PRISM v2.13.0 released — SP-16 The Elephant Rule (negation discipline)

[Ronkupper]

PRISM v2.13.0 is out, paired with Lens Library v0.14.

Releases:

• Framework: https://github.com/Ronkupper/PRISM/releases/tag/v2.13.0
• Lens Library: https://github.com/Ronkupper/PRISM/releases/tag/prism-lens-v0.14

What shipped. A new Standing Principle, SP-16 — The Elephant Rule (§10.1.7), after Lakoff's Don't Think of an Elephant!: negation is a targeting decision. A sentence may negate only a live alternative — a belief the reader demonstrably brings, or an inference the document's own numbers invite. Every other negation plants the accusation it denies: the reader leaves carrying the frame, the author reads as defensive, and the text implies a critic nobody heard from.

The test, run on every negation ("not Y", "X, not Y", "rather than Y", "no Y"): would a cold reader plausibly arrive believing Y, or derive Y from the document itself?

• Called-for (keep): "The limit is export permission, not customer demand." Both hypotheses are live; the contrast names the binding constraint.
• Uncalled-for (rewrite): a heading "Why it's a real market, not a hyped one" — nobody alleged hype — becomes "What anchors the $2.0 billion." The heading now asserts the anchor.

Where it's wired:

• Self-check step 5 — an output gate before any Output is emitted: enumerate every negation, tag each called-for (naming the live alternative) or uncalled-for (rewrite before release). Headings, titles, and opening sentences get the strictest scrutiny — they set frames the rest of the document inherits.
• LL-D-019 — "Who said otherwise?" — the audit-side twin in the Lens Library (Pack 1), for reviewing documents that already exist. Catalog 23 → 24.

Unchanged. No Monitor, Probe, or Gate semantics changed; lint catalog stays v4; the §2.2 ASCII map carries over untouched. Snapshots PRISM_v2_13_0.md and lens/PRISM_lens_library_v0_14.md are byte-identical to their canonical files at these tags.

Report-back. §16 calibration item 8 is open: on your next run, how many negations did step 5 tag, what fraction were false flags, and did LL-D-019 catch anything a human pass had already cleared? That signal decides whether the gate stays this strict.