systems using reparameterization.

We formalize and verify double auctions for multiple-quantity trades.

This paper describes a method for the automatic evaluation of the Links-Gould two-variable polynomial link invariant (LG) for any link, given only a braid presentation. This method is currently feasible for the evaluation of LG for links for which we have a braid presentation of string index at most 5. Data are present…

It is time-consuming and error-prone to implement inference procedures for each new probabilistic model. Probabilistic programming addresses this problem by allowing a user to specify the model and having a compiler automatically generate an inference procedure for it. For this approach to be practical, it is important…

Efficient algorithms for clustered Lasso and OSCAR reduce computational costs.

We present a study on predicting the factuality of reporting and bias of news media. While previous work has focused on studying the veracity of claims or documents, here we are interested in characterizing entire news media. These are under-studied but arguably important research problems, both in their own right and …