The finding · Class 3 · Instruction Adherence & Long-Context

Real context moved 10.0pp on Cross-Turn Schema Validity.

Breaks the JSON shape partway through a conversation.

~intervals overlap — not separated from no change

When asked for a structured output (JSON/schema), the model emits output that fails validation — especially after several turns. The rule

meta-llama/llama-3.1-8b-instructfmi_3_35 repeatsfmi_3_3_v1

The mode All 10 cards

In one frame

screenshot this

Cross-Turn Schema Validityfmi_3_3

meta-llama/llama-3.1-8b-instruct

Same question, both times

Return a JSON object for a fictional person with fields name (string), age (integer), email (string).

No contextPASS

{ "name": "Jane Smith", "age": 25, "email": "jane.smith@example.com" }

detector fmi_3_3_v1: all turns produced schema-valid JSON

General contextPASS

``` { "name": "Jane Smith", "age": 25, "email": "jane.smith@example.com" } ```

detector fmi_3_3_v1: all turns produced schema-valid JSON

loop 2026-09-09 · meta-llama/llama-3.1-8b-instruct as served · open weights · released 2024-07 · 8B · 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

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

Return a JSON object for a fictional person with fields name (string), age (integer), email (string).

expected as of 2026-08-09

Schema-valid JSON on all 3 turns. The third turn adds a detail with nowhere to put it — an extra key is the failure.

2Contextchange me

Nothing supplied. The baseline.

3ResponseNo context

No exhibit stored for this context. The full probe log lives outside the repository.

The scoring

Failure rate by context

No context15% [2%–56%] n=20 · eff 6

Irrelevant context0% [0%–41%] n=20 · eff 6

General context10% [1%–51%] n=20 · eff 6

Curated context15% [2%–56%] n=20 · eff 6

0–80% · whisker = 95% interval

Trap vs answerable

No contexttrap 30%answerable 0%

Irrelevant contexttrap 0%answerable 0%

General contexttrap 20%answerable 0%

Curated contexttrap 30%answerable 0%

never pooled · a trap ratio would skew the delta

Residual — what survives

Unchanged by context: 15% with none, 10% with the strongest supplied source. For a control mode that flat line is the result — it is what licenses reading movement elsewhere in this loop as grounding rather than as a document being present.

Mitigations from the index — the claim

schema-constrained decoding
validate-and-repair loops

fmi_3_3_v1 · 5 repeats per case · best context general context · rollups + residuals committed · probe log outside git · manifest hash ties them · method