OpenStreetMap (OSM) is a vital resource for investigative journalists doing geolocation verification. However, existing tools to query OSM data such as Overpass Turbo require familiarity with complex query languages, creating barriers for non-technical users. We present SPOT, an open source natural language interface that makes OSM's rich, tag-based geographic data more accessible through intuitive scene descriptions. SPOT interprets user inputs as structured representations of geospatial object configurations using fine-tuned Large Language Models (LLMs), with results being displayed in an interactive map interface. While more general geospatial search tasks are conceivable, SPOT is specifically designed for use in investigative journalism, addressing real-world challenges such as hallucinations in model output, inconsistencies in OSM tagging, and the noisy nature of user input. It combines a novel synthetic data pipeline with a semantic bundling system to enable robust, accurate query generation. To our knowledge, SPOT is the first system to achieve reliable natural language access to OSM data at this level of accuracy. By lowering the technical barrier to geolocation verification, SPOT contributes a practical tool to the broader efforts to support fact-checking and combat disinformation.

Efficient multi-hop reasoning requires Large Language Models (LLMs) based agents to acquire high-value external knowledge iteratively. Previous work has explored reinforcement learning (RL) to train LLMs to perform search-based document retrieval, achieving notable improvements in QA performance, but underperform on complex, multi-hop QA resulting from the sparse rewards from global signal only. To address this gap in existing research, we introduce StepSearch, a framework for search LLMs that trained with step-wise proximal policy optimization method. It consists of richer and more detailed intermediate search rewards and token-level process supervision based on information gain and redundancy penalties to better guide each search step. We constructed a fine-grained question-answering dataset containing sub-question-level search trajectories based on open source datasets through a set of data pipeline method. On standard multi-hop QA benchmarks, it significantly outperforms global-reward baselines, achieving 11.2% and 4.2% absolute improvements for 3B and 7B models over various search with RL baselines using only 19k training data, demonstrating the effectiveness of fine-grained, stepwise supervision in optimizing deep search LLMs. Our code will be released on https://github.com/Zillwang/StepSearch.

Identity document (ID) image analysis has become essential for many online services, like bank account opening or insurance subscription. In recent years, much research has been conducted on subjects like document localization, text recognition and fraud detection, to achieve a level of accuracy reliable enough to automatize identity verification. However, there are only a few available datasets to benchmark ID analysis methods, mainly because of privacy restrictions, security requirements and legal reasons. In this paper, we present the DocXPand-25k dataset, which consists of 24,994 richly labeled IDs images, generated using custom-made vectorial templates representing nine fictitious ID designs, including four identity cards, two residence permits and three passports designs. These synthetic IDs feature artificially generated personal information (names, dates, identifiers, faces, barcodes, ...), and present a rich diversity in the visual layouts and textual contents. We collected about 5.8k diverse backgrounds coming from real-world photos, scans and screenshots of IDs to guarantee the variety of the backgrounds. The software we wrote to generate these images has been published (https://github.com/QuickSign/docxpand/) under the terms of the MIT license, and our dataset has been published (https://github.com/QuickSign/docxpand/releases/tag/v1.0.0) under the terms of the CC-BY-NC-SA 4.0 License.

The Institutional Analysis and Development (IAD) framework is a conceptual toolbox put forward by Elinor Ostrom and colleagues in an effort to identify and delineate the universal common variables that structure the immense variety of human interactions. The framework identifies rules as one of the core concepts to determine the structure of interactions, and acknowledges their potential to steer a community towards more beneficial and socially desirable outcomes. This work presents the first attempt to turn the IAD framework into a computational model to allow communities of agents to formally perform what-if analysis on a given rule configuration. To do so, we define the Action Situation Language -- or ASL -- whose syntax is hgighly tailored to the components of the IAD framework and that we use to write descriptions of social interactions. ASL is complemented by a game engine that generates its semantics as an extensive-form game. These models, then, can be analyzed with the standard tools of game theory to predict which outcomes are being most incentivized, and evaluated according to their socially relevant properties.

'As a result of federal initiatives to "get tough on crime," such as the Reagan Administration's War on Drugs and the Clinton Administration's "Three Strikes" laws, the total number of incarcerated Americans more than quadrupled from roughly 500,000 inmates in 1980 to 2.2 million inmates in 2015. During these decades, black Americans were incarcerated at a rate five times higher than that of white Americans. Despite a new 2019 US Bureau of Justice Statistics (BJS) report, which suggests that the racial disparity between white and black incarceration rates is "narrowing," a Pew Research Center review of BJS stats reveals that this 2019 report "counts only inmates sentenced to more than a year."Moreover, Whites accounted for 64% of adults but 30% of prisoners. . . . In 2017, there were 1,549 black prisoners for every 100,000 black adults--nearly six times the imprisonment rate for whites (272 per 100,000)."