ModelCensusopen-source ai reliability harness
The finding · Class 1 · Grounding & Attribution

Real context moved -11.4pp on Citation Resolution Failure.

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: 61% bare against 65% with the best supplied source. What the source repaired is damage the presence of a document did.

~intervals overlap — not separated from no change

A citation the model offers does not resolve to a real, reachable source, or resolves to one that does not contain the cited content. The rule

meta-llama/llama-3.1-8b-instructfmi_1_25 repeatsfmi_1_2_v1
In one frame
screenshot this
Citation Resolution Failurefmi_1_2
meta-llama/llama-3.1-8b-instruct
Same question, both times
Cite the paper that introduced the transformer architecture, with its arXiv id.
No contextPASS

The paper that introduced the transformer architecture is: "Attention Is All You Need" by Vaswani et al. (2017) arXiv id: 1706.03762 Source: https://arxiv.org/abs/1706.03762

detector fmi_1_2_v1: all 1 citation(s) resolved

General contextPASS

The paper that introduced the transformer architecture is: "Attention Is All You Need" by Ashish Vaswani et al. The arXiv id is: 1907.03748 https://arxiv.org/abs/1907.03748

detector fmi_1_2_v1: all 1 citation(s) resolved

Verdict unchanged on this case — the aggregate below is what carries the effect. Across 5 repeats: -11.4pp (intervals overlap).fmi_1_2_v1 · meta-llama/llama-3.1-8b-instruct · 2026-08-15 · ground truth as of 2026-08-09

loop 2026-08-15 · meta-llama/llama-3.1-8b-instruct as served · open weights · released 2024-07 · 8B · set s1.2-live · cases v1.4 · 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 context61%[47%74%] n=49Irrelevant context76%presence — a document being there[63%86%] n=50+14.8pp OVERLAPSGeneral context65%content — the information itself[50%77%] n=48-11.4pp 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
Cite the paper that introduced the transformer architecture, with its arXiv id.

expected as of 2026-08-09

Attention Is All You Need, arXiv:1706.03762. A real, resolvable reference.

2Contextchange me

Nothing supplied. The baseline.

3ResponseNo context
PASS

The paper that introduced the transformer architecture is: "Attention Is All You Need" by Vaswani et al. (2017) arXiv id: 1706.03762 Source: https://arxiv.org/abs/1706.03762

fmi_1_2_v1

detector fmi_1_2_v1: all 1 citation(s) resolved

The scoring
Failure rate by context
No context61% [47%74%] n=49
Irrelevant context76% [63%86%] n=50
General context65% [50%77%] n=48
Curated context70% [56%81%] n=50

0–100% · whisker = 95% interval

Trap vs answerable
No contexttrap 88%answerable 36%
Irrelevant contexttrap 96%answerable 56%
General contexttrap 96%answerable 30%
Curated contexttrap 92%answerable 48%

never pooled · a trap ratio would skew the delta

Residual — what survives

Supplying context did not reduce this failure, it increased it: 61% with no context against 70% under the strongest supplied source. What survives is therefore not a remainder but a substitution — the failures under context are 31 probes the detector still rejected, dominated by: no citation offered.

Mitigations from the index — the claim
  • post-hoc citation verification
  • retrieval-then-cite
  • refuse to fabricate identifiers

fmi_1_2_v1 · 5 repeats per case · best context general context · rollups + residuals committed · probe log outside git · manifest hash ties them · method