Commit and justify 2075-2078 threshold-relaxation treatment

[MaxGhenis]

Context

The transcript noted that otherwise cleaner standard results still had a caveat: 2075-2078 relied on a local/uncommitted threshold relaxation, apparently around a 5.0% rule. The same years later showed splice-like behavior in external review.

This needs a clear decision before the 75-year release is treated as audited.

Work

• Locate the threshold-relaxation code/config used for 2075-2078.
• Decide whether those years should be rerun under the committed standard or the relaxed standard should be committed/documented.
• Compare raw annual outputs for 2074-2079 under both treatments where feasible.
• Add metadata marking any approximate/relaxed calibration years.

Acceptance Criteria

• 2075-2078 are no longer dependent on an undocumented local rule.
• If relaxed calibration remains, it is visible in run manifests, docs, and release caveats.
• Adjacent-year discontinuity checks pass or block publication.

Related: #97, #103, #106.