Goto

Collaborating Authors

 Government


An Auditable AI Agent Loop for Empirical Economics: A Case Study in Forecast Combination

arXiv.org Machine Learning

AI coding agents make empirical specification search fast and cheap, but they also widen hidden researcher degrees of freedom. Building on an open-source agent-loop architecture, this paper adapts that framework to an empirical economics workflow and adds a post-search holdout evaluation. In a forecast-combination illustration, multiple independent agent runs outperform standard benchmarks in the original rolling evaluation, but not all continue to do so on a post-search holdout. Logged search and holdout evaluation together make adaptive specification search more transparent and help distinguish robust improvements from sample-specific discoveries.


UK nuclear submarine deployed to Arabian Sea before Iran targets key US-UK base: reports

FOX News

This material may not be published, broadcast, rewritten, or redistributed. Quotes displayed in real-time or delayed by at least 15 minutes. Market data provided by Factset . Powered and implemented by FactSet Digital Solutions . Mutual Fund and ETF data provided by LSEG .


As cattle herds shrink and beef prices rise, investors back AI cow collars

FOX News

This material may not be published, broadcast, rewritten, or redistributed. Quotes displayed in real-time or delayed by at least 15 minutes. Market data provided by Factset . Powered and implemented by FactSet Digital Solutions . Mutual Fund and ETF data provided by LSEG .


Job-SDF: A Multi-Granularity Dataset for Job Skill Demand Forecasting and Benchmarking

Neural Information Processing Systems

In a rapidly evolving job market, skill demand forecasting is crucial as it enables policymakers and businesses to anticipate and adapt to changes, ensuring that workforce skills align with market needs, thereby enhancing productivity and competitiveness. Additionally, by identifying emerging skill requirements, it directs individuals towards relevant training and education opportunities, promoting continuous self-learning and development. However, the absence of comprehensive datasets presents a significant challenge, impeding research and the advancement of this field. To bridge this gap, we present Job-SDF, a dataset designed to train and benchmark job-skill demand forecasting models. Based on millions of public job advertisements collected from online recruitment platforms, this dataset encompasses monthly recruitment demand.Our dataset uniquely enables evaluating skill demand forecasting models at various granularities, including occupation, company, and regional levels. We benchmark a range of models on this dataset, evaluating their performance in standard scenarios, in predictions focused on lower value ranges, and in the presence of structural breaks, providing new insights for further research.


DAT: Improving Adversarial Robustness via Generative Amplitude Mix-up in Frequency Domain

Neural Information Processing Systems

To protect deep neural networks (DNNs) from adversarial attacks, adversarial training (AT) is developed by incorporating adversarial examples (AEs) into model training. Recent studies show that adversarial attacks disproportionately impact the patterns within the phase of the sample's frequency spectrum---typically containing crucial semantic information---more than those in the amplitude, resulting in the model's erroneous categorization of AEs. We find that, by mixing the amplitude of training samples' frequency spectrum with those of distractor images for AT, the model can be guided to focus on phase patterns unaffected by adversarial perturbations. As a result, the model's robustness can be improved. Unfortunately, it is still challenging to select appropriate distractor images, which should mix the amplitude without affecting the phase patterns.


YouTube job scam text: How to spot it fast

FOX News

This material may not be published, broadcast, rewritten, or redistributed. Quotes displayed in real-time or delayed by at least 15 minutes. Market data provided by Factset . Powered and implemented by FactSet Digital Solutions . Mutual Fund and ETF data provided by LSEG .


IMPACT: A Large-scale Integrated Multimodal Patent Analysis and Creation Dataset for Design Patents

Neural Information Processing Systems

In this paper, we introduce IMPACT (Integrated Multimodal Patent Analysis and Creation Dataset for Design Patents), a large-scale multimodal patent dataset with detailed captions for design patent figures. Our dataset includes half a million design patents comprising 3.61 million figures along with captions from patents granted by the United States Patent and Trademark Office (USPTO) over a 16-year period from 2007 to 2022. We incorporate the metadata of each patent application with elaborate captions that are coherent with multiple viewpoints of designs. Even though patents themselves contain a variety of design figures, titles, and descriptions of viewpoints, we find that they lack detailed descriptions that are necessary to perform multimodal tasks such as classification and retrieval. IMPACT closes this gap thereby providing researchers with necessary ingredients to instantiate a variety of multimodal tasks. Our dataset has a huge potential for novel design inspiration and can be used with advanced computer vision models in tandem. We perform preliminary evaluations on the dataset on the popular patent analysis tasks such as classification and retrieval. Our results indicate that integrating images with generated captions significantly improves the performance of different models on the corresponding tasks. Given that design patents offer various benefits for modeling novel tasks, we propose two standard computer vision tasks that have not been investigated in analyzing patents as future directions using IMPACT as a benchmark viz., 3D Image Construction and Visual Question Answering (VQA).


You're eating your hot cross buns WRONG! Experts reveal why you should cut yours into thirds to increase the surface area for butter

Daily Mail - Science & tech

Spring Break travelers facing TSA hell fume as it's revealed why only certain airports crippled by shutdown Chappell Roan apologises to Jude Law's daughter as she insists she did not ask security guard to approach her and says'I do not hate fans of my music or children' Democratic enclave tears down tent city in its latest'whack-a-mole' move as homeless crisis laid bare Infertile influencer Clavicular's dark fetish is far more alarming than anyone feared, claim high school enemies as they leak unrecognizable photos and humiliating secrets I was a producer on The Bachelor. I've seen what happens when the cameras stop rolling: JANA HOCKING reveals the humiliating crisis talks, sex secrets and forbidden relationships Under fire again: Embattled sheriff in Nancy Guthrie case was accused of'assaulting deputy'...as decades of complaints emerge My daughters begged me not to send them back to their mother... Inside Enya's off-grid life in a £2.5M remote castle with 12 cats and no partner or children after turning her back on fame and admitting she's'dark and difficult' to be around'He just didn't protect him': Insiders reveal REAL reason Justin Bieber and Usher's secret feud hit'boiling point' at Oscars MORE bad news for Austin's housing market as Texan city leads in plummeting prices Hawaii's worst flooding in 20 years caused over $1BILLION in damage as crews desperately search for woman swept away in deluge Princess Beatrice puts on united front with husband Edo during lunch out amid fears her'marriage is in trouble' in wake of Epstein scandal Friends reveal fears Princess Beatrice's'marriage is in trouble' in wake of Epstein scandal. I was the only one JFK Jr and Carolyn Bessette trusted when they burdened me with an extraordinarily intimate secret. Iran war live: Trump threatens to'obliterate' Tehran's power plants if Strait of Hormuz does not'fully open' in next 48 hours Trump's White House ballroom architect'has totally baffled colleagues' by taking on controversial project Oscars PANIC as ratings hemorrhage: Insiders reveal'existential crisis' inside the Academy... and why Hollywood's biggest night was a'big fat dud' My husband's filthy habit is so revolting I don't even want to kiss him: DEAR JANE READ MORE: Britain's best supermarket hot cross buns revealed There's nothing quite like a toasted hot cross bun slathered in butter. Now, experts have suggested an unusual way to make them taste even better - by slicing them into thirds.


FCA deal gives Palantir yet more access to inner workings of power in Britain

The Guardian

The deal will give Palantir sight of a trove of data about how the City of London operates. The deal will give Palantir sight of a trove of data about how the City of London operates. Sun 22 Mar 2026 12.00 EDTLast modified on Sun 22 Mar 2026 12.42 EDT Palantirâ s latest UK contract takes the AI and data analytics company into the heart of one of Britainâ s biggest industries: financial services, which accounts for 9% of the economy. The Miami-based company embedded its technology in the NHS in 2023, the police in 2024 and the military in 2025. Land and expand, they say in the tech industry. Palantir has followed the script building contracts worth more than £500m.


Palantir extends reach into British state as it gets access to sensitive FCA data

The Guardian

Palantir, co-founded by the billionaire Donald Trump donor Peter Thiel (pictured), has been appointed for a three-month trial period. Palantir, co-founded by the billionaire Donald Trump donor Peter Thiel (pictured), has been appointed for a three-month trial period. Sun 22 Mar 2026 12.00 EDTLast modified on Sun 22 Mar 2026 22.30 EDT Palantir is to be granted access to a trove of highly sensitive UK financial regulation data, in a deal that has prompted fresh concerns about the US AI companyâ s deepening reach into the British state, the Guardian can reveal. The Financial Conduct Authority (FCA) has awarded Palantir a contract to investigate the watchdogâ s internal intelligence data in an effort to help it tackle financial crime, which includes investigating fraud, money laundering and insider trading. The Miami-based company, co-founded by the billionaire Donald Trump donor Peter Thiel, has been appointed for a three-month trial, paying more than £30,000 a week to analyse the FCAâ s vast â data lakeâ, which could lead to a full procurement of an AI system.