In this paper, we introduce a set of spatial-temporal logic rules as knowledge to explain human actions.

Therefore, neuro-symbolic RL aims at creating policies that are interpretable in the first place. Unfortunately, interpretability is not explainability. To achieve both, we introduce Neurally gUided Differentiable loGic policiEs (NUDGE).

Recently, Language Models (LMs) have demonstrated complex reasoning capacities even without any finetuning.

In this paper, we propose a two-stage framework that imposes both structural and textual knowledge to learn rule-based systems. In the first stage, we compute a set of triples with confidence scores (called soft triples) from a text corpus by distant supervision, where a textual entailment model with multi-instance learning is exploited to estimate whether a given triple is entailed by a set of sentences. In the second stage, these soft triples are used to learn a rule-based model for KGC.

The British skeleton team - among Team GB's best hopes for medals at the Winter Olympics - have been told their helmets do not meet safety standards only days out from the competition starting. The British team have appealed to the Court of Arbitration for sport (Cas) after the International Bobsleigh and Skeleton Federation (IBSF) said the helmets did not comply with the IBSF skeleton rules based on its shape. The British Bobsleigh and Skeleton Association (BBSA) said the helmet was designed with safety in mind. The team would currently not be able to wear the helmets in competition, but the Cas ruling will be heard on Thursday, with the result expected on Friday, before competition begins on 12 February. The British skeleton team enjoyed a successful 2024-25 season, with Matt Weston winning overall World Cup gold and Marcus Wyatt silver, winning all seven races between them.

Why is the US Fed chair criminal probe causing alarm? Inside Story Is the world's rules-based order ruptured? Canadian Prime Minister Mark Carney says system is broken, with world powers employing force. The world's rules-based order is ruptured, Canadian Prime Minister Mark Carney has said, in a speech at the World Economic Forum in Davos, Switzerland that avoided mentioning United States President Donald Trump. While Trump hit back at Carney, the Canadian leader's words have been widely praised and analysed.

Imposing order on the world is seductive, but it flattens out the diversity and rich messiness of human life. Oddly, playing by the rules may help us fight back, argues C. Thi Nguyen in The Score THIS time last year, I wrote an article for New Scientist about the perfect way to cook the classic pasta dish cacio e pepe, according to physicists. The meal's smooth, glossy emulsion of black pepper, pecorino cheese and water is hard to make lump-free. Ivan Di Terlizzi at the Max Planck Institute for the Physics of Complex Systems in Germany and his colleagues cooked cacio e pepe hundreds of times until they produced an exacting and foolproof method. The story proved popular with readers.

How much is US support for Israel costing Trump? What is a Palestinian without olives? Why are Gaza's homes collapsing in winter? 'The end of the world as we know it': Is the rules-based order finished? Canadian Prime Minister Mark Carney said the quiet part out loud at the World Economic Forum: what many call the global rules-based order was either collapsing or had collapsed already.

Financial transactions are increasingly being handled by automated programs called . However, one challenge in the adaptation of smart contracts is the presence of vulnerabilities, which can cause significant monetary loss.In 2024, $247.88 M was lost in 20 smart contract exploits.According to a recent study, accounting bugs (i.e., incorrect implementations of domain-specific financial models) are the most prevalent type of vulnerability, and are one of the most difficult to find, requiring substantial human efforts.While Large Language Models (LLMs) have shown promise in identifying these bugs, they often suffer from lack of generalization of vulnerability types, hallucinations, and problems with representing smart contracts in limited token context space.This paper proposes a hybrid system combining LLMs and rule-based reasoning to detect accounting error vulnerabilities in smart contracts. In particular, it utilizes the understanding capabilities of LLMs to annotate the financial meaning of variables in smart contracts, and employs rule-based reasoning to propagate the information throughout a contract's logic and to validate potential vulnerabilities.To remedy hallucinations, we propose a feedback loop where validation is performed by providing the reasoning trace of vulnerabilities to the LLM for iterative self-reflection. We achieve 75.6% accuracy on the labelling of financial meanings against human annotations. Furthermore, we achieve a recall of 90.5% from running on 23 real-world smart contract projects containing 21 accounting error vulnerabilities.Finally, we apply the automated technique on 8 recent projects, finding 4 known and 2 unknown bugs.