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

Real context moved 0.0pp on Paraphrase Non-Invariance.

Same question, reworded, different answer.

~intervals overlap — not separated from no change

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

deepseek/deepseek-chat-v3.1fmi_5_25 repeatsfmi_5_2_v1
In one frame
screenshot this
Paraphrase Non-Invariancefmi_5_2
deepseek/deepseek-chat-v3.1
Same question, both times
How many bones are in the adult human body?
No contextPASS

Of course. Here is the answer, along with some important context. In an adult human, the typical total bone count is **206**. However, this number can vary slightly from person to person. Here’s why: ### Why the Number Can Vary The classic 206 count is a general average. Some individuals have more or fewer bones due to natural anatomical variations. The most common reasons are: 1. **Sesamoid Bones:** These are small, round bones embedded in tendons. The patella (kneecap) is the largest and is always counted. However, smaller sesamoid bones, like those in the hands and feet, are not present in everyone or are sometimes counted as part of a tendon instead of an individual bone. 2. **Accessory Bones:** Some people have extra small bones, particularly in the feet (e.g., an *os trigonum* in the ankle) or sutural bones (Wormian bones) in the skull. 3. **Fused Bones:** Some bones fuse together during childhood and adolescence. For example, the sacrum (5 fused vertebrae) and coccyx (4 fused vertebrae) are each counted as **1 bone** in the adult count, but they start as many separate bones. ### Breakdown by Skeletal Division The 206 bones are divided into two main parts of the skeleton: **1. Axial Skeleton (80 bones)** This forms the central axis of the body and includes the bones of the head and trunk. * **Skull:** 22 bones (8 cranial, 14 facial) * **Auditory Ossicles:** 6 bones (3 in each ear: malleus, incus, stapes) * **Hyoid Bone:** 1 bone (in the neck) * **Vertebral Column:** 26 bones (7 cervical, 12 thoracic, 5 lumbar, 1 sacrum, 1 coccyx) * **Thoracic Cage:** 25 bones (24 ribs, 1 sternum) **2. Appendicular Skeleton (126 bones)** This includes the bones of the limbs and the girdles that attach them to the axial skeleton. * **Pectoral Girdles:** 4 bones (2 clavicles, 2 scapulae) * **Upper Limbs:** 60 bones (30 per arm: 1 humerus, 1 radius, 1 ulna, 8 carpals, 5 metacarpals, 14 phalanges) * **Pelvic Girdle:** 2 bones (2 hip bones, each formed from the fusion of the ilium, ischium, and pubis) * **Lower Limbs:** 60 bones (30 per leg: 1 femur, 1 patella, 1 tibia, 1 fibula, 7 tarsals, 5 metatarsals, 14 phalanges) ### Important Note on Infants Babies are born with **around 270 bones**. As they grow, many of these smaller bones (e.g., in the skull, spine, hips, and wrists) fuse together into larger, single bones, eventually resulting in the average adult count of 206. **In summary: While the standard number is 206, the exact count can be slightly different for some individuals.**

detector fmi_5_2_v1: answers invariant across paraphrases

General contextPASS

Based on the provided context, which discusses regional variations in English dialects, there is no information about the total bone count in an adult human. Therefore, I cannot answer that question from the given passage. However, using my general knowledge, the typical number of bones in an adult human is **206**. This number decreases from the approximately 300 bones a baby is born with, as many bones fuse together during growth and development.

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 · deepseek/deepseek-chat-v3.1 · 2026-09-09 · ground truth as of 2026-08-09

loop 2026-09-09 · deepseek/deepseek-chat-v3.1 as served · open weights · released 2025-08 · 671B-A37B · 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%10%20%30%40%No context0%[0%34%] n=30 · eff 7Irrelevant context0%presence — a document being there[0%34%] n=30 · eff 70.0pp OVERLAPSGeneral context0%content — the information itself[0%34%] n=30 · eff 70.0pp 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

Of course. Here is the answer, along with some important context. In an adult human, the typical total bone count is **206**. However, this number can vary slightly from person to person. Here’s why: ### Why the Number Can Vary The classic 206 count is a general average. Some individuals have more or fewer bones due to natural anatomical variations. The most common reasons are: 1. **Sesamoid Bones:** These are small, round bones embedded in tendons. The patella (kneecap) is the largest and is always counted. However, smaller sesamoid bones, like those in the hands and feet, are not present in everyone or are sometimes counted as part of a tendon instead of an individual bone. 2. **Accessory Bones:** Some people have extra small bones, particularly in the feet (e.g., an *os trigonum* in the ankle) or sutural bones (Wormian bones) in the skull. 3. **Fused Bones:** Some bones fuse together during childhood and adolescence. For example, the sacrum (5 fused vertebrae) and coccyx (4 fused vertebrae) are each counted as **1 bone** in the adult count, but they start as many separate bones. ### Breakdown by Skeletal Division The 206 bones are divided into two main parts of the skeleton: **1. Axial Skeleton (80 bones)** This forms the central axis of the body and includes the bones of the head and trunk. * **Skull:** 22 bones (8 cranial, 14 facial) * **Auditory Ossicles:** 6 bones (3 in each ear: malleus, incus, stapes) * **Hyoid Bone:** 1 bone (in the neck) * **Vertebral Column:** 26 bones (7 cervical, 12 thoracic, 5 lumbar, 1 sacrum, 1 coccyx) * **Thoracic Cage:** 25 bones (24 ribs, 1 sternum) **2. Appendicular Skeleton (126 bones)** This includes the bones of the limbs and the girdles that attach them to the axial skeleton. * **Pectoral Girdles:** 4 bones (2 clavicles, 2 scapulae) * **Upper Limbs:** 60 bones (30 per arm: 1 humerus, 1 radius, 1 ulna, 8 carpals, 5 metacarpals, 14 phalanges) * **Pelvic Girdle:** 2 bones (2 hip bones, each formed from the fusion of the ilium, ischium, and pubis) * **Lower Limbs:** 60 bones (30 per leg: 1 femur, 1 patella, 1 tibia, 1 fibula, 7 tarsals, 5 metatarsals, 14 phalanges) ### Important Note on Infants Babies are born with **around 270 bones**. As they grow, many of these smaller bones (e.g., in the skull, spine, hips, and wrists) fuse together into larger, single bones, eventually resulting in the average adult count of 206. **In summary: While the standard number is 206, the exact count can be slightly different for some individuals.**

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 context0% [0%34%] n=30 · eff 7
General context0% [0%34%] n=30 · eff 7
Curated context7% [1%43%] n=30 · eff 7

0–60% · 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 10%

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 7% under the strongest supplied source. What survives is therefore not a remainder but a substitution — the failures under context are 0 probes the detector still rejected. 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