Maximiliano Hormazábal Lagos, Álvaro Bueno Saez, Héctor Cerezo-Costas
et al.
In this paper we expose our approach to solve the \textit{SemEval 2025 Task 8: Question-Answering over Tabular Data} challenge. Our strategy leverages Python code generation with LLMs to interact with the table and get the answer to the questions. The process is composed of multiple steps: understanding the content of the table, generating natural language instructions in the form of steps to follow in order to get the answer, translating these instructions to code, running it and handling potential errors or exceptions. These steps use open source LLMs and fine grained optimized prompts for each task (step). With this approach, we achieved a score of $70.50\%$ for subtask 1.
Valérie Berthé, Toghrul Karimov, Joris Nieuwveld
et al.
We investigate the decidability of the monadic second-order (MSO) theory of the structure $\langle \mathbb{N};<,P_1, \ldots,P_d \rangle$, for various unary predicates $P_1,\ldots,P_d \subseteq \mathbb{N}$. We focus in particular on 'arithmetic' predicates arising in the study of linear recurrence sequences, such as fixed-base powers $k^{\mathbf{N}} = \{k^n : n \in \mathbb{N}\}$, $k$-th powers $\mathbf{N}^k = \{n^k : n \in \mathbb{N}\}$, and the set of terms of the Fibonacci sequence $\mathsf{Fib} = \{0,1,2,3,5,8,13,\ldots\}$ (and similarly for other linear recurrence sequences having a single, non-repeated, dominant characteristic root). We obtain several new unconditional and conditional decidability results, a select sample of which are the following: $\bullet$ The MSO theory of $\langle \mathbb{N};<, 2^{\mathbf{N}}, \mathsf{Fib} \rangle$ is decidable; $\bullet$ The MSO theory of $\langle \mathbb{N};<, 2^{\mathbf{N}}, 3^{\mathbf{N}}, 6^{\mathbf{N}} \rangle$ is decidable; $\bullet$ The MSO theory of $\langle \mathbb{N};<, 2^{\mathbf{N}}, 3^{\mathbf{N}}, 5^{\mathbf{N}} \rangle$ is decidable assuming Schanuel's conjecture; $\bullet$ The MSO theory of $\langle \mathbb{N};<, 4^{\mathbf{N}}, \mathbf{N}^2 \rangle$ is decidable; $\bullet$ The MSO theory of $\langle \mathbb{N};<, 2^{\mathbf{N}}, \mathbf{N}^2 \rangle$ is Turing-equivalent to the MSO theory of $\langle \mathbb{N};<,S \rangle$, where $S$ is the predicate corresponding to the binary expansion of $\sqrt{2}$. (As the binary expansion of $\sqrt{2}$ is widely believed to be normal, the corresponding MSO theory is in turn expected to be decidable.) These results are obtained by exploiting and combining techniques from dynamical systems, number theory, and automata theory.
In this work, product tables in invoices are obtained autonomously via a deep learning model, which is named as ExTTNet. Firstly, text is obtained from invoice images using Optical Character Recognition (OCR) techniques. Tesseract OCR engine [37] is used for this process. Afterwards, the number of existing features is increased by using feature extraction methods to increase the accuracy. Labeling process is done according to whether each text obtained as a result of OCR is a table element or not. In this study, a multilayer artificial neural network model is used. The training has been carried out with an Nvidia RTX 3090 graphics card and taken $162$ minutes. As a result of the training, the F1 score is $0.92$.
In 1738, the King of Naples and future King of Spain, Carlos III, commissioned the Spanish military engineer Roque Joaquín de Alcubierre to begin the excavations of the ruins of the ancient Roman city of Pompeii and its surroundings, buried by the terrible explosion of Vesuvius in AD 79. Since that time, archaeologists have brought to light wonderful treasures found in the among ruins. Among them, the Sator Square is one of the most peculiar, apparently simple but mysterious. Supernatural and medicinal powers have been attributed to this object and its use was widespread during the Middle Age. Studies to explain its origin and meaning have been varied. There are theories that relate it to religion, the occult, medicine and music. However, no explanation has been convincing beyond pseudo-scientific sensationalism. In this study, the author intends to eliminate the mystical character of the Sator Square and suggests considering it as a simple palindrome or a game of words with certain symmetrical properties. However, these properties are not exclusive to the Sator Suare but are present in various mathematical and geometric objects.
Analysing several characteristic mathematical models: natural and real numbers, Euclidean geometry, group theory, and set theory, I argue that a mathematical model in its final form is a junction of a set of axioms and an internal partial interpretation of the corresponding language. It follows from the analysis that (i) mathematical objects do not exist in the external world: they are imagined objects, some of which, at least approximately, exist in our internal world of activities or we can realize or represent them there; (ii) mathematical truths are not truths about the external world but specifications (formulations) of mathematical conceptions; (iii) mathematics is first and foremost our imagined tool by which, with certain assumptions about its applicability, we explore nature and synthesize our rational cognition of it.
Rik Koncel-Kedziorski, Michael Krumdick, Viet Lai
et al.
Answering questions within business and finance requires reasoning, precision, and a wide-breadth of technical knowledge. Together, these requirements make this domain difficult for large language models (LLMs). We introduce BizBench, a benchmark for evaluating models' ability to reason about realistic financial problems. BizBench comprises eight quantitative reasoning tasks, focusing on question-answering (QA) over financial data via program synthesis. We include three financially-themed code-generation tasks from newly collected and augmented QA data. Additionally, we isolate the reasoning capabilities required for financial QA: reading comprehension of financial text and tables for extracting intermediate values, and understanding financial concepts and formulas needed to calculate complex solutions. Collectively, these tasks evaluate a model's financial background knowledge, ability to parse financial documents, and capacity to solve problems with code. We conduct an in-depth evaluation of open-source and commercial LLMs, comparing and contrasting the behavior of code-focused and language-focused models. We demonstrate that the current bottleneck in performance is due to LLMs' limited business and financial understanding, highlighting the value of a challenging benchmark for quantitative reasoning within this domain.
The problem of infinities in quantum field theory (QRT) is a long standing problem in physics.For solving this problem, different renormalization techniques have been suggested but the problem still persists. Here we suggest another approachto the elimination of infinities in QFT, which is based on non-Diophantine arithmetics - a novel mathematical area that already found useful applications in physics. To achieve this goal, new non-Diophantine arithmetics are constructed and their properties are studied. This allows using these arithmetics for computing integrals describing Feynman diagrams. Although in the conventional QFT these integrals diverge, their non-Diophantine counterparts are convergent and rigorously defined.
This research concerns the estimation of latent linear or polychoric correlations from fuzzy frequency tables. Fuzzy counts are of particular interest to many disciplines including social and behavioral sciences, and are especially relevant when observed data are classified using fuzzy categories - as for socio-economic studies, clinical evaluations, content analysis, inter-rater reliability analysis - or when imprecise observations are classified into either precise or imprecise categories - as for the analysis of ratings data or fuzzy coded variables. In these cases, the space of count matrices is no longer defined over naturals and, consequently, the polychoric estimator cannot be used to accurately estimate latent linear correlations. The aim of this contribution is twofold. First, we illustrate a computational procedure based on generalized natural numbers for computing fuzzy frequencies. Second, we reformulate the problem of estimating latent linear correlations from fuzzy counts in the context of Expectation-Maximization based maximum likelihood estimation. A simulation study and two applications are used to investigate the characteristics of the proposed method. Overall, the results show that the fuzzy EM-based polychoric estimator is more efficient to deal with imprecise count data as opposed to standard polychoric estimators that may be used in this context.
Anish K. Vallapuram, Nikhil Nanda, Young D. Kwon
et al.
The survival of a business is undeniably pertinent to its success. A key factor contributing to its continuity depends on its customers. The surge of location-based social networks such as Yelp, Dianping, and Foursquare has paved the way for leveraging user-generated content on these platforms to predict business survival. Prior works in this area have developed several quantitative features to capture geography and user mobility among businesses. However, the development of qualitative features is minimal. In this work, we thus perform extensive feature engineering across four feature sets, namely, geography, user mobility, business attributes, and linguistic modelling to develop classifiers for business survival prediction. We additionally employ an interpretability framework to generate explanations and qualitatively assess the classifiers' predictions. Experimentation among the feature sets reveals that qualitative features including business attributes and linguistic features have the highest predictive power, achieving AUC scores of 0.72 and 0.67, respectively. Furthermore, the explanations generated by the interpretability framework demonstrate that these models can potentially identify the reasons from review texts for the survival of a business.
Axiomatizing mathematical structures and theories is an objective of Mathematical Logic. Some axiomatic systems are nowadays mere definitions, such as the axioms of Group Theory; but some systems are much deeper, such as the axioms of Complete Ordered Fields with which Real Analysis starts. Groups abound in mathematical sciences, while by Dedekind's theorem there exists only one complete ordered field, up to isomorphism. Cayley's theorem in Abstract Algebra implies that the axioms of group theory completely axiomatize the class of permutation sets that are closed under composition and inversion. In this article, we survey some old and new results on the first-order axiomatizability of various mathematical structures. We will also review identities over addition, multiplication, and exponentiation that hold in the set of positive real numbers.
We study a generalisation of Simpson reversal (also known as Simpson's paradox or the Yule-Simpson effect) to $2 \times 2 \times 2$ contingency tables and characterise the cases for which it can and cannot occur with two combinatorial-geometric lemmas. We also present a conjecture based on some computational experiments on the expected likelihood of such events.
This paper continues the discussion of the representation of ontologies in the first-order logical environment FOLE. According to Gruber, an ontology defines the primitives with which to model the knowledge resources for a community of discourse. These primitives, consisting of classes, relationships and properties, are represented by the entity-relationship-attribute ERA data model of Chen. An ontology uses formal axioms to constrain the interpretation of these primitives. In short, an ontology specifies a logical theory. A series of three papers by the author provide a rigorous mathematical representation for the ERA data model in particular, and ontologies in general, within FOLE. The first two papers, which provide a foundation and superstructure for FOLE, represent the formalism and semantics of (many-sorted) first-order logic in a classification form corresponding to ideas discussed in the Information Flow Framework (IFF). The third paper will define an interpretation of FOLE in terms of the transformational passage, first described in (Kent, 2013), from the classification form of first-order logic to an equivalent interpretation form, thereby defining the formalism and semantics of first-order logical/relational database systems. Two papers will provide a precise mathematical basis for FOLE interpretation: the current paper develops the notion of a FOLE relational table following the relational model of Codd, and a follow-up paper will develop the notion of a FOLE relational database. Both of these papers expand on material found in the paper (Kent, 2011). Although the classification form follows the entity-relationship-attribute data model of Chen, the interpretation form follows the relational data model of Codd. In general, the FOLE representation uses a conceptual structures approach, that is completely compatible with formal concept analysis and information flow.
The VIKOR (Vlse Kriterijumska Optimizacija Kompromisno Resenje which means multi-criteria optimization and compromise solution, in Serbian) method has already become a quite popular multi-criteria decision making tool for its computational simplicity and solution accuracy. This method focuses on selecting and ranking from a set of feasible alternatives, and determines compromise solution for a problem with conflicting criteria to help the decision maker in reaching a final course of action. It determines the compromise ranking list based on the particular measure of closeness to the ideal solution. Depending upon the type of decision problem and necessity of the decision maker, apart from VIKOR method, different variants of it, like comprehensive VIKOR, fuzzy VIKOR, regret theory-based VIKOR, modified VIKOR and interval VIKOR methods have also been subsequently developed. In this paper, the ranking performance of original VIKOR method and its five variants is analyzed based on two demonstrative examples. It is observed that interval VIKOR method performs unsatisfactorily and when the information in a decision problem is imprecise, fuzzy VIKOR method should always be preferred. But, for any decision problem, original VIKOR is the best method for solution without unnecessarily complicating the related mathematical computations.
Analysis, Business mathematics. Commercial arithmetic. Including tables, etc.
Motivated by the music-theoretical work of Richard Cohn and David Clampitt on late-nineteenth century harmony, we mathematically prove that the PL-group of a hexatonic cycle is dual (in the sense of Lewin) to its T/I-stabilizer. Our point of departure is Cohn's notions of maximal smoothness and hexatonic cycle, and the symmetry group of the 12-gon; we do not make use of the duality between the T/I-group and PLR-group. We also discuss how some ideas in the present paper could be used in the proof of T/I-PLR duality by Crans--Fiore--Satyendra.
When comparing the citation impact of nations, departments or other groups of researchers within individual fields, three approaches have been proposed: arithmetic means, geometric means, and percentage in the top X%. This article compares the precision of these statistics using 97 trillion experimentally simulated citation counts from 6875 sets of different parameters (although all having the same scale parameter) based upon the discretised lognormal distribution with limits from 1000 repetitions for each parameter set. The results show that the geometric mean is the most precise, closely followed by the percentage of a country's articles in the top 50% most cited articles for a field, year and document type. Thus the geometric mean citation count is recommended for future citation-based comparisons between nations. The percentage of a country's articles in the top 1% most cited is a particularly imprecise indicator and is not recommended for international comparisons based on individual fields. Moreover, whereas standard confidence interval formulae for the geometric mean appear to be accurate, confidence interval formulae are less accurate and consistent for percentile indicators. These recommendations assume that the scale parameters of the samples are the same but the choice of indicator is complex and partly conceptual if they are not.
This paper describes the design and implementation of mechanisms for light-weight inclusion of formal mathematics in informal mathematical writings, particularly in a Web-based setting. This is conceptually done in three stages: (i) by choosing a suitable representation layer (based on RDF) for encoding the information about available resources of formal mathematics, (ii) by exporting this information from formal libraries, and (iii) by providing syntax and implementation for including formal mathematics in informal writings. We describe the use case of an author referring to formal text from an informal narrative, and discuss design choices entailed by this use case. Furthermore, we describe an implementation of the use case within the Agora prototype: a Wiki for collaborating on formalized mathematics.
We present the Cauchois and Sénémaud Tables of X-ray emission lines and absorption edges. They are written both in French and English. They were published in 1978 by Pergamon Press and are insufficiently known. However they are of large interest because of their completeness. They comprise the energies of all the K, L, M, N and O emission lines of natural elements from lithium up to uranium as well as the energies of satellite emissions and absorption discontinuities. The more intense lines of radio-elements up to fermium (Z = 100) are also given. The Tables range from the hard X-rays (122 keV, 0.01 nm) to the extreme ultra-violet (12 eV, 102 nm). For each transition, the wavelength (Å and uX) and energy (eV and Ry) are given and references are indicated. The transitions are grouped by increasing wavelength (decreasing photon energy) and also by element and spectral series. We present, as an example, the use of the Tables to identify the emissions of the molybdenum L spectrum. We decided to scan the Cauchois and Sénémaud Tables and make them available for the scientific community. They are now available at the Website of our laboratory, http://www.lcpmr.upmc.fr/.
Science and mathematics help people to better understand world, eliminating many inconsistencies, fallacies and misconceptions. One of such misconceptions is related to arithmetic of natural numbers, which is extremely important both for science and everyday life. People think their counting is governed by the rules of the conventional arithmetic and thus other kinds of arithmetics of natural numbers do not exist and cannot exist. However, this popular image of the situation with the natural numbers is wrong. In many situations, people have to utilize and do implicitly utilize rules of counting and operating different from rules and operations in the conventional arithmetic. This is a consequence of the existing diversity in nature and society. To correctly represent this diversity, people have to explicitly employ different arithmetics. To make a distinction, we call the conventional arithmetic by the name Diophantine arithmetic, while other arithmetics are called non-Diophantine. There are two big families of non-Diophantine arithmetics: projective arithmetics and dual arithmetics (Burgin, 1997). In this work, we give an exposition of projective arithmetics, presenting their properties and considering also a more general mathematical structure called a projective prearithmetic. The Diophantine arithmetic is a member of this parametric family: its parameter is equal to the identity function f(x) = x. In conclusion, it is demonstrated how non-Diophantine arithmetics may be utilized beyond mathematics and how they allow one to eliminate inconsistencies and contradictions encountered by other researchers.
Erich Schikuta, Thomas Weishaeupl, Flavia Donno
et al.
From 2004 to 2007 the Business In the Grid (BIG) project took place and was driven by the following goals: Firstly, make business aware of Grid technology and, secondly, try to explore new business models. We disseminated Grid computing by mainly concentrating on the central European market and interviewed several companies in order to gain insights into the Grid acceptance in industrial environments. In this article we present the results of the project, elaborate on a critical discussion on business adaptations, and describe a novel dynamic authorization workflow for business processes in the Grid.