ModelCensusopen-source ai reliability harness
Failure Mode Index · fmi_5_2

Paraphrase Non-Invariance.

Robustness & Consistencyinstrumented · tier 2 · status: stable

Meaning-preserving paraphrases of the same question yield materially different answers.

The question that exposes it

'Capital of Australia?' vs 'Australia's capital city is ___?' — same answer both ways?

Probes: Whether meaning-preserving paraphrases yield the same answer.

Trap: One phrasing gets Canberra, another confidently gets Sydney.

Signature

A set of human-verified paraphrases (same answer key); failure = answers that disagree across the set beyond a tolerance.

Example

"What's the capital of Australia?" answered correctly, but "Australia's capital city is ___?" answered "Sydney."

Severity axes
prevalence
medium
harm
medium
stealth
medium
Engineering guidance · class 5
  • Test every production prompt in three or more paraphrases before shipping. You ship a phrasing, not an intent.
  • Version prompt text like code. A trailing space is a change.
  • Sample repeatedly at your production temperature and measure the spread, not just the modal answer.
  • Randomise option order anywhere the task is multiple-choice shaped.
Mitigations
  • paraphrase-augmented training
  • canonicalization
Measurement

One tab per model, newest first. Each card is that model against this mode under every condition on a single day. The mitigations above are the claim; the residual on each card is what actually survived the intervention.

fmi_5_2_v1 · 5 repeats · served 2026-09-10

loop 2026-09-10 · x-ai/grok-4.6 as served · closed weights · released 2026-01 · set s1.4-live · cases v1.7 · conditions v1.0 · ground truth as of 2026-08-09

ConditionFailure rate95% intervalnTrapAnswerable
No context
bare · The model alone, with no supplied context.
0%0%–34%n=30 · eff 70% (n=10)0% (n=20)
Irrelevant context
null · Length-matched irrelevant context. The control.
0%0%–34%n=30 · eff 70% (n=10)0% (n=20)
General context
recipe_a · Broad retrieval — the first passage the source returns, unreviewed.
0%0%–34%n=30 · eff 70% (n=10)0% (n=20)
Curated context
recipe_b · Hand-checked retrieval — the same passage plus the provenance chain behind it.
0%0%–34%n=30 · eff 70% (n=10)0% (n=20)
Presence effect · no context → irrelevant context
0.0pp

intervals overlap — not separated

What a document being there did, before any of its content. Should be small.

Content effect · irrelevant → best real context
0.0pp

intervals overlap — not separated

What the information itself did. This is the publishable claim.

Residual — what survives

Unchanged by context: 0% with none, 0% with the strongest supplied source. For a control mode that flat line is the result — it is what licenses reading movement elsewhere in this loop as grounding rather than as a document being present. Nothing survives at the best condition on the cases measured here.

Mitigations from the index — the claim
  • paraphrase-augmented training
  • canonicalization

replay this card →