Evidence, Research, Decisions.
Explore how trustworthy data, sound research methods and careful decisions connect.
What we care about
Trustworthy evidence
Every number should be able to say where it came from and when it was known.
Explainable research
Methods and results that someone else can follow, check and repeat.
Careful decisions
Write down assumptions and counter-evidence before the outcome arrives, not after.
The family
Three independent projects, named after the parts of a water system.
Subjects
Short, sourced explanations — start anywhere.
Data Engineering
How data is collected, shaped, versioned and traced so that a number can be trusted.
Data Collection
Getting data from sources responsibly: access, limits, snapshots and the evidence you keep.
Statistics & Probability
Samples, distributions, intervals and error — the arithmetic of uncertainty.
Research & Validation
Hypotheses, baselines and backtests — and the ways validation quietly goes wrong.
Relevance
Matching, ranking and judging how well results fit what was asked.
Decision Science
Deciding under uncertainty, and keeping a record you can learn from.
Evidence Quality
Source credibility, levels of evidence, counter-evidence and reproducibility.
Media & Communication
Volume, attention, framing and tone: how coverage is counted, and how to read the counts.
E-commerce Data
Reading marketplace numbers — ranks, prices, ratings, listings — without mistaking them for something else.
Featured reading
When It Happened vs. When You Knew: Why Data Has Two Clocks
Every fact carries two times: when it happened and when you could have known it. Mixing them up is a quiet reason many historical results look better than they should.
- Data Lineage and Traceability: How to Tell Whether a Number Can Be Trusted
A number does not carry its own credibility. Three questions about where it came from, what was done to it and what depends on it let you judge it.
- Keyword Match vs. Semantic Relevance: How to Tell Whether a Ranking Is Good
Two ways to decide that a result fits a query, and a simple method for judging which ranking is better: measure it against people's judgments.