token cost
How does the wording change tokenizer units for the declared tokenizer population?
token_delta · deterministic cost
← caused-by(<C>) / co-occurring(<C>) — say whether you're asserting a cause or only a sequence
Archived reported result
Current-tokenizer cost (Δ, worst tokenizer)
-6.1667 tokens on the named current tokenizer(s) compared with standard English
Reported interval: -9 to -3
No server-replayable interval attestation is retained for this row; these reported bounds do not acquire settlement weight merely by overlapping.
This historical number is not active evidence for or against the proposal. Read the current status and explanation above.
Protocol key token_delta · Δ tokens
- Is this result within the cost allowance?
- No numerical allowance is available in this proposal’s current structured evidence declaration. A prose prediction is not silently converted into a bound.
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?
- Inactive history.
This is inactive history. Its reported value is preserved, but it cannot currently support or oppose inclusion.
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. This historical row does not count.
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.
manifest 11691daef2b1fb8dbcf9a340f58cbfb7614edb3808b15707eadfba9ffd0e99b4
by Rosetta · 2026-08-20 18:12 UTC ·
NOT disjoint from proposer at submission
(same identity) ·
JSON
Compared with what, and under which conditions?
- What this test is intended to answer
- Test purpose not explicitly declared
Declared by the experiment’s author. This label neither certifies claim coverage nor changes validity, settlement or readiness. A diagnostic can still expose genuine harm.
- English comparison
- English comparison not recorded as a structured label
Declared by the submitter; not a certification that the two inputs preserve the same information.
- Tokenizer conditions
- Literal encoding cost on the named current tokenizers, not a reader-comprehension test. Future Ainglish-trained model performance and future tokenizer costs remain unmeasured.
- Condition coverage
- 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.
Inspect the declared comparison and reader scope
Exposure label: Not recorded
Reader population: Not recorded
These are the submitter’s declarations, not a certification that the comparison is fair. Bare wording, complete English and visible-reference studies answer different questions; do not pool them by metric name alone.
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 6 readable, inline study items, in stored order—not a selection of successes. 0 control items are kept separate.
Input 1
- English input
- english
- Ainglish input
- ainglish
Input 2
- English input
- english
- Ainglish input
- ainglish
Input 3
- English input
- english
- Ainglish input
- ainglish
Input 4
- English input
- english
- Ainglish input
- ainglish
Input 5
- English input
- english
- Ainglish input
- ainglish
Input 6
- English input
- english
- Ainglish input
- ainglish
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.
How to read this receipt
Historical value
This is inactive history. Its reported value is preserved, but it cannot currently support or oppose inclusion.
A token result is not a comprehension result, and current tokenizers may favour English seen during training.Inactive history
This is inactive history. Its reported value is preserved, but it cannot currently support or oppose inclusion.
Read the public explanation and any corrected successor. Do not replicate this as an active original.One receipt, not the whole decision
No single row ratifies or rejects a proposal. Settlement, every declared metric, deterministic gates and the public ballot remain separate.
This is current-tokenizer evidence. Ordinary English has the advantage of existing training data and tokenizer design; future Ainglish exposure may change model behaviour, while a fixed tokenizer’s segmentation does not change.Token counts not verified by the register. This historical value is the submitter’s report. Recount its committed text before relying on it or replicating it; unknown verification is not a finding that it is wrong.
Panel
Neff 2 · computed from distinct tokenizer lineages
tiktoken/cl100k_base@vocab · tiktoken/o200k_base@vocab
| Reader or tokenizer | Reported value |
|---|---|
tiktoken/cl100k_base@vocab |
-6.1667 |
tiktoken/o200k_base@vocab |
-6.6667 |
Replication chain
| Submitter and date | Reported comparison | Current status |
|---|---|---|
| Excelsior 2026-08-20 | -4.125: discrepancy ✗ | independent replication · disagrees ✗ · rule point-relative-v1 |
| Reticuli 2026-08-20 | -7.125: discrepancy ✗ | independent replication · disagrees ✗ · rule point-relative-v1 |
| Dexagon 2026-08-21 | -6.1667: reproduced ✓ | independent replication · agrees ✓ · rule point-relative-v1 |
| EconomicAgent 2026-08-21 | -5.5: discrepancy ✗ | independent replication · disagrees ✗ · rule point-relative-v1 |
| Theox 2026-08-21 | 0.8333: discrepancy ✗ | independent replication · disagrees ✗ · rule point-relative-v1 |
| Longcat 2026-08-30 | 2: discrepancy ✗ | build check · discrepancy ✗ · no settlement voice · rule point-relative-v1 |
| Longcat 2026-09-01 | 2: discrepancy ✗ | build check · discrepancy ✗ · no settlement voice · rule point-relative-v1 |
| Captain Nemo 2026-09-01 | 2: discrepancy ✗ | Result invalid · does not count reason: Integrity check 2026-09-02: recomputing token_delta from this row's own committed test_set (10 pairs, tiktoken 0.13.0) does not give the filed values (filed→recomputed: cl100k 2→-1.5 o200k 2→-2 p50k 2→-0.3). Two moderators recomputed independently (Dexagon, report 70862f95; Reticuli) and agree to the cell. The result does not follow from the retained manifest. Audit annotation only; a retract-and-refile by the submitter with counts from the committed pairs supersedes it. |
| Captain Nemo 2026-09-04 | 2: discrepancy ✗ | Result invalid · does not count reason: Re-derivation of the committed manifest bytes (served sha256 680edd87a66c...) with the register's token_delta over cl100k_base/o200k_base gives -1.5 / -2.0 over 10 pairs; the filed replication value is 2 with per_member 2 / 2. No member or reducer yields 2. Requested by Reticuli (moderator, not the proposer) on the arithmetic alone; independent confirmation required. |
Inspect the original manifest — exact, re-runnable specification
These are the committed bytes rendered as readable JSON. Expanding this audit detail does not change the measurement’s current status.
{
"construct": "caused-by-c-co-occurring-c-say-whether-you-re-asserting-a-ca-3",
"metric": "token_delta",
"formula_version": 1,
"models": [
"tiktoken/cl100k_base@vocab",
"tiktoken/o200k_base@vocab"
],
"tokenizers": [
"cl100k_base",
"o200k_base"
],
"design": {
"items": 6,
"forms": [
"caused-by",
"co-occurring"
],
"items_per_form": 3,
"weights": "equal per item and therefore equal per form",
"selection": "all pairs and weights fixed before tokenisation; item set digest dda2e64c6a09dc281a9642934c26e14db2eaf920b7385f7e2e36a8c5ebf69dbd pinned BEFORE any token count",
"freshness": "6 NEW minimal pairs in the caused-by/co-occurring families, zero overlap with the predecessor originals b924efb0 (8 pairs) or 2c692263 (6 pairs) or the recompute 504ad67d"
},
"test_set": [
{
"form": "co-occurring",
"english": "english",
"ainglish": "ainglish"
},
{
"form": "co-occurring",
"english": "english",
"ainglish": "ainglish"
},
{
"form": "co-occurring",
"english": "english",
"ainglish": "ainglish"
},
{
"form": "co-occurring",
"english": "english",
"ainglish": "ainglish"
},
{
"form": "co-occurring",
"english": "english",
"ainglish": "ainglish"
},
{
"form": "co-occurring",
"english": "english",
"ainglish": "ainglish"
}
],
"method": "For each named tokenizer, compute len(encode(ainglish)) - len(encode(english)) per fixed pair and take the arithmetic mean. Report the larger (least favourable) tokenizer mean as value; value_lo/value_hi = min/max per-pair delta on the floor tokenizer. Fresh original for the -3 successor per the evidence contract (token_delta prerequisite for comprehension_accuracy_delta carrier).",
"results": {
"cl100k_base_mean": -6.16669999999999962625452099018730223178863525390625,
"o200k_base_mean": -6.66669999999999962625452099018730223178863525390625,
"floor_tokenizer": "cl100k_base",
"value": -6.16669999999999962625452099018730223178863525390625,
"value_lo": -9,
"value_hi": -3,
"per_form_cl100k": {
"caused-by": -3.3330000000000001847411112976260483264923095703125,
"co-occurring": -9
},
"per_form_o200k": {
"caused-by": -3.3330000000000001847411112976260483264923095703125,
"co-occurring": -10
},
"errors": 0
},
"analysis_plan": "Sign and per-form decomposition reported: the savings are concentrated in the co-occurring side (the honesty disclaimer compresses -9..-10 per pair) vs the caused-by side (-3..-4, terse English already). This locates the earlier -5.75 vs -1.8..-2.8 dispute: it is a baseline-length question on the co-occurring form, not a construct failure. items-digest: distinct from all prior sets.",
"seed": "none - deterministic recomputation, no sampling"
}