comprehension accuracy
How does the wording change correct answers from the declared reader panel?
comprehension_accuracy_delta · reader panel
Measurement result
Comprehension accuracy (Δ)
46.965 percentage points
Reported interval: 35.8333 to 59.4444
Server-replayed item bootstrap ·
72 items ·
72 scored/dead cells ·
receipt 1599c1d5561d….
The complete attestation is in the JSON record.
The result is on the helpful side of this metric's neutral point.
Protocol key comprehension_accuracy_delta · Δ accuracy, pp
Understanding, not just improvement
- English comparison
- 53.04%
53.04% - 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:
doer-live: 100.00%, compared with English 40.00%; doer-clash: 100.00%, compared with English 100.00%; done-to-live: 100.00%, compared with English 12.50%. 3 other conditions share that Ainglish score.
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
8fe64c3dfdf8a6e58ff8a7935e15658bb18be289d4b7f31f93a5fb96ecd9bd52manifest 422b3540b59289277d0e23982f7264973e692da750670601ffbcaafc8a0ab175
by Morgan · 2026-09-11 21:41 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
- Other declared comparison; inspect the specification
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 6 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: bare-role-ambiguous-english-v1
The same fresh frame with the role-completing words removed. The frozen ledger fixes the intended role; exact recovery is scored against that intent.
Exposure label: Not recorded
Reader population: Not recorded
Conditions: doer-live · doer-clash · done-to-live · done-to-clash · full-live · full-clash
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.
An external input location was declared, but it is not a safe HTTPS link this view can display. Inspect the retained specification; the missing link does not establish that there were no inputs.
No readable study input pairs are stored inline in this receipt. This does not mean the experiment used none.
Recorded input digest: 73fdf17661e5d3eb9fe4834863e69846fc05c3e5e5a6ecff98423370e15fc8bf
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
Supports
The value falls on the registered helpful side of this metric’s neutral point.
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.Uncertainty and sample
Reported item-bootstrap interval: 35.8333 to 59.4444 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: 72 · 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 |
|---|---|---|---|---|
doer-live | 60 | Not recorded | 40.00% | 100.00% |
doer-clash | 0 | Not recorded | 100.00% | 100.00% |
done-to-live | 87.5 | Not recorded | 12.50% | 100.00% |
done-to-clash | 14.29 | Not recorded | 85.71% | 100.00% |
full-live | 20 | Not recorded | 80.00% | 100.00% |
full-clash | 100 | Not recorded | 0.00% | 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
big-pickle-opaque-choice-zen
no per-member results declared — divergence structure NOT COMPUTED (aggregate only)
Replication chain
This row is itself a replication of 8fe64c3dfdf8….
No replications yet. This measurement is testimony until a party disjoint from Morgan re-runs the manifest within tolerance (rel 0.1 / abs 0.02).
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": "complete-the-comparative — explicit rival grammatical role",
"metric": "comprehension_accuracy_delta",
"seed": 2026091112,
"comparator": {
"kind": "bare-role-ambiguous-english-v1",
"description": "The same fresh frame with the role-completing words removed. The frozen ledger fixes the intended role; exact recovery is scored against that intent."
},
"items_sha256": "73fdf17661e5d3eb9fe4834863e69846fc05c3e5e5a6ecff98423370e15fc8bf",
"items_url": "/home/morgan/artifacts/complete-comparative/items.json",
"models": [
"big-pickle-opaque-choice-zen"
],
"readers": [
{
"name": "big-pickle-opaque-choice-zen",
"provider": "opencode-zen",
"model": "opencode/big-pickle",
"api": "anthropic",
"base_url": "https://opencode.ai/zen/v1",
"model_digest": null,
"digest_source": "unbound",
"model_catalog": "openai:/models",
"instrument_preparation": {
"entry_point": "not-prepared",
"binding": "unbound"
},
"answer_protocol": "opaque-choice-v1",
"max_tokens": 64,
"timeout_s": 300,
"temperature": null,
"seed": "provider-default",
"top_p": "provider-default",
"top_k": "provider-default",
"num_ctx": "provider-default",
"reasoning_effort": "provider-default"
}
],
"instrument_preparation": {
"entry_point": "run_panel(custom ask_fn)",
"binding": "unbound"
},
"item_counts": {
"real": 72,
"calibration": 8
},
"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": "2eb97b145e759027207e19acf24de1d88620eba1444fa5ccfbd583b8190f21ac"
},
"settlement_strata": [
{
"id": "doer-live",
"weight": 1
},
{
"id": "doer-clash",
"weight": 1
},
{
"id": "done-to-live",
"weight": 1
},
{
"id": "done-to-clash",
"weight": 1
},
{
"id": "full-live",
"weight": 1
},
{
"id": "full-clash",
"weight": 1
}
],
"settlement_item_field": "settlement_stratum",
"settlement_rule": "manifest-weighted arms and value; every stratum load-bearing",
"calibration": {
"planted_arm": "ainglish",
"min_gap": 0.5,
"min_recovered": 0.5,
"rule": "headroom-relative-v1",
"ordering": "calibration-first",
"arm_exposure": "both-arms-per-reader-item",
"cells": 16
},
"difficulty": {
"annotated": false
},
"harness": "ainglish-panel/0.2.60",
"transport": {
"big-pickle-opaque-choice-zen": {
"max_tokens": 64,
"timeout_s": 300,
"temperature": null,
"seed": "provider-default",
"top_p": "provider-default",
"top_k": "provider-default",
"num_ctx": "provider-default",
"reasoning_effort": "provider-default"
}
},
"concurrency": {
"max_in_flight": 1,
"per_reader_max_in_flight": {
"big-pickle-opaque-choice-zen": 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",
"replicates_hash": "8fe64c3dfdf8a6e58ff8a7935e15658bb18be289d4b7f31f93a5fb96ecd9bd52"
}