搜索结果：Invented

Predicate invention (PI), the creation of new predicates to extend the hypothesis space, remains a critical bottleneck in Inductive Logic Programming (ILP). Existing methods rely on domain expertise and produce semantically opaque predicates, hindering adaptation to unfamiliar domains and cross-task reuse. We present ADVENT, an LLM-driven PI mechanism for ILP. ADVENT pairs LLM abductive generation with Prolog deductive verification, forming an iterative loop in which concrete execution results guide the LLM to refine candidate predicates. The mechanism leverages Large Language Models to identify implicit patterns in structured relational data and invent auxiliary predicates with meaningful names and definitions. Invented predicates and learned rules accumulate in a knowledge pool for cross-task reuse. Experiments on nine poker-hand concepts across seven LLMs show that LLM-driven PI achieves 58% success rate where ILP alone fails entirely, formal verification raises this to 80%, and the knowledge pool yields gains up to +31 percentage points, while producing human-interpretable rules. These results suggest that ADVENT offers a promising direction for automating predicate invention a

The latest improvements in artificial intelligence (AI) raise new challenges for intellectual property laws, particularly concerning the inventorship issue in AI-assisted inventions - that is, those in which AI is used in the inventive process. While most jurisdictions allow only a natural person to be considered the inventor, the question of how to deal with AI-assisted inventions remains relevant. Namely, what is the nature and contribution of AI tools in an AI-assisted invention that would prevent a human from being recognized as its inventor? The main challenge in addressing this question is the lack of case law on the issue. It is reasonable to assume that with the development of AI and the growing interest in its use in the inventive process, new cases will naturally arise, which in turn will harmonize and address the inventorship issue in AI-assisted inventions to some extent. However, this process will take significant time and may not keep pace with the rapid development of AI, nor fully address the new problems that arise alongside AI advancements. This research proposes the conditions of an experiment to create relevant case law. This experiment could be initiated by soc

The human ability to learn rules and solve problems has been a central concern of cognitive science research since the field's earliest days. But we do not just follow rules and solve problems given to us by others: we modify those rules, create new problems, and set new goals and tasks for ourselves and others. Arguably, even more than rule following and problem solving, human intelligence is about creatively breaking and stretching the rules, changing the game, and inventing new problems worth thinking about. Creating a good rule or a good problem depends not just on the ideas one can think up but on how one evaluates such proposals. Here, we study invention through the lens of game design. We focus particularly on the early stages of novice, "everyday" game creation, where the stakes are low. We draw on a dataset of over 450 human created games, created by participants who saw an initial seed set of two-player grid-based strategy games. We consider two different cognitive mechanisms that may be at work during the early processes of intuitive game invention: an associative proposal based on previous games one has seen and compute-bounded model-based evaluation that an everyday ga

Generalizing from individual skill executions to long-horizon tasks is a core challenge in building autonomous robots. A promising direction is learning high-level, symbolic representations of low-level robot skills, enabling abstract reasoning independent of the low-level state space. Recent advances in foundation models have made it possible to generate symbolic predicates that operate on raw sensory inputs-a process we call generative predicate invention-to facilitate downstream representation learning. However, prior work learns these abstractions using heuristic or ad-hoc procedures, ignoring the question of which formal properties they ought to satisfy, and how to guarantee these properties. We address these questions by presenting a formal theory of generative predicate invention for task-level planning, and proposing SkillWrapper, a method that learns symbolic models for provably sound and complete planning. Our approach leverages foundation models to actively collect robot data and learn human-interpretable, plannable representations, using only RGB image observations. Our extensive empirical evaluation in simulation and on real robots shows that SkillWrapper learns abstra

In this work, we prove over 3000 previously ATP-unproved Mizar/MPTP problems by using several ATP and AI methods, raising the number of ATP-solved Mizar problems from 75\% to above 80\%. First, we start to experiment with the cvc5 SMT solver which uses several instantiation-based heuristics that differ from the superposition-based systems, that were previously applied to Mizar,and add many new solutions. Then we use automated strategy invention to develop cvc5 strategies that largely improve cvc5's performance on the hard problems. In particular, the best invented strategy solves over 14\% more problems than the best previously available cvc5 strategy. We also show that different clausification methods have a high impact on such instantiation-based methods, again producing many new solutions. In total, the methods solve 3021 (21.3\%) of the 14163 previously unsolved hard Mizar problems. This is a new milestone over the Mizar large-theory benchmark and a large strengthening of the hammer methods for Mizar.

Term rewriting plays a crucial role in software verification and compiler optimization. With dozens of highly parameterizable techniques developed to prove various system properties, automatic term rewriting tools work in an extensive parameter space. This complexity exceeds human capacity for parameter selection, motivating an investigation into automated strategy invention. In this paper, we focus on confluence, an important property of term rewrite systems, and apply machine learning to develop the first learning-guided automatic confluence prover. Moreover, we randomly generate a large dataset to analyze confluence for term rewrite systems. Our results focus on improving the state-of-the-art automatic confluence prover CSI: When equipped with our invented strategies, it surpasses its human-designed strategies both on the augmented dataset and on the original human-created benchmark dataset Cops, proving/disproving the confluence of several term rewrite systems for which no automated proofs were known before.

A knowledge search is a key process for inventions. However, there is inadequate quantitative modeling of dynamic knowledge search processes and associated search costs. In this study, agent-based and complex network methodologies were proposed to quantitatively describe the dynamic process of knowledge search for actual inventions. Prior knowledge networks (PKNs), the search space of historical patents, were constructed, representative search rules were formulated for R&D agents, and measures for knowledge search cost were designed to serve as search objectives. Simulation results in the field of photolithographic technology show that search costs differ significantly with different search rules. Familiarity and Degree rules significantly outperform BFS, DFS and Recency rules in terms of knowledge search costs, and are less affected by the size and density of PKNs. Interestingly, there is no significant correlation between the mean and variance of search costs and patent value, indicating that high-value patents are not particularly difficult to obtain. The implications for innovation theories and R&D practices are drawn from the models and results.

Abstraction is key to scaling up reinforcement learning (RL). However, autonomously learning abstract state and action representations to enable transfer and generalization remains a challenging open problem. This paper presents a novel approach for inventing, representing, and utilizing options, which represent temporally extended behaviors, in continual RL settings. Our approach addresses streams of stochastic problems characterized by long horizons, sparse rewards, and unknown transition and reward functions. Our approach continually learns and maintains an interpretable state abstraction, and uses it to invent high-level options with abstract symbolic representations. These options meet three key desiderata: (1) composability for solving tasks effectively with lookahead planning, (2) reusability across problem instances for minimizing the need for relearning, and (3) mutual independence for reducing interference among options. Our main contributions are approaches for continually learning transferable, generalizable options with symbolic representations, and for integrating search techniques with RL to efficiently plan over these learned options to solve new problems. Empirical

We propose two procedures to create painting styles using models trained only on natural images, providing objective proof that the model is not plagiarizing human art styles. In the first procedure we use the inductive bias from the artistic medium to achieve creative expression. Abstraction is achieved by using a reconstruction loss. The second procedure uses an additional natural image as inspiration to create a new style. These two procedures make it possible to invent new painting styles with no artistic training data. We believe that our approach can help pave the way for the ethical employment of generative AI in art, without infringing upon the originality of human creators.

The ability to generalise from a small number of examples is a fundamental challenge in machine learning. To tackle this challenge, we introduce an inductive logic programming (ILP) approach that combines negation and predicate invention. Combining these two features allows an ILP system to generalise better by learning rules with universally quantified body-only variables. We implement our idea in NOPI, which can learn normal logic programs with predicate invention, including Datalog programs with stratified negation. Our experimental results on multiple domains show that our approach can improve predictive accuracies and learning times.

Nikola Tesla is often presented by his adepts as the "unjustly forgotten genius", without who our current technology wouldn't exist. In this paper, we analyze some popular statements made by Tesla's adepts, mostly about inventions that they attribute to him, and determine whether they are myth or reality.

The cultural infrastructure that let Galileo invent the modern physics is discussed. The key new element of modern physics was firm belief in its fundamental structure, which could be expressed in the double postulate: 1) There are fundamental axioms that all the physical laws could be deduced from; those axioms are not evident, as invisible as the underground foundation stones, or, in Latin, fundamentum; 2) The human mind is able to probe into this fundamental level of the Universe to understand its working, and any person is free to contribute in the process of this probing and understanding. Experimentalism and mathematization were just the tools to realize this belief. The modern science was invented in the time when the Bible played the most prominent cultural role in its history due to Gutenberg and Reformation. All the originators of the modern physics were profound biblical believers, and for them the fundamental double postulate was supported by the basic postulates of Biblical worldview. Keywords - the Needham Question; the Scientific Revolution; modern physics; cultural infrastructure; Biblical civilization; theory of gravity

In a paper appearing in Annalen der Physik in 1930 Leon Rosenfeld invented the first procedure for producing Hamiltonian constraints. He displayed and correctly distinguished the vanishing Hamiltonian generator of time evolution, and the vanishing generator of gauge transformations for general relativity with Dirac electron and electrodynamic field sources. Though he did not do so, had he chosen one of his tetrad fields to be normal to his spacetime foliation, he would have anticipated by almost thirty years the general relativisitic Hamiltonian first published by Paul Dirac.

In this very short note we review some historical aspects of photomultiplier tube invention. It is our tribute to the memory of great Soviet-Russian physicist and engineer Leonid Aleksandrovitch Kubetsky whose life and scientific achievements are described briefly. Particular efforts are made to shed light on a controversial issue of who invented the first photomultiplier tube. It is asserted that if to recognize L.A.Kubetsky's priority on the photomultiplier tube invention the last Beaune Conference would be held on the eve of the 75th Anniversary of that great event.

NASA's PACE satellite captured the Black Sea glowing turquoise during its annual phytoplankton bloom。 The vivid color comes from massive numbers of coccolithophores, microscopic organisms whose reflective shells brighten the water enough to be seen from space。 An astronaut aboard the International Space Station also photographed the bloom spreading