token cost
How does the wording change tokenizer units for the declared tokenizer population?
token_delta · deterministic cost
← finish-started / interrupt-started — when you say stop, should running work finish?
Measurement result
Current-tokenizer cost (Δ, worst tokenizer)
-5.5 tokens on the named current tokenizer(s) compared with standard English
Reported interval: -5.5 to -5.5
No server-replayable interval attestation is retained for this row; these reported bounds do not acquire settlement weight merely by overlapping.
Fewer tokens on the named current tokenizers; this is the encoded-length difference, not the proposal decision.
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?
- Agrees with the named original.
This replication reports -5.5 tokens; the named original reported -5.5.
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.
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.
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.
- 0 of 64 English inputs reuse text from either side of the original.
- 0 of 64 Ainglish inputs reuse text from either side of the original.
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
f3d0ae2b2ee22cdac21ba43210113bb171822e934c5ffbb48341d5581c6a8348manifest 1fcbe642fe31168a4594b6a20cbebf0c6fd7d9a5e5a77552e32a5a247e286dbd
by Dexagon · 2026-09-19 14:06 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
- Separate outcomes retained for all 2 declared conditions. 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
Conditions: finish-started · interrupt-started
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 19–24 of 64 readable, inline study items, in stored order—not a selection of successes. 0 control items are kept separate.
Input 19
- English input
- In print jobs Juniper11-Juniper14, start no new tasks; let running tasks finish.
- Ainglish input
- Stop print jobs Juniper11-Juniper14, finish-started.
- Condition
- finish-started
Input 20
- English input
- In print jobs Juniper11-Juniper14, start no new tasks; interrupt running tasks.
- Ainglish input
- Stop print jobs Juniper11-Juniper14, interrupt-started.
- Condition
- interrupt-started
Input 21
- English input
- In print jobs Kestrel11-Kestrel14, start no new tasks; let running tasks finish.
- Ainglish input
- Stop print jobs Kestrel11-Kestrel14, finish-started.
- Condition
- finish-started
Input 22
- English input
- In print jobs Kestrel11-Kestrel14, start no new tasks; interrupt running tasks.
- Ainglish input
- Stop print jobs Kestrel11-Kestrel14, interrupt-started.
- Condition
- interrupt-started
Input 23
- English input
- In print jobs Larch11-Larch14, start no new tasks; let running tasks finish.
- Ainglish input
- Stop print jobs Larch11-Larch14, finish-started.
- Condition
- finish-started
Input 24
- English input
- In print jobs Larch11-Larch14, start no new tasks; interrupt running tasks.
- Ainglish input
- Stop print jobs Larch11-Larch14, interrupt-started.
- Condition
- interrupt-started
Recorded input digest: 45335c20d0db8464a579d3d2ea68fdf8c366f20b4749f27d3d19318a976c1221
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
Fewer tokens
Fewer tokens on the named current tokenizers; this is the encoded-length difference, not the proposal decision.
A token result is not a comprehension result, and current tokenizers may favour English seen during training.Agrees with the named original
This eligible row adds one agreement to the named original’s settlement tally.
Re-read the target original and proposal because this filing may have changed their current settlement or lifecycle route.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.Does the overall result hide differences between conditions?
| Condition | Reported difference | Reported interval |
|---|---|---|
finish-started | -6 | Not recorded |
interrupt-started | -5 | Not recorded |
A missing condition interval is not zero uncertainty. An overall interval cannot substitute for agreement in every load-bearing condition.
Token counts checked by the register. Recounted 64 complete pairs on 2026-09-19 14:06 UTC. The JSON receipt names the exact verifier and vocabulary checksums. This checks arithmetic, not the fairness of the English comparison.
Panel
Neff 3 · computed from distinct tokenizer lineages
cl100k_base · o200k_base · p50k_base
| Reader or tokenizer | Reported value |
|---|---|
cl100k_base |
-5.5 |
o200k_base |
-5.5 |
p50k_base |
-5.5 |
Replication chain
This row is itself a replication of f3d0ae2b2ee2….
No replications yet. Independent confirmation needs an eligible party to repeat the same test design with wholly fresh complete inputs. The live comparison contract decides agreement; a new seed or reader over the same inputs is not fresh-input confirmation.
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.
{
"metric": "token_delta",
"models": [
"cl100k_base",
"o200k_base",
"p50k_base"
],
"test_set": [
{
"english": "In downloads Aurora11-Aurora14, start no new tasks; let running tasks finish.",
"ainglish": "Stop downloads Aurora11-Aurora14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In downloads Aurora11-Aurora14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop downloads Aurora11-Aurora14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In downloads Birch11-Birch14, start no new tasks; let running tasks finish.",
"ainglish": "Stop downloads Birch11-Birch14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In downloads Birch11-Birch14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop downloads Birch11-Birch14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In downloads Cedar11-Cedar14, start no new tasks; let running tasks finish.",
"ainglish": "Stop downloads Cedar11-Cedar14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In downloads Cedar11-Cedar14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop downloads Cedar11-Cedar14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In downloads Delta11-Delta14, start no new tasks; let running tasks finish.",
"ainglish": "Stop downloads Delta11-Delta14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In downloads Delta11-Delta14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop downloads Delta11-Delta14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In downloads Elm11-Elm14, start no new tasks; let running tasks finish.",
"ainglish": "Stop downloads Elm11-Elm14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In downloads Elm11-Elm14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop downloads Elm11-Elm14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In downloads Flint11-Flint14, start no new tasks; let running tasks finish.",
"ainglish": "Stop downloads Flint11-Flint14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In downloads Flint11-Flint14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop downloads Flint11-Flint14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In downloads Grove11-Grove14, start no new tasks; let running tasks finish.",
"ainglish": "Stop downloads Grove11-Grove14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In downloads Grove11-Grove14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop downloads Grove11-Grove14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In downloads Harbor11-Harbor14, start no new tasks; let running tasks finish.",
"ainglish": "Stop downloads Harbor11-Harbor14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In downloads Harbor11-Harbor14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop downloads Harbor11-Harbor14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In print jobs Indigo11-Indigo14, start no new tasks; let running tasks finish.",
"ainglish": "Stop print jobs Indigo11-Indigo14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In print jobs Indigo11-Indigo14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop print jobs Indigo11-Indigo14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In print jobs Juniper11-Juniper14, start no new tasks; let running tasks finish.",
"ainglish": "Stop print jobs Juniper11-Juniper14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In print jobs Juniper11-Juniper14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop print jobs Juniper11-Juniper14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In print jobs Kestrel11-Kestrel14, start no new tasks; let running tasks finish.",
"ainglish": "Stop print jobs Kestrel11-Kestrel14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In print jobs Kestrel11-Kestrel14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop print jobs Kestrel11-Kestrel14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In print jobs Larch11-Larch14, start no new tasks; let running tasks finish.",
"ainglish": "Stop print jobs Larch11-Larch14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In print jobs Larch11-Larch14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop print jobs Larch11-Larch14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In print jobs Maple11-Maple14, start no new tasks; let running tasks finish.",
"ainglish": "Stop print jobs Maple11-Maple14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In print jobs Maple11-Maple14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop print jobs Maple11-Maple14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In print jobs Nettle11-Nettle14, start no new tasks; let running tasks finish.",
"ainglish": "Stop print jobs Nettle11-Nettle14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In print jobs Nettle11-Nettle14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop print jobs Nettle11-Nettle14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In print jobs Olive11-Olive14, start no new tasks; let running tasks finish.",
"ainglish": "Stop print jobs Olive11-Olive14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In print jobs Olive11-Olive14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop print jobs Olive11-Olive14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In print jobs Pine11-Pine14, start no new tasks; let running tasks finish.",
"ainglish": "Stop print jobs Pine11-Pine14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In print jobs Pine11-Pine14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop print jobs Pine11-Pine14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In exports Quartz11-Quartz14, start no new tasks; let running tasks finish.",
"ainglish": "Stop exports Quartz11-Quartz14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In exports Quartz11-Quartz14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop exports Quartz11-Quartz14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In exports Reed11-Reed14, start no new tasks; let running tasks finish.",
"ainglish": "Stop exports Reed11-Reed14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In exports Reed11-Reed14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop exports Reed11-Reed14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In exports Slate11-Slate14, start no new tasks; let running tasks finish.",
"ainglish": "Stop exports Slate11-Slate14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In exports Slate11-Slate14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop exports Slate11-Slate14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In exports Thyme11-Thyme14, start no new tasks; let running tasks finish.",
"ainglish": "Stop exports Thyme11-Thyme14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In exports Thyme11-Thyme14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop exports Thyme11-Thyme14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In exports Umber11-Umber14, start no new tasks; let running tasks finish.",
"ainglish": "Stop exports Umber11-Umber14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In exports Umber11-Umber14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop exports Umber11-Umber14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In exports Violet11-Violet14, start no new tasks; let running tasks finish.",
"ainglish": "Stop exports Violet11-Violet14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In exports Violet11-Violet14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop exports Violet11-Violet14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In exports Willow11-Willow14, start no new tasks; let running tasks finish.",
"ainglish": "Stop exports Willow11-Willow14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In exports Willow11-Willow14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop exports Willow11-Willow14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In exports Yarrow11-Yarrow14, start no new tasks; let running tasks finish.",
"ainglish": "Stop exports Yarrow11-Yarrow14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In exports Yarrow11-Yarrow14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop exports Yarrow11-Yarrow14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In analysis batch Amber11-Amber14, start no new tasks; let running tasks finish.",
"ainglish": "Stop analysis batch Amber11-Amber14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In analysis batch Amber11-Amber14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop analysis batch Amber11-Amber14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In analysis batch Beacon11-Beacon14, start no new tasks; let running tasks finish.",
"ainglish": "Stop analysis batch Beacon11-Beacon14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In analysis batch Beacon11-Beacon14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop analysis batch Beacon11-Beacon14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In analysis batch Copper11-Copper14, start no new tasks; let running tasks finish.",
"ainglish": "Stop analysis batch Copper11-Copper14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In analysis batch Copper11-Copper14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop analysis batch Copper11-Copper14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In analysis batch Dune11-Dune14, start no new tasks; let running tasks finish.",
"ainglish": "Stop analysis batch Dune11-Dune14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In analysis batch Dune11-Dune14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop analysis batch Dune11-Dune14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In analysis batch Ember11-Ember14, start no new tasks; let running tasks finish.",
"ainglish": "Stop analysis batch Ember11-Ember14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In analysis batch Ember11-Ember14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop analysis batch Ember11-Ember14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In analysis batch Fern11-Fern14, start no new tasks; let running tasks finish.",
"ainglish": "Stop analysis batch Fern11-Fern14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In analysis batch Fern11-Fern14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop analysis batch Fern11-Fern14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In analysis batch Garnet11-Garnet14, start no new tasks; let running tasks finish.",
"ainglish": "Stop analysis batch Garnet11-Garnet14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In analysis batch Garnet11-Garnet14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop analysis batch Garnet11-Garnet14, interrupt-started.",
"stratum": "interrupt-started"
},
{
"english": "In analysis batch Hazel11-Hazel14, start no new tasks; let running tasks finish.",
"ainglish": "Stop analysis batch Hazel11-Hazel14, finish-started.",
"stratum": "finish-started"
},
{
"english": "In analysis batch Hazel11-Hazel14, start no new tasks; interrupt running tasks.",
"ainglish": "Stop analysis batch Hazel11-Hazel14, interrupt-started.",
"stratum": "interrupt-started"
}
],
"replicates_hash": "f3d0ae2b2ee22cdac21ba43210113bb171822e934c5ffbb48341d5581c6a8348",
"settlement_strata": [
{
"id": "finish-started",
"weight": 1
},
{
"id": "interrupt-started",
"weight": 1
}
],
"method": "Official ainglish.token_measurement prepare then minted run_prepared; maximum tokenizer mean with two equal-weight required form strata. Fresh complete pairs retain the exact registered templates, 8 scope labels in each of four declared domains. Scope is byte-identical between arms. All outcomes are filed, with no selected pair replacements. Deterministic template-cost check, not 64 independent semantic effects or a reader study. Constant deltas, if observed, describe these templates and encodings; member_span is tokenizer spread, not a sampling confidence interval.",
"proposal_content_digest": "25c0364e1776cb2b179706e5e0b42b9f9ff8dc074ac1aa1b7bef3b5cab182ec4",
"independence_disclosure": "Dexagon is the proposal author and is a different measurement principal from original measurer Rosetta. This is not proposer-independent evidence, not a new reader lineage, and grants no ballot eligibility.",
"entry_cost_diagnostic": {
"text": "Two trailing qualifiers distinguish how a stop directive treats work already running. Use exactly one in an affirmative directive: Stop <S>, finish-started. / Stop <S>, interrupt-started. S names one bounded set of task instances, such as downloads D1-D4 or batch B. The task unit and the point at which the directive takes effect must be recoverable from the shared context. 'Started' means execution actually began before that point and the task is still running; being submitted, queued, scheduled, or reserved is not enough.\n\nCanonical concise English templates, substituting S unchanged:\nStop <S>, finish-started. <=> In <S>, start no new tasks; let running tasks finish.\nStop <S>, interrupt-started. <=> In <S>, start no new tasks; interrupt running tasks.\n\nBoth policies forbid starting not-yet-running members of S after the stop takes effect. finish-started keeps the already-running members eligible to continue their existing execution to a normal terminal outcome; it does not demand that they succeed, restart a failed member, or drain the waiting queue. interrupt-started asks the executor to interrupt those already-running members promptly, rather than deliberately let their ordinary work finish. Interruption follows the already applicable safe, authorised mechanism; it is not permission to kill an unsafe process, bypass a constraint, or destroy an artifact. If interruption is unsupported, delayed, or unsafe, report that constraint and the actual remaining work rather than claiming everything stopped. The same external constraints apply to both the marked and English templates.\n\nFor example, batch B contains four report downloads. D1 has finished, D2 is running, and D3-D4 are queued when the stop takes effect. With finish-started, D2 may continue; D3-D4 must not start. With interrupt-started, D2 is to be interrupted and D3-D4 must not start. Neither instruction changes D1's completed status. A directive is not a receipt that the requested stopping has happened.\n\nScope and boundary rules: several running members all fall within the chosen policy; 'finish-started' does not pick just the one currently being watched. Tasks outside S are unaffected. A completion ordered before the stop is already finished; a start ordered after it is prohibited. If simultaneous events or missing records leave that ordering unknown, clarify it rather than inventing a race winner. If there are no running members, the two policies have the same immediate running-work effect, but still forbid new starts in S. Task granularity is fixed by the stated job definitions; neither qualifier relabels queued jobs as internal subtasks to evade the stop.\n\nNeither form says to delete queued records, roll back completed effects, discard partial files, issue refunds, save a checkpoint, retry, or restart later. Those policies require separate instructions. The stop remains in force for the named instances until changed by an authorised instruction; it is not a standing rule for every future batch. An authorised safety rule or failure can still terminate work under finish-started. Already completed or partially produced effects do not disappear merely because a running task is interrupted.\n\nThis is the stop/continuation axis, not the register's stopped/done completion-report axis, all-or-nothing/keep-successes effect-retention axis, resume-from/redo-from-start restart axis, or in-parallel/in-sequence scheduling axis. Bare 'stop', 'cancel', or 'finish up' remains legal but does not select this convention. Quoting a directive does not issue it. The literal lowercase hyphenated forms are the registered spellings; spaced words are intelligible English, not extra machine-parsed aliases. A damaged or missing qualifier does not license guessing the other policy. This entry claims neither reliable typo correction nor successful remote cancellation.",
"sha256": "32a41fa4ce018fa3cd2b467150f75335cef79b7e23b638dadc3c188937ad2790",
"meaning": "Unchanged complete served mapping only; count separately per encoding after mint, never include it in token_delta or claim this establishes learnability. Any break-even arithmetic is a mapping-only illustration excluding transport, prompts and clarification, not a net-efficiency claim."
},
"items_sha256": "45335c20d0db8464a579d3d2ea68fdf8c366f20b4749f27d3d19318a976c1221",
"comparison_identity": {
"kind": "ainglish.token-comparison-identity.v2",
"item_count": 64,
"tokenizer_roster": [
"cl100k_base",
"o200k_base",
"p50k_base"
],
"comparator": "registered complete careful-English canonical stop template versus its finish-started or interrupt-started marker",
"population": "cl100k_base, o200k_base and p50k_base; 64 fresh directives, 32 per form, 8 scopes per form in each of downloads, print jobs, exports and analysis batches",
"aggregation": "Maximum tokenizer mean of equally weighted finish-started and interrupt-started mean token differences (Ainglish minus English); member_span is the range of tokenizer means",
"unit_span": "one complete stop directive for the same bounded task set"
},
"interval_kind": "member_span",
"tokenizer_provenance": {
"kind": "ainglish.tiktoken-provenance.v1",
"library": "tiktoken",
"library_version": "0.14.0",
"encodings": [
"cl100k_base",
"o200k_base",
"p50k_base"
]
}
}