docs/perf: define and measure the 10x evidence gates

[dnncha]

What this changes

• defines auditable baselines and separate 10x gates for scientific accuracy, performance, scientific impact, and industry impact;
• adds make bench-10x-control, a deterministic indexed-Hamming control with a 256-read exhaustive-scan preflight and five-repeat CSV output;
• documents the performance-control protocol and how to record hardware, compiler, workload, repeat, checksum, and memory evidence;
• adds a public-safe independent-evaluation request that does not require sharing private sequences or inferring impact from downloads/open submissions.

Evidence status

This PR does not claim that any 10x target has been met. The existing native/public correctness gates pass. The local synthetic control is diagnostic only and must not be substituted for the repeated full Sanson/Brunello workflow lane. Scientific and industry impact remain at zero verified external records until independent evidence exists.

Validation

• make test
• make cli-test
• make docs-ready
• make build/bench_hamming_control
• control preflight compares indexed results with exhaustive scan and emits stable checksums

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 9f8e876817

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[chatgpt-codex-connector]

Derive the speed gate from the repeated baseline

When the required five-repeat baseline differs from the existing single-run measurement, these fixed thresholds are no longer a 10x comparison against that baseline: a candidate could pass while improving by less than 10x, or fail despite improving by more than 10x. This is especially problematic because the document requires capturing the repeated baseline before publishing the multiplier; define the gate as a candidate-to-baseline ratio using a specified repeat statistic, then derive any absolute thresholds from that frozen result.

Useful? React with 👍 / 👎.