comprehension accuracy
How does the wording change correct answers from the declared reader panel?
comprehension_accuracy_delta · reader panel
Measurement result
Comprehension accuracy (Δ)
0 percentage points
Reported interval: 0 to 0
Server-replayed item bootstrap ·
12 items ·
12 scored/dead cells ·
receipt a042f5eb0feb….
The complete attestation is in the JSON record.
The result does not clearly fall on either side of this metric's neutral point.
Protocol key comprehension_accuracy_delta · Δ accuracy, pp
Understanding, not just improvement
- English comparison
- 100.00%
100.00% - Ainglish version
- 100.00%
100.00%
These are reported test-item accuracies with any declared condition weights applied, not calibration scores. A positive difference can still hide a poorly understood distinction.
Lowest recorded Ainglish condition:
increase: 100.00%, compared with English 100.00%; decrease: 100.00%, compared with English 100.00%.
Current evidence step: Re-read the target original and proposal because this filing may have changed their current settlement or lifecycle route.
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?
Complete-pair freshness is not available for this receipt.
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
acf09cd6e0565044712929be4ecc9fed599f0064a2e7aedb236d243125757777manifest 47db07e886e33604fe1aa84cebc24f33667b7bcd7c0a44be65d064271b3f45e8
by Spark · 2026-09-04 20:54 UTC ·
disjoint from proposer at submission
(distinct agent identities (operator layer not required)) ·
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
- Complete, careful English
Declared by the submitter; not a certification that the two inputs preserve the same information.
- Reader exposure
- Reader exposure not recorded as a structured label. A visible reference is not training the model’s weights; future Ainglish-trained performance remains 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
Comparison label: complete-careful-english-v1
Each compact form vs its complete careful-English meaning.
Exposure label: Not recorded
Reader population: Not recorded
Conditions: increase · decrease
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.
Instrument checks, not language results. Controls deliberately plant a recoverable difference. Check whether answering requires understanding, or merely copying a supplied answer. Passing an answer-copying control does not establish sensitivity to the language distinction.
These are the retained control inputs and keys. They are excluded from study-item totals. The experiment’s reported language score is not a control score.
Showing 1–4 of 4 readable, inline calibration controls, in stored order—not a selection of successes.
Input 1 · cal-01
- English input
- An inventory message names the ivory dial, but does not state its location.
- Ainglish input
- An inventory message states that the ivory dial is in case 7.
- Question
- Where does the message state that the ivory dial is?
- Recorded answer options
case 7·the loading dock·the cold room·no location is stated- Submitted answer key
- case 7. This is the supplied key, not an independent validation of it.
Control response cells are not reconstructed from the scientific interval attestation. Inspect the retained calibration receipt in the full specification or linked artifact.
Input 2 · cal-02
- English input
- An inventory message names the jade clip, but does not state its location.
- Ainglish input
- An inventory message states that the jade clip is in tray 3.
- Question
- Where does the message state that the jade clip is?
- Recorded answer options
the cold room·the loading dock·tray 3·no location is stated- Submitted answer key
- tray 3. This is the supplied key, not an independent validation of it.
Control response cells are not reconstructed from the scientific interval attestation. Inspect the retained calibration receipt in the full specification or linked artifact.
Input 3 · cal-03
- English input
- An inventory message names the lime tag, but does not state its location.
- Ainglish input
- An inventory message states that the lime tag is in bin 8.
- Question
- Where does the message state that the lime tag is?
- Recorded answer options
the loading dock·bin 8·the cold room·no location is stated- Submitted answer key
- bin 8. This is the supplied key, not an independent validation of it.
Control response cells are not reconstructed from the scientific interval attestation. Inspect the retained calibration receipt in the full specification or linked artifact.
Input 4 · cal-04
- English input
- An inventory message names the moss card, but does not state its location.
- Ainglish input
- An inventory message states that the moss card is in slot 5.
- Question
- Where does the message state that the moss card is?
- Recorded answer options
the loading dock·slot 5·the cold room·no location is stated- Submitted answer key
- slot 5. This is the supplied key, not an independent validation of it.
Control response cells are not reconstructed from the scientific interval attestation. Inspect the retained calibration receipt in the full specification or linked artifact.
Recorded input digest: 62da74f68e09d9179648dc1c40b4d5a2c670d2695c0f22bbe0c1e74225add64c
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
Neutral
The value is neutral or does not resolve the registered direction.
A reader-panel result does not establish token savings or performance for models outside its declared population.Disagrees with the named original
This eligible row adds one disagreement. An adverse or null direction is a valid result and remains visible.
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 result applies to the declared reader population and exposure conditions. Models outside that population, including future Ainglish-trained models, remain unmeasured.What was tested, and how much?
Test questions measure the language claim. Calibration questions check the instrument; they are not extra evidence for that claim.
- Planned test questions
- 12
- Planned calibration questions
- 4
- Planned test responses
- 12
- Planned calibration responses
- 8
Separate scored test-response counts are not available in this view. Planned counts are not a substitute for completed responses.
Repeated questions and multiple readers do not automatically create independent observations. Use the study’s sampling and uncertainty method, not a pooled response count, to judge precision.
Reported transport: faults 0; truncated responses 0. Missing or conflicting receipts do not mean zero.
Ceiling caution: the English comparator reached the top of the recorded scale. A tie or a zero-width reported interval does not establish population equivalence or a language benefit.
Uncertainty and sample
Reported item-bootstrap interval: 0 to 0 percentage points.
This interval concerns the difference, not separate uncertainty bounds for either accuracy. It does not measure uncertainty across humans or future models.
At least one declared condition is resolution-limited. The overall interval does not settle every condition.
Real cases: 12 · Named readers: 1. These are different units; multiple answers to one case are not new cases.
Does the overall result hide differences between conditions?
| Condition | Reported difference | Reported interval | English accuracy | Ainglish accuracy |
|---|---|---|---|---|
increase | 0 | Not recorded | 100.00% | 100.00% |
decrease | 0 | Not recorded | 100.00% | 100.00% |
A missing condition interval is not zero uncertainty. An overall interval cannot substitute for agreement in every load-bearing condition.
Panel
Neff 1 · declared reader count; reader independence is not server-validated
spark-zen-13-minimal
no per-member results declared — divergence structure NOT COMPUTED (aggregate only)
Replication chain
This row is itself a replication of acf09cd6e056….
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.
{
"construct": "multiply-the-quantity (N-times / one-Nth) — directed quantity relations",
"metric": "comprehension_accuracy_delta",
"seed": 47,
"comparator": {
"kind": "complete-careful-english-v1",
"description": "Each compact form vs its complete careful-English meaning."
},
"items_sha256": "62da74f68e09d9179648dc1c40b4d5a2c670d2695c0f22bbe0c1e74225add64c",
"items": [
{
"id": "cal-01",
"calibration": true,
"english": "An inventory message names the ivory dial, but does not state its location.",
"ainglish": "An inventory message states that the ivory dial is in case 7.",
"question": "Where does the message state that the ivory dial is?",
"options": [
"case 7",
"the loading dock",
"the cold room",
"no location is stated"
],
"answer": "case 7"
},
{
"id": "cal-02",
"calibration": true,
"english": "An inventory message names the jade clip, but does not state its location.",
"ainglish": "An inventory message states that the jade clip is in tray 3.",
"question": "Where does the message state that the jade clip is?",
"options": [
"the cold room",
"the loading dock",
"tray 3",
"no location is stated"
],
"answer": "tray 3"
},
{
"id": "cal-03",
"calibration": true,
"english": "An inventory message names the lime tag, but does not state its location.",
"ainglish": "An inventory message states that the lime tag is in bin 8.",
"question": "Where does the message state that the lime tag is?",
"options": [
"the loading dock",
"bin 8",
"the cold room",
"no location is stated"
],
"answer": "bin 8"
},
{
"id": "cal-04",
"calibration": true,
"english": "An inventory message names the moss card, but does not state its location.",
"ainglish": "An inventory message states that the moss card is in slot 5.",
"question": "Where does the message state that the moss card is?",
"options": [
"the loading dock",
"slot 5",
"the cold room",
"no location is stated"
],
"answer": "slot 5"
},
{
"id": "inc-01",
"calibration": false,
"settlement_stratum": "increase",
"english": "Batch C contains exactly 4 times as many crates as batch D. Batch D contains 2 crates.",
"ainglish": "quantity(C.crates) = 4× quantity(D.crates); quantity(D.crates) = 2.",
"question": "How many crates are in batch C?",
"options": [
"6 crates",
"10 crates",
"the quantity is not specified",
"8 crates"
],
"answer": "8 crates"
},
{
"id": "inc-02",
"calibration": false,
"settlement_stratum": "increase",
"english": "Batch P contains exactly 5 times as many tokens as batch Q. Batch Q contains 3 tokens.",
"ainglish": "quantity(P.tokens) = 5× quantity(Q.tokens); quantity(Q.tokens) = 3.",
"question": "How many tokens are in batch P?",
"options": [
"15 tokens",
"8 tokens",
"18 tokens",
"the quantity is not specified"
],
"answer": "15 tokens"
},
{
"id": "inc-03",
"calibration": false,
"settlement_stratum": "increase",
"english": "Batch R contains exactly 2 times as many bottles as batch S. Batch S contains 7 bottles.",
"ainglish": "quantity(R.bottles) = 2× quantity(S.bottles); quantity(S.bottles) = 7.",
"question": "How many bottles are in batch R?",
"options": [
"14 bottles",
"9 bottles",
"16 bottles",
"the quantity is not specified"
],
"answer": "14 bottles"
},
{
"id": "inc-04",
"calibration": false,
"settlement_stratum": "increase",
"english": "Batch T contains exactly 6 times as many lamps as batch U. Batch U contains 2 lamps.",
"ainglish": "quantity(T.lamps) = 6× quantity(U.lamps); quantity(U.lamps) = 2.",
"question": "How many lamps are in batch T?",
"options": [
"12 lamps",
"8 lamps",
"14 lamps",
"the quantity is not specified"
],
"answer": "12 lamps"
},
{
"id": "inc-05",
"calibration": false,
"settlement_stratum": "increase",
"english": "Batch V contains exactly 3 times as many drums as batch W. Batch W contains 5 drums.",
"ainglish": "quantity(V.drums) = 3× quantity(W.drums); quantity(W.drums) = 5.",
"question": "How many drums are in batch V?",
"options": [
"15 drums",
"8 drums",
"10 drums",
"the quantity is not specified"
],
"answer": "15 drums"
},
{
"id": "inc-06",
"calibration": false,
"settlement_stratum": "increase",
"english": "Batch X contains exactly 4 times as many boxes as batch Y. Batch Y contains 4 boxes.",
"ainglish": "quantity(X.boxes) = 4× quantity(Y.boxes); quantity(Y.boxes) = 4.",
"question": "How many boxes are in batch X?",
"options": [
"8 boxes",
"12 boxes",
"the quantity is not specified",
"16 boxes"
],
"answer": "16 boxes"
},
{
"id": "dec-01",
"calibration": false,
"settlement_stratum": "decrease",
"english": "Batch M contains exactly one-2th as many pears as batch N. Batch N contains 10 pears.",
"ainglish": "quantity(M.pears) = quantity(N.pears)/2; quantity(N.pears) = 10.",
"question": "How many pears are in batch M?",
"options": [
"20 pears",
"8 pears",
"the quantity is not specified",
"5 pears"
],
"answer": "5 pears"
},
{
"id": "dec-02",
"calibration": false,
"settlement_stratum": "decrease",
"english": "Batch G contains exactly one-4th as many planks as batch H. Batch H contains 12 planks.",
"ainglish": "quantity(G.planks) = quantity(H.planks)/4; quantity(H.planks) = 12.",
"question": "How many planks are in batch G?",
"options": [
"3 planks",
"48 planks",
"8 planks",
"the quantity is not specified"
],
"answer": "3 planks"
},
{
"id": "dec-03",
"calibration": false,
"settlement_stratum": "decrease",
"english": "Batch J contains exactly one-3th as many tiles as batch K. Batch K contains 9 tiles.",
"ainglish": "quantity(J.tiles) = quantity(K.tiles)/3; quantity(K.tiles) = 9.",
"question": "How many tiles are in batch J?",
"options": [
"6 tiles",
"the quantity is not specified",
"3 tiles",
"27 tiles"
],
"answer": "3 tiles"
},
{
"id": "dec-04",
"calibration": false,
"settlement_stratum": "decrease",
"english": "Batch S contains exactly one-5th as many ropes as batch T. Batch T contains 15 ropes.",
"ainglish": "quantity(S.ropes) = quantity(T.ropes)/5; quantity(T.ropes) = 15.",
"question": "How many ropes are in batch S?",
"options": [
"3 ropes",
"75 ropes",
"10 ropes",
"the quantity is not specified"
],
"answer": "3 ropes"
},
{
"id": "dec-05",
"calibration": false,
"settlement_stratum": "decrease",
"english": "Batch A contains exactly one-2th as many cups as batch B. Batch B contains 6 cups.",
"ainglish": "quantity(A.cups) = quantity(B.cups)/2; quantity(B.cups) = 6.",
"question": "How many cups are in batch A?",
"options": [
"the quantity is not specified",
"3 cups",
"12 cups",
"4 cups"
],
"answer": "3 cups"
},
{
"id": "dec-06",
"calibration": false,
"settlement_stratum": "decrease",
"english": "Batch C contains exactly one-6th as many nails as batch D. Batch D contains 18 nails.",
"ainglish": "quantity(C.nails) = quantity(D.nails)/6; quantity(D.nails) = 18.",
"question": "How many nails are in batch C?",
"options": [
"12 nails",
"the quantity is not specified",
"3 nails",
"108 nails"
],
"answer": "3 nails"
}
],
"models": [
"spark-zen-13-minimal"
],
"readers": [
{
"name": "spark-zen-13-minimal",
"provider": "opencode-zen",
"model": "muse-spark-1.3-contributor-free",
"api": "responses",
"base_url": "https://opencode.ai/zen/v1",
"model_digest": null,
"digest_source": "provider-opaque",
"instrument_preparation": {
"entry_point": "prepare_reader_instruments",
"binding": "provider-opaque"
},
"answer_protocol": "opaque-choice-v1",
"max_tokens": 1024,
"timeout_s": 120,
"temperature": null,
"seed": "provider-default",
"top_p": "provider-default",
"top_k": "provider-default",
"num_ctx": "provider-default",
"reasoning_effort": "minimal"
}
],
"instrument_preparation": {
"entry_point": "prepare_reader_instruments",
"binding": [
{
"reader": "spark-zen-13-minimal",
"digest_source": "provider-opaque"
}
]
},
"item_counts": {
"real": 12,
"calibration": 4
},
"interval_kind": "bootstrap_items",
"interval_estimator": {
"kind": "ainglish.panel.bootstrap-items-attestation.v1",
"algorithm": "sha256-counter-modulo-v1",
"draws": 2000,
"sampling_unit": "item",
"quantiles": [
"0.025",
"0.975"
],
"items_index_sha256": "3cef9ed436dbd7aba8934254b7152145e6c3bdecb63e23108d81be09de4910e1"
},
"settlement_strata": [
{
"id": "increase",
"weight": 1
},
{
"id": "decrease",
"weight": 1
}
],
"settlement_item_field": "settlement_stratum",
"settlement_rule": "manifest-weighted arms and value; every stratum load-bearing",
"calibration": {
"planted_arm": "ainglish",
"min_gap": 0.125,
"min_recovered": 0.5,
"rule": "headroom-relative-v1",
"ordering": "calibration-first",
"arm_exposure": "both-arms-per-reader-item",
"cells": 8
},
"difficulty": {
"annotated": false
},
"harness": "ainglish-panel/0.2.51",
"transport": {
"spark-zen-13-minimal": {
"max_tokens": 1024,
"timeout_s": 120,
"temperature": null,
"seed": "provider-default",
"top_p": "provider-default",
"top_k": "provider-default",
"num_ctx": "provider-default",
"reasoning_effort": "minimal"
}
},
"concurrency": {
"max_in_flight": 1,
"per_reader_max_in_flight": {
"spark-zen-13-minimal": 1
},
"result_order": "deterministic-plan-order",
"calibration_barrier": true,
"automatic_retries": false
},
"transport_faults": {
"total": 0,
"retried": false,
"per_cell": []
},
"transport_truncations": {
"total": 0,
"per_reader_cell": [],
"by_cell": {
"english": 0,
"ainglish": 0
},
"imbalanced_across_cells": false
},
"protocol": "panel.py counterbalanced real arms + both-arms-per-reader-item planted-effect calibration gate"
}