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

Real context moved 7.6pp on Citation Resolution Failure.

Cites a source that does not exist.

~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

anthropic/claude-3-haikufmi_1_25 repeatsfmi_1_2_v1
The modeAll 10 cards
In one frame
screenshot this
Citation Resolution Failurefmi_1_2
anthropic/claude-3-haiku
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., published on arXiv with the ID arXiv:1706.03762. Citation: Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. arXiv preprint arXiv: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 Vaswani et al., published at NeurIPS 2017 and available on arXiv with the identifier arXiv:1706.03762. Citation: Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. arXiv preprint arXiv:1706.03762.

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: +7.6pp (intervals overlap).fmi_1_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%20%40%60%80%No context39%[19%–64%] n=46 · eff 15Irrelevant context24%presence — a document being there[10%–50%] n=45 · eff 15-14.7pp OVERLAPSGeneral context32%content — the information itself[14%–57%] n=50 · eff 15+7.6pp 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., published on arXiv with the ID arXiv:1706.03762. Citation: Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. arXiv preprint arXiv:1706.03762.

fmi_1_2_v1

detector fmi_1_2_v1: all 1 citation(s) resolved

The scoring
Failure rate by context
No context39% [19%–64%] n=46 · eff 15
Irrelevant context24% [10%–50%] n=45 · eff 15
General context32% [14%–57%] n=50 · eff 15
Curated context33% [15%–58%] n=49 · eff 15

0–80% · whisker = 95% interval

Trap vs answerable
No contexttrap 82%answerable 0%
Irrelevant contexttrap 55%answerable 0%
General contexttrap 64%answerable 0%
Curated contexttrap 67%answerable 0%

never pooled · a trap ratio would skew the delta

Residual — what survives

39% with no context, 32% under the best supplied source. What survives is 16 failing probes at that best condition, the detector's reason on most of them being: 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