Compare two experiments

First result · 2026-08-31 16:20 UTC

test-run(<T>) / test-passed(<T>) — did “tested” mean the check happened, or that it succeeded?

Not yet counting in evidence decisions. This row remains available for assessment, but does not currently carry a counting evidence result.

What was measured

comprehension accuracy · comprehension_accuracy_delta
How does the wording change correct answers from the declared reader panel?

Reported result

-9.02 percentage points
Reported interval: -18.254 to -2.

The value falls on the registered harmful side of this metric’s neutral point.

English comparison

Complete, careful English

Declared by the submitter; not a certification of equivalent information.

The shortest careful-English statement of the full declared mapping: for test-run, execution asserted with the outcome expressly unreported; for test-passed, execution plus every declared acceptance criterion met. The marked arm varies only the marker form.

Reader exposure

Reader exposure not recorded as a structured label

Named instruments

deepseek/deepseek-v4-flash@provider-served

Reader population not separately declared.

Conditions covered

Separate outcomes retained for all 2 declared conditions

marker:test-run, marker:test-passed

An overall average can hide a weak condition. A condition list is not proof that every form or claim in the proposal was tested.

Settlement role

Awaiting independent settlement

An original reports one result. It does not confirm itself.

How often did each version lead to the right answer?

English comparison: 100.00%; 100.00%
Ainglish version: 90.98%; 90.98%

Reported real-item accuracy, not the separate calibration score. Both bars use the same 0–100% scale. The difference is measured in percentage points, not percent improvement. Any declared stratum weights are already applied.

Reported item-bootstrap interval: -18.254 to -2 percentage points.

This interval concerns the difference, not separate uncertainty bounds for either accuracy. It does not measure uncertainty across humans or future models.

At least one declared condition is resolution-limited. The overall interval does not settle every condition.

Real cases: 96 · Named readers: 1. These are different units; multiple answers to one case are not new cases.

Does the overall result hide differences between conditions?

Every stored condition, without new pooling. Differences and intervals use percentage points. Condition names come from the frozen experiment.
Condition	Reported difference	Reported interval	English accuracy	Ainglish accuracy
`marker:test-run`	-5	Not recorded	100.00%	95.00%
`marker:test-passed`	-13.04	Not recorded	100.00%	86.96%

A missing condition interval is not zero uncertainty. An overall interval cannot substitute for agreement in every load-bearing condition.

Inspect actual inputs and recorded answers

The comparison label is the submitter’s declaration, not a semantic certification. Check that both versions preserve the information needed to answer the same question.

Numbers count only readable inputs attached to this receipt. They are not the experiment’s declared sample size or the number of reader calls.

An external input location was declared, but it is not a safe HTTPS link this view can display. Inspect the retained specification; the missing link does not establish that there were no inputs.

No readable study input pairs are stored inline in this receipt. This does not mean the experiment used none.

Recorded input digest: 99487bdee8f3c54f4e8c5244702d1e5abb6e519b5e7dd916476fdac1874df424

Prompts, reference material and other context can live elsewhere in the specification. Inputs and keys alone do not reconstruct every reader call or establish a fair comparison.

Declared population, method and retained outcomes

No structured study scope is declared here. Inspect the immutable manifest; do not infer a comparator or population from the headline.

Absolute arm results, reader-specific results and condition results below are retained values, not a newly pooled analysis. Accuracy arms use fractions from 0 to 1; their difference uses percentage points.

Absolute arm results

{
    "english": 1,
    "ainglish": 0.90980000000000005311306949806748889386653900146484375,
    "chance": 0.333299999999999985167420391007908619940280914306640625
}

Reader or tokenizer results

[
    {
        "model": "deepseek\/deepseek-v4-flash",
        "value": -9.019999999999999573674358543939888477325439453125,
        "precision": "provider-served"
    }
]

Condition results

[
    {
        "id": "marker:test-run",
        "weight": 1,
        "share": 0.5,
        "value": -5,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 1,
            "ainglish": 0.9499999999999999555910790149937383830547332763671875,
            "chance": 0.333299999999999985167420391007908619940280914306640625
        },
        "resolution_bound": "ceiling"
    },
    {
        "id": "marker:test-passed",
        "weight": 1,
        "share": 0.5,
        "value": -13.03999999999999914734871708787977695465087890625,
        "value_lo": null,
        "value_hi": null,
        "arms": {
            "english": 1,
            "ainglish": 0.86960000000000003961275751862558536231517791748046875,
            "chance": 0.333299999999999985167420391007908619940280914306640625
        },
        "resolution_bound": "resolvable"
    }
]

Exact result and immutable specification Experiment history

Attempt 3c6abb28-e3f3-44a9-a102-4543997dd6ca
Content 6739df5eae40670f667fec50eee4f2c508e8ed1ab824d520c5168e8f7f2d3254