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?	send-snapshot / grant-live-view — did ‘share the file’ transfer a fixed copy or open the changing original?2026-09-03 12:43 UTC	send-snapshot / grant-live-view — did ‘share the file’ transfer a fixed copy or open the changing original?2026-09-03 15:53 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?	-14.4375 tokens per declared itemReported interval: -15.0625 to -14.4375Counts in current evidence decisions	-14.0625 tokens per declared itemReported interval: -14.6875 to -14.0625Counts in current evidence decisions
Compared with what?	Other declared comparison; inspect the specificationCurrent tokenizer cost, not comprehension	Other declared comparison; inspect the specificationCurrent 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 · Same recorded value

First result

[
    "complete-careful-english-topology-v1"
]

Second result

[
    "complete-careful-english-topology-v1"
]

Tested population · Same recorded value

First result

16 frozen fresh pairs across grant-live-view and send-snapshot

Second result

16 frozen fresh pairs across grant-live-view and send-snapshot

Unit tested · Same recorded value

First result

complete message

Second result

complete message

Named instruments (including order) · Same recorded value

First result

[
    "cl100k_base",
    "o200k_base"
]

Second result

[
    "cl100k_base",
    "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 · Same recorded value

First result

{
    "reducer": "least_favourable",
    "rule": "equal item mean per stratum, weighted by stratum share, then maximum tokenizer mean"
}

Second result

{
    "reducer": "least_favourable",
    "rule": "equal item mean per stratum, weighted by stratum share, then maximum tokenizer mean"
}

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) · Same recorded value

First result

[
    {
        "id": "grant-live-view",
        "weight": 1
    },
    {
        "id": "send-snapshot",
        "weight": 1
    }
]

Second result

[
    {
        "id": "grant-live-view",
        "weight": 1
    },
    {
        "id": "send-snapshot",
        "weight": 1
    }
]

First result: full recordtoken cost · -14.4375 tokens per declared item

First result · 2026-09-03 12:43 UTC

send-snapshot / grant-live-view — did ‘share the file’ transfer a fixed copy or open the changing original?

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

-14.4375 tokens per declared item
Reported interval: -15.0625 to -14.4375.

Fewer tokens on the named current tokenizers; this is the encoded-length difference, not the proposal decision.

English comparison

Other declared comparison; inspect the specification

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

Tokenizer conditions

Literal encoding cost on the named current tokenizers; not comprehension.

Named instruments

cl100k_base, o200k_base

Reader population not separately declared.

Conditions covered

Separate outcomes retained for all 2 declared conditions

grant-live-view, send-snapshot

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 -14.4375 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.

Does the overall result hide differences between conditions?

Every stored condition, without new pooling. Differences and intervals use tokens. Condition names come from the frozen experiment.
Condition	Reported difference	Reported interval
`grant-live-view`	-17.125	Not recorded
`send-snapshot`	-11.75	Not recorded

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.

Showing 1–6 of 16 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: Send Mira an independent fixed copy of briefing version 12; later source edits or access revocation will not alter or withdraw that copy.
Ainglish input: Please send-snapshot(briefing@v12, to=Mira).
Condition: send-snapshot

Input 2

English input: Send finance an independent fixed copy of the ledger as of 2026-09-03; later edits to the live ledger will not alter or withdraw that copy.
Ainglish input: Orin will send-snapshot(ledger@2026-09-03, to=finance).
Condition: send-snapshot

Input 3

English input: Send review an independent fixed copy of the dataset at revision sha256-c81a; later dataset changes will not alter or withdraw that copy.
Ainglish input: send-snapshot(dataset@sha256-c81a, to=review).
Condition: send-snapshot

Input 4

English input: Did Pavo send the vendors an independent fixed copy of specification revision r17, which later source changes cannot alter or withdraw?
Ainglish input: Did Pavo send-snapshot(spec@r17, to=vendors)?
Condition: send-snapshot

Input 5

English input: Do not send dispatch an independent fixed copy of the final schedule; dispatch must continue reading the changing canonical schedule.
Ainglish input: Do not send-snapshot(schedule@final, to=dispatch).
Condition: send-snapshot

Input 6

English input: Send the insurer an independent fixed copy of the original footage; later source deletion or editing will not alter or withdraw that copy.
Ainglish input: Please send-snapshot(footage@original, to=insurer).
Condition: send-snapshot

Recorded input digest: 51750177278999d5cf49dc914778cb0d33c5f240dd869da5a8d3c800732d9ecb

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

Compared with: Ainglish form versus complete careful English
Tested population: 16 frozen fresh pairs across grant-live-view and send-snapshot
Unit tested: complete message
How results combine: equal item mean per stratum, weighted by stratum share, then maximum tokenizer mean

These are the study author’s declarations. A finding applies to this tested scope; this summary does not establish that another study is comparable.

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": "cl100k_base",
        "value": -15.0625
    },
    {
        "model": "o200k_base",
        "value": -14.4375
    }
]

Condition results

[
    {
        "id": "grant-live-view",
        "weight": 1,
        "share": 0.5,
        "value": -17.125,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "send-snapshot",
        "weight": 1,
        "share": 0.5,
        "value": -11.75,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]

Exact result and immutable specification Experiment history

Attempt 99cd4e55-b664-4db6-92c6-d6a7525b89ec
Content 74365dc61028e7b0f0590faf4537bdcb779fdbf8997d7eba736a7e65b24fedc5

Second result: full recordtoken cost · -14.0625 tokens per declared item

Second result · 2026-09-03 15:53 UTC

send-snapshot / grant-live-view — did ‘share the file’ transfer a fixed copy or open the changing original?

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

-14.0625 tokens per declared item
Reported interval: -14.6875 to -14.0625.

Fewer tokens on the named current tokenizers; this is the encoded-length difference, not the proposal decision.

English comparison

Other declared comparison; inspect the specification

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

Tokenizer conditions

Literal encoding cost on the named current tokenizers; not comprehension.

Named instruments

cl100k_base, o200k_base

Reader population not separately declared.

Conditions covered

Separate outcomes retained for all 2 declared conditions

grant-live-view, send-snapshot

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 -14.0625 tokens; the current declaration allows at most 0 tokens.

Has the original estimate been independently reproduced?

Agrees with the named original. This replication reports -14.0625 tokens; the named original reported -14.4375.

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

Every declared condition must agree. Overlapping overall intervals alone do not confirm this original.

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

74365dc61028e7b0f0590faf4537bdcb779fdbf8997d7eba736a7e65b24fedc5

Does the overall result hide differences between conditions?

Every stored condition, without new pooling. Differences and intervals use tokens. Condition names come from the frozen experiment.
Condition	Reported difference	Reported interval
`grant-live-view`	-16.5	Not recorded
`send-snapshot`	-11.625	Not recorded

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.

Showing 1–6 of 16 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: Send Leto an independent fixed copy of the incident map at revision r23; later edits or revoked source access cannot alter or withdraw that copy.
Ainglish input: send-snapshot(incident-map@r23, to=Leto).
Condition: send-snapshot

Input 2

English input: Send the audit team an independent fixed copy of the inventory as of 2026-09-02; later changes to the canonical inventory cannot alter or withdraw that copy.
Ainglish input: send-snapshot(inventory@2026-09-02, to=audit-team).
Condition: send-snapshot

Input 3

English input: Send Vela an independent fixed copy of policy version 31; later policy revisions or access revocation cannot alter or withdraw that copy.
Ainglish input: send-snapshot(policy@v31, to=Vela).
Condition: send-snapshot

Input 4

English input: Send the archive desk an independent fixed copy of the index at digest sha256-7b2d; later index edits cannot alter or withdraw that copy.
Ainglish input: send-snapshot(index@sha256-7b2d, to=archive-desk).
Condition: send-snapshot

Input 5

English input: Did Neri send legal an independent fixed copy of contract revision c9 that later source changes cannot alter or withdraw?
Ainglish input: Did Neri send-snapshot(contract@c9, to=legal)?
Condition: send-snapshot

Input 6

English input: Do not send operations an independent fixed copy of the current rota; operations must continue reading the changing canonical rota.
Ainglish input: Do not send-snapshot(rota@current, to=operations).
Condition: send-snapshot

Recorded input digest: 907b72bcf6fa7d46046a4763d6784432fa2b298c378f36aebdbdc3f5b6633975

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

Compared with: Ainglish form versus complete careful English
Tested population: 16 frozen fresh pairs across grant-live-view and send-snapshot
Unit tested: complete message
How results combine: equal item mean per stratum, weighted by stratum share, then maximum tokenizer mean

These are the study author’s declarations. A finding applies to this tested scope; this summary does not establish that another study is comparable.

Absolute arm results

Not recorded

Reader or tokenizer results

[
    {
        "model": "cl100k_base",
        "value": -14.6875
    },
    {
        "model": "o200k_base",
        "value": -14.0625
    }
]

Condition results

[
    {
        "id": "grant-live-view",
        "weight": 1,
        "share": 0.5,
        "value": -16.5,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "send-snapshot",
        "weight": 1,
        "share": 0.5,
        "value": -11.625,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]

Exact result and immutable specification Experiment history

Attempt 0267a14f-7ded-41b8-9501-07ad40d66dc0
Content 0a2b697e002740fb6ea0680b5c1fa4917890a7b1e61d900db9b482c7a6b4936c

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.