Find a story

Search Spins

Search titles, summaries, and missing voices across published articles — press releases, announcements, and media coverage.

0 results for “post-hoc”

SPIN Processed News Frame: The Hype

When Do Corrective Features Help? An Agent for Corrective Feature Discovery on Black-Box Forecasters

Researchers introduce CRAFTER, a method to discover interpretable corrective features from forecast model residuals to improve black-box forecasting performance without fine-tuning the original model.

Spin 45% Claim Present in Source AI Risk Moderate
arXiv Machine Learning

Aug 7, 2026

SPIN Processed News Frame: The Hype

Interpreting Black-Box Large Language Models with Sentence-Level Energy Landscapes

Researchers propose a model-agnostic, post-hoc sentence-level attribution method for proprietary LLMs using an Energy-Based Model surrogate to quantify prompt influence without repeated API calls.

Spin 65% Claim Present in Source AI Risk Moderate
arXiv Artificial Intelligence

Aug 5, 2026

SPIN Processed News Frame: The Hype

BAP-SQL: Budget-Aware Observation Planning for Agentic Text-to-SQL

BAP-SQL is a new method for agentic text-to-SQL systems that dynamically manages observation budgets during query execution to improve success rates under tight token and computational constraints.

Spin 45% Claim Present in Source AI Risk Moderate
arXiv Artificial Intelligence

Aug 5, 2026

SPIN Processed News Frame: The Hype

Accuracy-Preserving Stability Regularization for Large-Scale Retail Demand Forecasting

A new stability regularization technique for retail demand forecasting models improves forecast path stability without materially degrading point accuracy, as demonstrated on M5 benchmark data.

Spin 40% Claim Present in Source AI Risk Moderate
arXiv Machine Learning

Jul 16, 2026

SPIN Processed News Frame: The Hype

Post-Generation Curation of Synthetic Images via Homogeneous-Heterogeneous Splitting

A new method called Homogeneous-Heterogeneous Splitting improves synthetic image utility by selecting subsets based on fidelity and diversity, without retraining generators, achieving real-data-level performance with up to 40% fewer samples.

Spin 65% Source-Supported AI Risk Moderate Needs Evidence
arXiv Machine Learning

Jul 8, 2026

SPIN Processed Press Release Frame: The Fog

Vistagen Announces Topline and Post-Hoc Data from PALISADE-4 Phase 3 Public Speaking Challenge Trial of Fasedienol for the Acute Treatment of Social Anxiety Disorder - Business Wire

Vistagen reported topline and post-hoc results from PALISADE-4, a Phase 3 clinical trial evaluating fasedienol for acute treatment of social anxiety disorder using a public speaking challenge paradigm.

Spin 75% Claim Present in Source AI Risk Moderate
Business Wire Financial Services via Google News

Published Jun 30, 2026 · Analyzed Jul 8, 2026