Work Research Notes Knowledge Base Search Contact

praxagent / Methods

Experiment integrity

Plan comparisons before inspecting results. Report all outcomes, document changes, and publish the supporting evidence.

01 / Why

Credibility is chronological

Confirmatory research goes wrong when the rules change after the data arrive: optional stopping, selective reporting, or hypothesizing after results are known. We cannot erase judgment. We can make the consequential choices visible and time-ordered.

A dated record lets readers check that the design preceded the outcomes, the run followed the design, and all outcomes were retained. Later analyses should be labeled by when they were added.

02 / Sequence

Freeze, run, audit, release

01 / Freeze

Lock the design before outcomes exist

The question, claim boundary, sample, controls, endpoints, and analysis are committed before any target outcome is generated or inspected.

02 / Run

Execute the plan as frozen

Keep the planned rules independent of the observed effect. Document defects and necessary changes in dated amendments.

03 / Audit

Bind the artifacts to the design

Runtime records are checked against the frozen plan, and every condition and failure path stays in the record.

04 / Release

Publish the supporting evidence

Code, prompts, data, and result records let readers inspect the evidence behind each claim.

03 / Labels

Say what the result is

These labels distinguish when the design was set and how the results can be interpreted:

Exploratory

Outcomes may still shape design

Useful for discovery and feasibility, and reported as exploratory rather than confirmatory evidence.

Frozen

The design predates the outcomes

The complete plan was committed before target outcomes existed. Later changes are dated amendments, not quiet edits.

Confirmatory

Everything reported was in the freeze

Endpoint, sample, controls, exclusions, and analysis all trace back to the frozen design.

Post-run

Added after the results were seen

Sensitivity analyses can be informative, but they are labeled by timing and never promoted to confirmatory status.

04 / In public

What you should see

01

Release the evidence.

Published code, prompts, data, and result records let readers check the evidence behind each claim.

02

Run the control.

Matched baselines and null tests determine what survives into the conclusion.

03

Report the failure.

Negative results and broken hypotheses remain part of the public record.

These are our research standards. Each research note should identify its study plan, supporting results, and any changes made after outcomes were inspected.

A worked example: detecting SAE steering

The steering study links a protocol committed before outcomes, a report with results and evidence, and a dated follow-up amendment. The follow-up failed its planned replay-equivalence test, so its endpoint results are reported as exploratory. Readers can trace that change in status instead of inferring it from the headline.

Research notes Back to How we work