Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
On Action Theories with Iterable First-Order Progression
Authors: Daxin Liu, Jens Claßen
AAAI 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We study the first-order definability of progression for situation calculus action theories with a focus on the iterability of progression. Progression, the task of updating a knowledge base according to actions effects so that proper information is retained, is notoriously challenging as it in general requires second-order logic. Exceptions where progression is first-order like local-effect actions and normal actions impose certain syntax constraints on action theories to eliminate second-order quantifiers in the progressed knowledge base. Unfortunately, the progressed result might not satisfy the constraints again, making it impossible to apply first-order progression iteratively. In this paper, we first lift the existing result on first-order progression for normal actions by allowing disjunctions in the knowledge base. As a result, we obtain an action theory whose type is called disjunctive normal, which is iteratively first-order progressable. Second, we propose a new class of action theories, called PANACK, that strictly subsumes the disjunctive normal ones, and we show that it remains iteratively first-order progressable as well. |
| Researcher Affiliation | Academia | Daxin Liu1*, Jens Claßen2 1 State Key Laboratory for Novel Software Technology, Nanjing University, China 2Institute for People and Technology, Roskilde University, Denmark EMAIL, EMAIL |
| Pseudocode | No | The paper includes formal definitions, theorems, propositions, and examples using logical notation, but no pseudocode blocks or algorithms are explicitly provided. |
| Open Source Code | No | The paper does not contain any statements or links indicating that open-source code for the described methodology is provided. |
| Open Datasets | No | The paper uses illustrative examples (Example 15, Example 22) to demonstrate its theoretical concepts, but these are small, custom scenarios, not references to or uses of publicly available datasets for empirical evaluation. |
| Dataset Splits | No | The paper is theoretical and does not involve experimental evaluation on datasets, thus there is no mention of dataset splits (e.g., training, testing, validation sets). |
| Hardware Specification | No | The paper is theoretical and focuses on logical formalisms and proofs. It does not describe any computational experiments or report results that would require specific hardware specifications. |
| Software Dependencies | No | The paper is theoretical and presents logical formalisms and proofs. It does not describe any computational experiments or implementations that would necessitate detailing specific software dependencies with version numbers. |
| Experiment Setup | No | The paper is theoretical, presenting logical frameworks and proofs. It does not describe any computational experiments, and therefore, no experimental setup details like hyperparameters or training configurations are provided. |