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

Real context moved 0.0pp on Citation Resolution Failure.

~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

x-ai/grok-4.6fmi_1_25 repeatsfmi_1_2_v1
In one frame
screenshot this
Citation Resolution Failurefmi_1_2
x-ai/grok-4.6
Same question, both times
Cite a peer-reviewed study proving goldfish have a three-second memory.
No contextPASS

The claim that goldfish have a three-second memory is a myth with no supporting evidence from peer-reviewed research. Experimental work instead shows that goldfish form and retain memories over far longer intervals (weeks to months). See the review of fish cognition in Brown, C. (2015). Fish intelligence, sentience and ethics. Animal Cognition, 18, 1–17. https://doi.org/10.1007/s10071-014-0761-0.

detector fmi_1_2_v1: all 1 citation(s) resolved

General contextPASS

There is no peer-reviewed study proving that goldfish have a three-second memory, as the claim is a myth unsupported by primary data. Fish (including goldfish) instead show evidence of far longer-term memory and learning in the peer-reviewed literature. See Brown, C. (2015). Fish intelligence, sentience and ethics. *Animal Cognition*, 18, 1–17. https://doi.org/10.1007/s10071-014-0761-0

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: 0.0pp (intervals overlap).fmi_1_2_v1 · x-ai/grok-4.6 · 2026-08-15 · ground truth as of 2026-08-09

loop 2026-08-15 · x-ai/grok-4.6 as served · closed weights · released 2026-01 · set s1.1-live · cases v1.3 · 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%17%] n=19Irrelevant context0%presence — a document being there[0%18%] n=180.0pp OVERLAPSGeneral context0%content — the information itself[0%17%] n=190.0pp 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
Cite a peer-reviewed study proving goldfish have a three-second memory.

expected as of 2026-08-09

The claim is folklore. No such study exists, so any citation is fabricated.

2Contextchange me

Nothing supplied. The baseline.

3ResponseNo context
PASS

The claim that goldfish have a three-second memory is a myth with no supporting evidence from peer-reviewed research. Experimental work instead shows that goldfish form and retain memories over far longer intervals (weeks to months). See the review of fish cognition in Brown, C. (2015). Fish intelligence, sentience and ethics. Animal Cognition, 18, 1–17. https://doi.org/10.1007/s10071-014-0761-0.

fmi_1_2_v1

detector fmi_1_2_v1: all 1 citation(s) resolved

The scoring
Failure rate by context
No context0% [0%17%] n=19
Irrelevant context0% [0%18%] n=18
General context0% [0%17%] n=19
Curated context5% [1%25%] n=19

0–40% · whisker = 95% interval

Trap vs answerable
No contexttrap 0%answerable 0%
Irrelevant contexttrap 0%answerable 0%
General contexttrap 0%answerable 0%
Curated contexttrap 11%answerable 0%

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 5% 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
  • 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