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
4 tokens per declared item Reported interval: 2 to 4.
More 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
assigned-to, accepted-by
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 4 tokens; the current declaration allows at most 4 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
assigned-to
4
Not recorded
accepted-by
4
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 128 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 · assign-cost-001
English input
the Elm ticket summary is assigned to agent Fern by coordinator Aspen.
Ainglish input
the Elm ticket summary assigned-to(agent Fern; by=coordinator Aspen).
Condition
assigned-to
Input 2 · accept-cost-001
English input
agent Fern accepted responsibility for the Elm ticket summary in acceptance-event-001.
Ainglish input
the Elm ticket summary accepted-by(agent Fern; ref=acceptance-event-001).
Condition
accepted-by
Input 3 · assign-cost-002
English input
the Birch account reply is assigned to agent Moss by coordinator Beech.
Ainglish input
the Birch account reply assigned-to(agent Moss; by=coordinator Beech).
Condition
assigned-to
Input 4 · accept-cost-002
English input
agent Moss accepted responsibility for the Birch account reply in acceptance-event-002.
Ainglish input
the Birch account reply accepted-by(agent Moss; ref=acceptance-event-002).
Condition
accepted-by
Input 5 · assign-cost-003
English input
the Rowan help-page review is assigned to agent Reed by coordinator Cypress.
Ainglish input
the Rowan help-page review assigned-to(agent Reed; by=coordinator Cypress).
Condition
assigned-to
Input 6 · accept-cost-003
English input
agent Reed accepted responsibility for the Rowan help-page review in acceptance-event-003.
Ainglish input
the Rowan help-page review accepted-by(agent Reed; ref=acceptance-event-003).
Condition
accepted-by
Recorded input digest: 036b99ebabe3b3b057d6c9de32141c428be4461ac74c417cf98aae8e5d256d7b
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 statement minus concise complete English: T is assigned to A by P; A accepted responsibility for T in R. Identical task and principal references and attributable acceptance event. No bare status comparator.
Tested population
128 authored task statements: 64 operative current assignments and 64 attributable deliberate acceptances; eight task domains equally weighted within each form, eight task titles per domain. Named fictional principals and bounded task references are resolved in the shared ledger.
Unit tested
one complete task assignment or acceptance statement
How results combine
equal item mean within two equally weighted form strata per tokenizer, then maximum tokenizer mean; report both form strata
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.
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.
