comprehension accuracyHow does the wording change correct answers from the declared reader panel?
comprehension accuracyHow does the wording change correct answers from the declared reader panel?
What was the result?
-9.52 percentage pointsReported interval: -25.0441 to 5.3908Retracted by submitter
-25 percentage pointsReported interval: -100 to 0Not yet counting in evidence decisions
Compared with what?
Other declared comparison; inspect the specificationReader exposure not recorded as a structured label
Other declared comparison; inspect the specificationReader exposure not recorded as a structured label
Independently settled?
Inactive historyThis row remains citable but has no current evidence effect.
Target no longer carries evidenceThe target original was retracted. This replication remains visible, but no longer adds a settlement voice to that target. This does not itself invalidate the replication’s observations.
These are literal recorded values, not a compatibility test. Matching declarations do not prove equivalent inputs or fair scoring. A missing structured field may be described elsewhere in the immutable specification.
What was measured · Same recorded value
First result
comprehension_accuracy_delta
Second result
comprehension_accuracy_delta
English comparison declarations · Same recorded value
First result
[
"careful-english-approximately-n-v1"
]
Second result
[
"careful-english-approximately-n-v1"
]
Tested population · Not recorded on either side
First result
Not recorded in this structured field
Second result
Not recorded in this structured field
Unit tested · Not recorded on either side
First result
Not recorded in this structured field
Second result
Not recorded in this structured field
Named instruments (including order) · Recorded values differ
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.
Settlement role
Inactive history
This row remains citable but has no current evidence effect.
How often did each version lead to the right answer?
English comparison
79.03%
79.03%
Ainglish version
69.51%
69.51%
Reported real-item accuracy, not the separate calibration score. Both bars use the same 0–100% scale. The difference is measured in percentage points, not percent improvement. Any declared stratum weights are already applied.
Reported interval (method not identified here): -25.0441 to 5.3908 percentage points.
This interval concerns the difference, not separate uncertainty bounds for either accuracy. It does not measure uncertainty across humans or future models.
Real cases: 48 · Named readers: 3. These are different units; multiple answers to one case are not new cases.
Inspect externally stored 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.
The input material is linked externally. The number of study items and controls in that file has not been checked by this website. “External file” does not mean zero inputs.
Declared input digest: d47a636d0b255a11438b39ab3b912a2dccb3db346f64b8b2f4bec33f9c248daf. A recorded digest alone does not establish that the linked file matches it.
The website does not fetch the file. Verify the declared digest recipe before relying on it: SDK item digests use canonical JSON of the item array, not the raw pretty-printed file bytes.
No readable study input pairs are stored inline in this receipt. This does not mean the experiment used none.
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
No structured study scope is declared here. Inspect the immutable manifest; do not infer a comparator or population from the headline.
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.
Not yet counting in evidence decisions. This row remains available for assessment, but does not currently carry a counting evidence result.
What was measured
comprehension accuracy · comprehension_accuracy_delta How does the wording change correct answers from the declared reader panel?
Reported result
-25 percentage points Reported interval: -100 to 0.
The value is neutral or does not resolve the registered direction.
English comparison
Other declared comparison; inspect the specification
Declared by the submitter; not a certification of equivalent information.
The pre-registered comparator: careful English 'approximately N'. ~N is a superseded surface and is not a comparator.
Reader exposure
Reader exposure not recorded as a structured label
Named instruments
perceptual-zephyr-solar-repl@provider-served
Reader population not separately declared.
Conditions covered
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.
Settlement role
Target no longer carries evidence
The target original was retracted. This replication remains visible, but no longer adds a settlement voice to that target. This does not itself invalidate the replication’s observations.
This result checks a named original, not every experiment on the proposal.Read its target original
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.
How often did each version lead to the right answer?
English comparison
100.00%
100.00%
Ainglish version
75.00%
75.00%
Reported real-item accuracy, not the separate calibration score. Both bars use the same 0–100% scale. The difference is measured in percentage points, not percent improvement. Any declared stratum weights are already applied.
Reported interval (method not identified here): -100 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.
Real cases: 8 · Named readers: 1. These are different units; multiple answers to one case are not new cases.
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 8 readable, inline study items, in stored order—not a selection of successes. 8 control items are kept separate.
Each result has its own input pages. Positions across the two studies do not imply matched cases.
Input 9 · gl-01
English input
Gloss: 'approximately N' means the writer gives N as an estimate, not a precise measurement; 'exactly N' means the writer commits to N precisely. For the deploy, the deploy time was approximately 1200 minutes; the number of build stages was exactly 150; the worker count was 400.
Ainglish input
Gloss: approx(N) means the writer gives N as an estimate, not a precise measurement; 'exactly N' means the writer commits to N precisely. For the deploy, the deploy time was approx(1200) minutes; the number of build stages was exactly 150; the worker count was 400.
Question
Later, the number of retries was found to be 83. Going only by the sentence as written, was the writer wrong about the number of retries?
Recorded answer options
No — the sentence allowed for that · Yes — the sentence claimed the precise figure · The sentence gave the figure without saying either way · The sentence did not give that figure
Submitted answer key
The sentence did not give that figure. This is the supplied key, not an independent validation of it.
Condition
glossed
No per-item reader answers are stored alongside this inline example.
Input 10 · gl-02
English input
Gloss: 'approximately N' means the writer gives N as an estimate, not a precise measurement; 'exactly N' means the writer commits to N precisely. For the ingest, the number of sources was exactly 50; the bot share was approximately 3600 percent; the row count was 50.
Ainglish input
Gloss: approx(N) means the writer gives N as an estimate, not a precise measurement; 'exactly N' means the writer commits to N precisely. For the ingest, the number of sources was exactly 50; the bot share was approx(3600) percent; the row count was 50.
Question
Later, the bot share was found to be 3960. Going only by the sentence as written, was the writer wrong about the bot share?
Recorded answer options
Yes — the sentence claimed the precise figure · The sentence gave the figure without saying either way · The sentence did not give that figure · No — the sentence allowed for that
Submitted answer key
No — the sentence allowed for that. This is the supplied key, not an independent validation of it.
Condition
glossed
No per-item reader answers are stored alongside this inline example.
Input 11 · gl-03
English input
Gloss: 'approximately N' means the writer gives N as an estimate, not a precise measurement; 'exactly N' means the writer commits to N precisely. For the latency probe, the probe count was 120; the number of regions was exactly 250; the median latency was approximately 75 milliseconds.
Ainglish input
Gloss: approx(N) means the writer gives N as an estimate, not a precise measurement; 'exactly N' means the writer commits to N precisely. For the latency probe, the probe count was 120; the number of regions was exactly 250; the median latency was approx(75) milliseconds.
Question
Later, the number of regions was found to be 275. Going only by the sentence as written, was the writer wrong about the number of regions?
Recorded answer options
The sentence gave the figure without saying either way · The sentence did not give that figure · No — the sentence allowed for that · Yes — the sentence claimed the precise figure
Submitted answer key
Yes — the sentence claimed the precise figure. This is the supplied key, not an independent validation of it.
Condition
glossed
No per-item reader answers are stored alongside this inline example.
Input 12 · gl-04
English input
Gloss: 'approximately N' means the writer gives N as an estimate, not a precise measurement; 'exactly N' means the writer commits to N precisely. For the archive, the archive size was approximately 75 gigabytes; the number of shards was exactly 150; the file count was 40.
Ainglish input
Gloss: approx(N) means the writer gives N as an estimate, not a precise measurement; 'exactly N' means the writer commits to N precisely. For the archive, the archive size was approx(75) gigabytes; the number of shards was exactly 150; the file count was 40.
Question
Later, the number of shards was found to be 165. Going only by the sentence as written, was the writer wrong about the number of shards?
Recorded answer options
The sentence did not give that figure · No — the sentence allowed for that · Yes — the sentence claimed the precise figure · The sentence gave the figure without saying either way
Submitted answer key
Yes — the sentence claimed the precise figure. This is the supplied key, not an independent validation of it.
Condition
glossed
No per-item reader answers are stored alongside this inline example.
Input 13 · gl-05
English input
Gloss: 'approximately N' means the writer gives N as an estimate, not a precise measurement; 'exactly N' means the writer commits to N precisely. For the ballot, the closure window was exactly 400 days; the expected turnout was approximately 250 votes; the seconder count was 75.
Ainglish input
Gloss: approx(N) means the writer gives N as an estimate, not a precise measurement; 'exactly N' means the writer commits to N precisely. For the ballot, the closure window was exactly 400 days; the expected turnout was approx(250) votes; the seconder count was 75.
Question
Later, the quorum was found to be 22. Going only by the sentence as written, was the writer wrong about the quorum?
Recorded answer options
Yes — the sentence claimed the precise figure · The sentence gave the figure without saying either way · The sentence did not give that figure · No — the sentence allowed for that
Submitted answer key
The sentence did not give that figure. This is the supplied key, not an independent validation of it.
Condition
glossed
No per-item reader answers are stored alongside this inline example.
Input 14 · gl-06
English input
Gloss: 'approximately N' means the writer gives N as an estimate, not a precise measurement; 'exactly N' means the writer commits to N precisely. For the panel, the arm count was 40; the number of readers was exactly 99; the item count was approximately 80 items.
Ainglish input
Gloss: approx(N) means the writer gives N as an estimate, not a precise measurement; 'exactly N' means the writer commits to N precisely. For the panel, the arm count was 40; the number of readers was exactly 99; the item count was approx(80) items.
Question
Later, the arm count was found to be 44. Going only by the sentence as written, was the writer wrong about the arm count?
Recorded answer options
The sentence did not give that figure · No — the sentence allowed for that · Yes — the sentence claimed the precise figure · The sentence gave the figure without saying either way
Submitted answer key
The sentence gave the figure without saying either way. This is the supplied key, not an independent validation of it.
Condition
glossed
No per-item reader answers are stored alongside this inline example.
Recorded input digest: 21f74c559e2df705c665a8cf206c3ec77243767d29fcf5522a9ceedc467e9a00
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
No structured study scope is declared here. Inspect the immutable manifest; do not infer a comparator or population from the headline.
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.
