Compare two experiments

First result · 2026-09-30 06:29 UTC

no-undo / can-undo(<how>) — can this action's effect be taken back, and by what path?

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

What was measured

token cost · token_delta
How does the wording change tokenizer units for the declared tokenizer population?

Reported result

-0.6875 tokens per declared item
Reported interval: -1.15625 to -0.6875.

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

cl100k_base, o200k_base, p50k_base

Reader population not separately declared.

Conditions covered

Separate outcomes retained for all 2 declared conditions

no-undo, can-undo

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.

Is this result within the cost allowance?

This headline is within the allowance. The reported difference is -0.6875 tokens; the current declaration allows at most 2 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?

Disputed.

Eligible replications disagree and this original does not hold 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
`no-undo`	-1	Not recorded
`can-undo`	-0.375	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 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: Rotated the signing key; I cannot reverse this.
Ainglish input: Rotated the signing key, no-undo.
Condition: no-undo

Input 2

English input: Published 1.4.0 to npm; I cannot reverse this.
Ainglish input: Published 1.4.0 to npm, no-undo.
Condition: no-undo

Input 3

English input: Sent the invoice to the client; I cannot reverse this.
Ainglish input: Sent the invoice to the client, no-undo.
Condition: no-undo

Input 4

English input: Purged the March audit log; I cannot reverse this.
Ainglish input: Purged the March audit log, no-undo.
Condition: no-undo

Input 5

English input: Posted the apology; I cannot reverse this.
Ainglish input: Posted the apology, no-undo.
Condition: no-undo

Input 6

English input: Shredded the ballots; I cannot reverse this.
Ainglish input: Shredded the ballots, no-undo.
Condition: no-undo

Recorded input digest: 993534fa3ad7c259348757dc3060ba21a0d43b0f7781e1b987af1895c7f538cf

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: marked form (`ACTION, no-undo.` / `ACTION, can-undo(PATH[; HOLDER][; WINDOW][; COST]).`) minus the one fixed careful-English rendering R* v3 (`ACTION; I cannot reverse this.` / `ACTION; I can reverse this via PATH[ within N units][; cost COST].` / `ACTION; HOLDER can reverse this via PATH[...].`), both arms carrying the same ACTION, PATH, HOLDER, WINDOW and COST; renderer noundo_rstar.py sha256 b1cd2787af86de587058fb7914e959a66ddaaedbf974f1f6b440f43832dbeed8
Tested population: the authored 32-pair bank of the row's proposer (bank.json canonical-JSON sha256 f7e05fd81e90786610de559ad3c8ae4d29477180b8051cff20552d1610ef04de, panel-artifacts commit ecab3926b535b8b8ab6326b83b6ed13f24f4687e): 16 no-undo and 16 can-undo, 8 report and 8 instruction per stratum, ACTION word lengths 3:6 4:8 5:8 6:6 7:4, the sixteen can-undo slot combinations on the pinned joint schedule, materialised in profile.json (sha256 bd684a47ec245f1ff265ae35913bf69b06de75d2a6c28d699cbc2125cc02f79b); every ACTION fresh against the 96 prior-bank digests; English arms byte-equal to R* by the packet validator
Unit tested: complete message
How results combine: equal item mean per tokenizer, then maximum tokenizer mean (least-favourable); strata no-undo and can-undo reported at weight 1 each

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": -1.15625
    },
    {
        "model": "o200k_base",
        "value": -1.125
    },
    {
        "model": "p50k_base",
        "value": -0.6875
    }
]

Condition results

[
    {
        "id": "no-undo",
        "weight": 1,
        "share": 0.5,
        "value": -1,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "can-undo",
        "weight": 1,
        "share": 0.5,
        "value": -0.375,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]

Exact result and immutable specification Experiment history

Attempt 85b51498-899a-45ad-a9da-f9396415f76f
Content b9572064b47bf2fe82f88dc56097292cb8dccee4775f94b6875e80f146eb3a88