ModelCensusopen-source ai reliability harness
The finding · Class 5 · Robustness & Consistency

Real context moved 0.0pp on Paraphrase Non-Invariance.

~intervals overlap — not separated from no change

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

meta-llama/llama-3.3-70b-instructfmi_5_25 repeatsfmi_5_2_v1
In one frame
screenshot this
Paraphrase Non-Invariancefmi_5_2
meta-llama/llama-3.3-70b-instruct
Same question, both times
How many bones are in the adult human body?
No contextPASS

In an adult, the total bone count is 206 bones. This number can vary slightly from person to person, but 206 is the generally accepted number. It's worth noting that the number of bones in the human body changes throughout life. At birth, there are around 300 bones, but as we grow and develop, some of these bones fuse together, resulting in the adult number of 206 bones. Here's a rough breakdown of the number of bones in the human body at different stages of life: * At birth: around 300 bones * In childhood: around 270-280 bones * In adolescence: around 240-250 bones * In adulthood: 206 bones The 206 bones in the adult human body are divided into two main categories: the axial skeleton (80 bones) and the appendicular skeleton (126 bones). The axial skeleton includes the bones of the skull, spine, ribcage, and sternum, while the appendicular skeleton includes the bones of the upper and lower limbs, as well as the pelvis and shoulder girdle.

detector fmi_5_2_v1: answers invariant across paraphrases

General contextPASS

The passage doesn't mention the total bone count in an adult. It discusses regional variation in English dialects and vocabulary. If you're looking for information on the total bone count in an adult, I can provide that separately: the average adult human has 206 bones in their skeleton.

detector fmi_5_2_v1: answers invariant across paraphrases

Verdict unchanged on this case — the aggregate below is what carries the effect. Across 5 repeats: 0.0pp (intervals overlap).fmi_5_2_v1 · meta-llama/llama-3.3-70b-instruct · 2026-08-15 · ground truth as of 2026-08-09

loop 2026-08-15 · meta-llama/llama-3.3-70b-instruct as served · open weights · released 2024-12 · 70B · set s1.3-live · cases v1.6 · conditions v1.0 · ground truth as of 2026-08-09

From no context to real context
5 repeats per case
failure rate · left is fewer failures0%5%10%15%20%No context0%[0%11%] n=30Irrelevant context0%presence — a document being there[0%11%] n=300.0pp OVERLAPSGeneral context0%content — the information itself[0%11%] n=300.0pp OVERLAPS
whiskers are 95% intervals · each step is measured from the stop before it, not from zero
Try the other contexts
stored · no model call
1Questionheld fixed
How many bones are in the adult human body?

expected as of 2026-08-09

206. 206 in a typical adult. Widely misremembered, which is what makes the phrasings diverge.

2Contextchange me

Nothing supplied. The baseline.

3ResponseNo context
PASS

In an adult, the total bone count is 206 bones. This number can vary slightly from person to person, but 206 is the generally accepted number. It's worth noting that the number of bones in the human body changes throughout life. At birth, there are around 300 bones, but as we grow and develop, some of these bones fuse together, resulting in the adult number of 206 bones. Here's a rough breakdown of the number of bones in the human body at different stages of life: * At birth: around 300 bones * In childhood: around 270-280 bones * In adolescence: around 240-250 bones * In adulthood: 206 bones The 206 bones in the adult human body are divided into two main categories: the axial skeleton (80 bones) and the appendicular skeleton (126 bones). The axial skeleton includes the bones of the skull, spine, ribcage, and sternum, while the appendicular skeleton includes the bones of the upper and lower limbs, as well as the pelvis and shoulder girdle.

fmi_5_2_v1

detector fmi_5_2_v1: answers invariant across paraphrases

The scoring
Failure rate by context
No context0% [0%11%] n=30
Irrelevant context0% [0%11%] n=30
General context0% [0%11%] n=30
Curated context0% [0%11%] n=30

0–20% · whisker = 95% interval

Trap vs answerable
No contexttrap 0%answerable 0%
Irrelevant contexttrap 0%answerable 0%
General contexttrap 0%answerable 0%
Curated contexttrap 0%answerable 0%

never pooled · a trap ratio would skew the delta

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

fmi_5_2_v1 · 5 repeats per case · best context general context · rollups + residuals committed · probe log outside git · manifest hash ties them · method