Evidence

Compare two experiments

Check what changed in the question, wording or readers before comparing the numbers.

This view keeps both results separate. It does not calculate a combined score or decide whether they reproduce each other.

Change the selected experimentsSearch by proposal, select a result or enter an exact identifier

Find experiments by proposal

Choose two experiments by title, measurement and date. The choices include up to 50 newest public completed results, plus your current selections. Historical results stay labelled. For older records, use the evidence explorer or exact entry below.

Use an exact experiment identifier instead

A full attempt UUID entered here replaces the corresponding choice above. Content hashes are not result identifiers.

Clear comparison

Compare the essentials

Read each question across both results. A matching description is not proof that the studies are scientifically comparable.

Question	First result	Second result
Which proposal?	wit(class) and pred(class) — witness and settle axes2026-08-03 03:30 UTC	wit(class) and pred(class) — witness and settle axes2026-08-11 12:27 UTC
What was measured?	robustness under corruptionHow does the construct change task accuracy under the declared corruption process?	robustness under corruptionHow does the construct change task accuracy under the declared corruption process?
What was the result?	-0.108 percentage pointsReported interval: -0.192 to -0.024Not yet counting in evidence decisions	0 percentage pointsCounts in current evidence decisions
Compared with what?	English comparison not recorded as a structured labelReader exposure not recorded as a structured label	English comparison not recorded as a structured labelReader exposure not recorded as a structured label
Independently settled?	DisputedEligible replications disagree and this original does not hold a settlement majority.	Disagrees with the named originalThis eligible row adds one disagreement. An adverse or null direction is a valid result and remains visible.

Inspect first result Inspect second result

What differs in the declared methods?

These are literal recorded values, not a compatibility test. Matching declarations do not prove equivalent inputs or fair scoring. A missing structured field may be described elsewhere in the immutable specification.

What was measured · Same recorded value

First result

robustness_delta

Second result

robustness_delta

English comparison declarations · Not recorded on either side

First result

Not recorded in this structured field

Second result

Not recorded in this structured field

Tested population · Not recorded on either side

First result

Not recorded in this structured field

Second result

Not recorded in this structured field

Unit tested · Not recorded on either side

First result

Not recorded in this structured field

Second result

Not recorded in this structured field

Named instruments (including order) · Recorded values differ

First result

[
    "qwen3.6:27b",
    "gemma4:31b-it-q4_K_M"
]

Second result

[
    "qwen25-7b@q4_k_m"
]

Reader exposure · Not recorded on either side

First result

Not recorded in this structured field

Second result

Not recorded in this structured field

Exposure window · Not recorded on either side

First result

Not recorded in this structured field

Second result

Not recorded in this structured field

How results combine · Not recorded on either side

First result

Not recorded in this structured field

Second result

Not recorded in this structured field

Scoring declaration · Not recorded on either side

First result

Not recorded in this structured field

Second result

Not recorded in this structured field

Conditions (including order) · Not recorded on either side

First result

Not recorded in this structured field

Second result

Not recorded in this structured field

First result: full recordrobustness under corruption · -0.108 percentage points

First result · 2026-08-03 03:30 UTC

wit(class) and pred(class) — witness and settle axes

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

What was measured: robustness under corruption · robustness_delta
How does the construct change task accuracy under the declared corruption process?
Reported result: -0.108 percentage points
Reported interval: -0.192 to -0.024.
The value falls on the registered harmful side of this metric’s neutral point.
English comparison: English comparison not recorded as a structured label
Declared by the submitter; not a certification of equivalent information.
Reader exposure: Reader exposure not recorded as a structured label
Named instruments: qwen3.6:27b, gemma4:31b-it-q4_K_M
Reader population not separately declared.
Conditions covered: No condition-by-condition settlement contract recorded
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: Disputed
Eligible replications disagree and this original does not hold a settlement majority.

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.

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

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

Not recorded

Reader or tokenizer results

[
    {
        "model": "gemma4:31b-it-q4_K_M",
        "value": -0.1000000000000000055511151231257827021181583404541015625
    },
    {
        "model": "qwen3.6:27b",
        "value": -0.11700000000000000677236045021345489658415317535400390625
    }
]

Condition results

Not recorded

Exact result and immutable specification Experiment history

Attempt f131cd65-961a-11f1-9e5e-04e365516815
Content c2a6decea7dc1537e36564cc62508048147a7eb01945c64dcd7c7804cc9b0a04

Second result: full recordrobustness under corruption · 0 percentage points

Second result · 2026-08-11 12:27 UTC

wit(class) and pred(class) — witness and settle axes

Counts in current evidence decisions. This row currently contributes to evidence decisions. Its direction is separate from whether the proposal is ready for adoption.

What was measured: robustness under corruption · robustness_delta
How does the construct change task accuracy under the declared corruption process?
Reported result: 0 percentage points
The value is neutral or does not resolve the registered direction.
English comparison: English comparison not recorded as a structured label
Declared by the submitter; not a certification of equivalent information.
Reader exposure: Reader exposure not recorded as a structured label
Named instruments: qwen25-7b@q4_k_m
Reader population not separately declared.
Conditions covered: No condition-by-condition settlement contract recorded
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: Disagrees with the named original
This eligible row adds one disagreement. An adverse or null direction is a valid result and remains visible.

This result checks a named original, not every experiment on the proposal. Read its target original

Compare with the exact target attempt

How much input text was reused?

Complete-pair freshness is not available for this receipt.

Separate-arm overlap is unavailable or has not been computed. This does not mean zero reuse.

Exact text comparisons only; repeated occurrences count separately. Shared text can deserve scrutiny even when each complete pair is new. These arm counts are descriptive and do not change settlement eligibility.

Declared target content identity

c2a6decea7dc1537e36564cc62508048147a7eb01945c64dcd7c7804cc9b0a04

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: c66e5f41b4e7db30765681987de885e5d0ccc56ae01fa85ec5cc5db28567e5a6

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

Not recorded

Reader or tokenizer results

[
    {
        "model": "qwen25-7b",
        "value": 3.3300000000000000710542735760100185871124267578125,
        "precision": "q4_k_m"
    }
]

Condition results

Not recorded

Exact result and immutable specification Experiment history

Attempt f1326ad0-961a-11f1-9e5e-04e365516815
Content 4a7e4d84d9e8723e0e2d75b54bcb4c693b913cdf131773f3293351b0bd84635b

Different wording, readers, exposure or populations can legitimately produce different results. A visible reference is not training the model’s weights. Current models and tokenizers have learned English; future Ainglish-trained performance remains a research question.