How BriefPulse Science works
Findings, methods and limits explained with the evidence in view.
Who it is for
Curious readers who want to understand what a result shows and how strong it is.
Where the stories come from
- Each publication follows a fixed list of public feeds and APIs, listed below. Nothing is scraped from behind a paywall.
- A story is written from the text stored for it, and every article links the exact pages used.
- Numbers and identifiers in the text must appear in that stored text before publication; anything that cannot be traced is removed rather than guessed.
- Reporting and interpretation are separated: reported statements are listed with the page that states them, and our own reading is labelled as ours.
- Where the reporting was silent, the text says so instead of filling the gap.
What this publication avoids
- Unsourced claims, invented numbers, and headlines the reporting cannot carry.
Corrections and withdrawals
- When source material changes, the story is revised and the change is recorded on the article.
- If a story cannot be supported, it is withdrawn: the address stays live with an explanation instead of disappearing.
- To ask for a correction, reply to the source list on the story.
Sources followed
These are the publishers and public bodies this desk actually collects from, with the interval each one is checked. A source appears here once it has completed a collection; a feed that stops working is removed until it is fixed. Reference pages the desk checks by hand are listed separately.
News reporting
- Phys.orgchecked every 180 minutes
- ScienceDailychecked every 180 minutes
Primary and public sources
- NASA newschecked every 60 minutes · 1 items routed
- MIT research newschecked every 60 minutes · 1 items routed
Other sources
- arXiv API: LLM evaluation paperschecked every 180 minutes
- arXiv cs.AIchecked every 180 minutes
- Hugging Face daily paperschecked every 180 minutes
- Google AI blogchecked every 30 minutes
- Hugging Face blogchecked every 60 minutes
Checked by hand, not monitored
- NASA Jet Propulsion Laboratory
Editorial depth
A finding must distinguish the measured result from the authors' interpretation, identify the sample or comparison, and name the main limit before publication.
Recurring coverage
- What the study measured
- Methods and limits
- Replication, correction and retraction watch
- Research result in context
Source priority
- The paper, preprint or dataset before a press release
- Methods, sample and uncertainty over a dramatic headline
- Independent replication or expert context when available