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?	test-run(<T>) / test-passed(<T>) — did “tested” mean the check happened, or that it succeeded?2026-08-28 12:54 UTC	test-run(<T>) / test-passed(<T>) — did “tested” mean the check happened, or that it succeeded?2026-08-28 16:06 UTC
What was measured?	token costHow does the wording change tokenizer units for the declared tokenizer population?	token costHow does the wording change tokenizer units for the declared tokenizer population?
What was the result?	-6.9375 tokens per declared itemReported interval: -7 to -6.9375Counts in current evidence decisions	-6.875 tokens per declared itemReported interval: -6.9375 to -6.875Counts in current evidence decisions
Compared with what?	English comparison not recorded as a structured labelCurrent tokenizer cost, not comprehension	English comparison not recorded as a structured labelCurrent tokenizer cost, not comprehension
Independently settled?	Confirmed by eligible settlementEligible fresh-input replications currently give this original a settlement majority.	Agrees with the named originalThis eligible row adds one agreement to the named original’s settlement tally.

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

token_delta

Second result

token_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) · Same recorded value

First result

[
    "tiktoken/cl100k_base",
    "tiktoken/o200k_base"
]

Second result

[
    "tiktoken/cl100k_base",
    "tiktoken/o200k_base"
]

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 recordtoken cost · -6.9375 tokens per declared item

First result · 2026-08-28 12:54 UTC

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

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: token cost · token_delta
How does the wording change tokenizer units for the declared tokenizer population?
Reported result: -6.9375 tokens per declared item
Reported interval: -7 to -6.9375.
Fewer tokens on the named current tokenizers; this is the encoded-length difference, not the proposal decision.
English comparison: English comparison not recorded as a structured label
Declared by the submitter; not a certification of equivalent information.
Tokenizer conditions: Literal encoding cost on the named current tokenizers; not comprehension.
Named instruments: tiktoken/cl100k_base, tiktoken/o200k_base
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: Confirmed by eligible settlement
Eligible fresh-input replications currently give this original a settlement majority.

Is this result within the cost allowance?

This headline is within the allowance. The reported difference is -6.9375 tokens; the current declaration allows at most 0 tokens.

This compares Ainglish minus English with the current declaration, which may differ from the declaration when the result was filed. It checks the headline only: inspect any required per-form and per-tokenizer results too.

Has the original estimate been independently reproduced?

Confirmed by eligible settlement.

Eligible fresh-input replications currently give this original a settlement majority.

Reproduction asks whether fresh-input findings agree under the settlement rule. It does not ask whether either value satisfies the cost allowance.

Being within the cost allowance is not a completed prerequisite. Reproducing an original estimate is a separate check, not proof that the allowance is met. Current evidence status, settlement and every declared result still determine readiness.

How can one check pass while the other does not?

For example, an allowance of at most +3 tokens and an original estimate of +3 ask different questions. A replication of −0.5 is within that allowance but may disagree with the original. A replication of +3.25 may reproduce +3 within the settlement tolerance while exceeding the allowance.

These are illustrative numbers, not a new settlement rule. A cost saving is not a comprehension result, and a reproduced premium does not by itself mean a proposal should be adopted or rejected.

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.

Showing 1–6 of 32 readable, inline study items, in stored order—not a selection of successes. 0 control items are kept separate.

Each result has its own input pages. Positions across the two studies do not imply matched cases.

Input 1

English input: Test execution restore-v4@run-817 occurred on backup B17; its outcome is not asserted.
Ainglish input: backup B17, test-run(restore-v4@run-817).

Input 2

English input: Test execution smoke-linux@run-114 occurred on release 4.2; its outcome is not asserted.
Ainglish input: release 4.2, test-run(smoke-linux@run-114).

Input 3

English input: Test execution schema-audit@run-52 occurred on dataset Q9; its outcome is not asserted.
Ainglish input: dataset Q9, test-run(schema-audit@run-52).

Input 4

English input: Test execution bias-panel@run-31 occurred on model M7; its outcome is not asserted.
Ainglish input: model M7, test-run(bias-panel@run-31).

Input 5

English input: Test execution pressure-cycle@run-88 occurred on pump P3; its outcome is not asserted.
Ainglish input: pump P3, test-run(pressure-cycle@run-88).

Input 6

English input: Test execution reconciliation@run-209 occurred on ledger L2; its outcome is not asserted.
Ainglish input: ledger L2, test-run(reconciliation@run-209).

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": "tiktoken\/cl100k_base",
        "value": -6.9375
    },
    {
        "model": "tiktoken\/o200k_base",
        "value": -7
    }
]

Condition results

Not recorded

Exact result and immutable specification Experiment history

Attempt e45875dc-96b4-4979-ae22-9b7ec82eb005
Content 9def481776a800efb4662c5c6c922b95687d05f9d76e6ad7b9a8ab3e0177c8cc

Second result: full recordtoken cost · -6.875 tokens per declared item

Second result · 2026-08-28 16:06 UTC

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

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: token cost · token_delta
How does the wording change tokenizer units for the declared tokenizer population?
Reported result: -6.875 tokens per declared item
Reported interval: -6.9375 to -6.875.
Fewer tokens on the named current tokenizers; this is the encoded-length difference, not the proposal decision.
English comparison: English comparison not recorded as a structured label
Declared by the submitter; not a certification of equivalent information.
Tokenizer conditions: Literal encoding cost on the named current tokenizers; not comprehension.
Named instruments: tiktoken/cl100k_base, tiktoken/o200k_base
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: Agrees with the named original
This eligible row adds one agreement to the named original’s settlement tally.

Is this result within the cost allowance?

This headline is within the allowance. The reported difference is -6.875 tokens; the current declaration allows at most 0 tokens.

Has the original estimate been independently reproduced?

Agrees with the named original. This replication reports -6.875 tokens; the named original reported -6.9375.

This eligible row adds one agreement to the named original’s settlement tally.

Reproduction asks whether fresh-input findings agree under the settlement rule. It does not ask whether either value satisfies the cost allowance.

How can one check pass while the other does not?

These are illustrative numbers, not a new settlement rule. A cost saving is not a comprehension result, and a reproduced premium does not by itself mean a proposal should be adopted or rejected.

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?

100.0% of complete English–Ainglish pairs are fresh.

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

9def481776a800efb4662c5c6c922b95687d05f9d76e6ad7b9a8ab3e0177c8cc

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.

Showing 1–6 of 32 readable, inline study items, in stored order—not a selection of successes. 0 control items are kept separate.

Each result has its own input pages. Positions across the two studies do not imply matched cases.

Input 1

English input: Test execution boot-loop-soak@run-2207 occurred on firmware image F31; its outcome is not asserted.
Ainglish input: firmware image F31, test-run(boot-loop-soak@run-2207).

Input 2

English input: Test execution balance-recompute@run-91 occurred on ledger snapshot L8; its outcome is not asserted.
Ainglish input: ledger snapshot L8, test-run(balance-recompute@run-91).

Input 3

English input: Test execution segment-align@run-17 occurred on translation memory TM4; its outcome is not asserted.
Ainglish input: translation memory TM4, test-run(segment-align@run-17).

Input 4

English input: Test execution thermal-profile@run-6 occurred on kiln batch K12; its outcome is not asserted.
Ainglish input: kiln batch K12, test-run(thermal-profile@run-6).

Input 5

English input: Test execution potency-assay@run-3 occurred on vaccine lot V220; its outcome is not asserted.
Ainglish input: vaccine lot V220, test-run(potency-assay@run-3).

Input 6

English input: Test execution load-cycle@run-440 occurred on bridge span S2; its outcome is not asserted.
Ainglish input: bridge span S2, test-run(load-cycle@run-440).

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": "tiktoken\/cl100k_base",
        "value": -6.875
    },
    {
        "model": "tiktoken\/o200k_base",
        "value": -6.9375
    }
]

Condition results

Not recorded

Exact result and immutable specification Experiment history

Attempt 08b3ccdd-20d7-4bbd-8a12-eea45a180a7b
Content 7fc69b3b92ff46e6e86012786158bfebe8a984abc5bd5db0341b52b0711bc2b8

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.