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

Real context moved 30.0pp on Paraphrase Non-Invariance.

Same question, reworded, different answer.

Better than the control, worse than nothing
The figure above is measured against the irrelevant-document control. Against no context at all this card is worse: 0% bare against 50% with the best supplied source. What the source repaired is damage the presence of a document did.

~intervals overlap — not separated from no change

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

anthropic/claude-3-haikufmi_5_25 repeatsfmi_5_2_v1
In one frame
screenshot this
Paraphrase Non-Invariancefmi_5_2
anthropic/claude-3-haiku
Same question, both times
How many bones are in the adult human body?
No contextPASS

The total number of bones in an adult human body is typically 206. The breakdown of the bones in an adult human body is as follows: 1. Axial skeleton (80 bones): - Skull (22 bones) - Hyoid bone (1 bone) - Auditory ossicles (6 bones) - Rib cage (24 ribs) - Sternum (1 bone) - Auditory ossicles (6 bones) 2. Appendicular skeleton (126 bones): - Pectoral girdles (4 bones) - Upper limbs (60 bones) - Pelvic girdle (2 bones) - Lower limbs (60 bones) The number of bones can vary slightly due to individual differences, such as the fusion of certain bones or the presence of additional bones in some people. It's important to note that the number of bones can change throughout a person's life. In infants and young children, the number of bones is higher due to the presence of unfused bones that eventually fuse as the individual grows and develops.

detector fmi_5_2_v1: answers invariant across paraphrases

General contextPASS

The total bone count in an adult human body is approximately 206 bones. The human skeletal system is composed of 206 bones, which can be categorized into the following main groups: 1. Axial skeleton (80 bones): - Skull (22 bones) - Hyoid bone (1 bone) - Auditory ossicles (6 bones) - Rib cage (24 bones) - Sternum (1 bone) - Auditory ossicles (6 bones) 2. Appendicular skeleton (126 bones): - Pectoral girdles (4 bones) - Upper limbs (60 bones) - Pelvic girdle (2 bones) - Lower limbs (60 bones) The number of bones can vary slightly due to individual differences, such as the presence of additional bones or the fusion of certain bones during development and growth. It's important to note that the provided context about regional variations in English terminology for bread products is not directly relevant to the question about the total bone count in an adult human. The bone count information is a separate, general fact about human anatomy.

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: +30.0pp (intervals overlap).fmi_5_2_v1 · anthropic/claude-3-haiku · 2026-09-09 · ground truth as of 2026-08-09

loop 2026-09-09 · anthropic/claude-3-haiku as served · closed weights · released 2024-03 · set s1.4-live · cases v1.7 · 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%25%50%75%100%No context0%[0%34%] n=30 · eff 7Irrelevant context20%presence — a document being there[5%56%] n=30 · eff 7+20.0pp OVERLAPSGeneral context50%content — the information itself[21%79%] n=30 · eff 7+30.0pp 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

The total number of bones in an adult human body is typically 206. The breakdown of the bones in an adult human body is as follows: 1. Axial skeleton (80 bones): - Skull (22 bones) - Hyoid bone (1 bone) - Auditory ossicles (6 bones) - Rib cage (24 ribs) - Sternum (1 bone) - Auditory ossicles (6 bones) 2. Appendicular skeleton (126 bones): - Pectoral girdles (4 bones) - Upper limbs (60 bones) - Pelvic girdle (2 bones) - Lower limbs (60 bones) The number of bones can vary slightly due to individual differences, such as the fusion of certain bones or the presence of additional bones in some people. It's important to note that the number of bones can change throughout a person's life. In infants and young children, the number of bones is higher due to the presence of unfused bones that eventually fuse as the individual grows and develops.

fmi_5_2_v1

detector fmi_5_2_v1: answers invariant across paraphrases

The scoring
Failure rate by context
No context0% [0%34%] n=30 · eff 7
Irrelevant context20% [5%56%] n=30 · eff 7
General context50% [21%79%] n=30 · eff 7
Curated context63% [30%87%] n=30 · eff 7

0–100% · whisker = 95% interval

Trap vs answerable
No contexttrap 0%answerable 0%
Irrelevant contexttrap 50%answerable 5%
General contexttrap 50%answerable 50%
Curated contexttrap 90%answerable 50%

never pooled · a trap ratio would skew the delta

Residual — what survives

Supplying context did not reduce this failure, it increased it: 0% with no context against 63% under the strongest supplied source. What survives is therefore not a remainder but a substitution — the failures under context are 15 probes the detector still rejected, dominated by: answers differ across meaning-preserving paraphrases.

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