Topic
transparency
Commodities Standardised pack sizes for edible oils to enhance transparency, says Gokul Agro
The Department of Consumer Affairs has notified nine standard pack sizes for edible oils under the Legal Metrology framework, with a three-month transition period. Gokul Agro Resources Ltd welcomes the reform as a consumer-first move that enhances transparency and simplifies price comparison. The company also reported its strongest-ever financial performance in fiscal 2025-26, with revenue crossing ₹24,000 crore and profit after tax up 50% year-on-year.
UK Employers Must Publish Salary Information in Job Ads Under New Government Plans
The UK Cabinet Office has proposed requiring employers to publish salary information in job adverts, aiming to improve transparency and reduce pay discrimination. The exact details—whether exact salary, range, or benchmark rate—will be determined after a consultation ending in October. The rules would apply in England, Wales, and Scotland, with Northern Ireland's stance pending.
DOGE Used AI for Housing Policy Decisions at HUD, FOIA Denials Raise Transparency Concerns
Members of the Department of Government Efficiency (DOGE) deployed artificial intelligence at the Department of Housing and Urban Development (HUD) to inform policy decisions, according to documents obtained by Democracy Forward. The agency has denied Freedom of Information Act requests for details on the AI tools, citing a previously nonexistent 'AI privilege' and presidential communications privilege. Experts say the lack of transparency raises concerns about bias, hallucinations, and accountability in government AI use.
Supply Chain Supply Chains Become Truth Chains as EU Mandates Digital Product Passports and Verifiable Data
The European Union's new regulatory regime, including the Carbon Border Adjustment Mechanism and digital product passports, requires importers to provide verifiable information about product origin, composition, and carbon footprint. According to Splash247, supply chains must now demonstrate reliable connections between physical goods and their digital identities, with implications extending beyond Europe to global exporters and logistics providers.
Finance Health Insurance Claims Satisfaction Drops as Unexplained Rejections Rise, Report Finds
According to Policybazaar's 'Is India Happy with Health Insurance Claims? 2.0' report, satisfaction with health insurance claims is moderate at 82.8 out of 100, but a sharp rise in unexplained claim rejections and reliance on reimbursement are eroding consumer trust. 73% of dissatisfied claimants say they were not given a clear reason for rejection, up from 53% in 2023. The report calls on insurers to shift underwriting to onboarding and eliminate vague denial terms.
How Transparent Is DiffusionGemma? New Research Quantifies Reasoning Transparency Gap
A new paper decomposes LLM transparency into variable and algorithmic components. It finds DiffusionGemma's naive opaque serial depth is 28.6X higher than Gemma 4, but a token bottleneck reduces it to 1.1X. Algorithmic transparency remains harder due to non-chronological reasoning and token smearing, yet monitorability is similar.
New Survey Maps How Evidence Tracing and Execution Provenance Can Make LLM Agents Trustworthy
A new survey from arXiv explores evidence tracing and execution provenance as key mechanisms for ensuring trustworthiness in LLM-based agents. The paper defines a unified framework connecting retrieval grounding, tool-use safety, memory lineage, and failure diagnosis, and reviews benchmarks and open challenges.
Explainable deep learning improves human mental models of self-driving cars, study finds
A new method called Concept-Wrapper Network (CW-Net) provides faithful explanations of deep neural network planners in self-driving cars, improving human drivers' ability to anticipate vehicle behavior, especially in surprising situations. Deployed on a real autonomous vehicle, the system shows that explainable AI can be practical and useful in real-world settings.
Algorithm Audit Reveals LLM Hotel Recommendations Biased by Eco-Labels, Ignore Management Responses
A pre-specified algorithm audit of 12 large language models (LLMs) found that guest rating and price dominate hotel recommendations, while eco-certification is overweighted and management response is ignored. List position—a content-free artifact—also causally shifts recommendations, worth about $12 per night. The study grounds generative engine optimization and the accountability of AI infomediaries.
New Auditing Framework Detects Synthetic Data Privacy Leaks Without Model Access
A new causal framework for auditing synthetic data detects privacy leaks by distinguishing true disclosures from phantom ones. It uses statistical hypothesis testing with holdout sets, requires no model access or canary insertion, and is orders of magnitude more efficient than shadow-model approaches.
Finance RBI Proposes Transparent Bulk Deposit Pricing Framework
The Reserve Bank of India (RBI) has proposed new rules to enhance transparency and flexibility in bulk deposit pricing. Banks will need to disclose interest rates upfront and consider withdrawal risks in pricing.