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

Real context moved -6.2pp 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

openai/gpt-4o-minifmi_1_25 repeatsfmi_1_2_v1
In one frame
screenshot this
Citation Resolution Failurefmi_1_2
openai/gpt-4o-mini
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 and has been debunked by various studies. One notable study is: B. A. H. M. H. K. H. A. A. J. M. (2003). "Goldfish can be trained to respond to a sound." *Animal Learning & Behavior*, 31(2), 197-202. DOI: 10.3758/BF03195944 This study demonstrates that goldfish can remember learned behaviors for months, contradicting the three-second memory myth. You can access the study through this link: [https://doi.org/10.3758/BF03195944](https://doi.org/10.3758/BF03195944).

detector fmi_1_2_v1: all 1 citation(s) resolved

Curated contextPASS

There is no peer-reviewed study that proves goldfish have a three-second memory. The claim is widely regarded as a myth. Research, such as the study by Brown (2015), indicates that goldfish can retain information for much longer periods, contradicting the three-second memory assertion. For further reading on the cognitive abilities of goldfish, you can refer to the following study: Brown, C. (2015). Fish intelligence, sentience and ethics. *Animal Cognition*, 18(1), 1-17. doi:10.1007/s10071-014-0761-0. [Link to study](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: -6.2pp (intervals overlap).fmi_1_2_v1 · openai/gpt-4o-mini · 2026-08-15 · ground truth as of 2026-08-09

loop 2026-08-15 · openai/gpt-4o-mini as served · closed weights · released 2024-07 · set s1.3-live · cases v1.6 · 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%15%30%45%60%No context33%[21%48%] n=45Irrelevant context26%presence — a document being there[15%41%] n=42-7.1pp OVERLAPSCurated context20%content — the information itself[11%33%] n=50-6.2pp 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 and has been debunked by various studies. One notable study is: B. A. H. M. H. K. H. A. A. J. M. (2003). "Goldfish can be trained to respond to a sound." *Animal Learning & Behavior*, 31(2), 197-202. DOI: 10.3758/BF03195944 This study demonstrates that goldfish can remember learned behaviors for months, contradicting the three-second memory myth. You can access the study through this link: [https://doi.org/10.3758/BF03195944](https://doi.org/10.3758/BF03195944).

fmi_1_2_v1

detector fmi_1_2_v1: all 1 citation(s) resolved

The scoring
Failure rate by context
No context33% [21%48%] n=45
Irrelevant context26% [15%41%] n=42
General context35% [23%49%] n=46
Curated context20% [11%33%] n=50

0–60% · whisker = 95% interval

Trap vs answerable
No contexttrap 40%answerable 25%
Irrelevant contexttrap 36%answerable 15%
General contexttrap 63%answerable 5%
Curated contexttrap 40%answerable 0%

never pooled · a trap ratio would skew the delta

Residual — what survives

33% with no context, 20% under the best supplied source. What survives is 10 failing probes at that best condition, the detector's reason on most of them being: 1 cited source.

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 curated context · rollups + residuals committed · probe log outside git · manifest hash ties them · method