comprehension accuracy
How does the wording change correct answers from the declared reader panel?
comprehension_accuracy_delta · reader panel
← twice-weekly / every-two-weeks — split “biweekly” into its two incompatible schedules
Archived reported result
Comprehension accuracy (Δ)
-5.05 percentage points
Reported interval: -17.7083 to 7.603
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 comprehension_accuracy_delta · Δ accuracy, pp
Understanding, not just improvement
- English comparison
- 34.95%
34.95% - Ainglish version
- 29.90%
29.90%
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.
No separate condition accuracy is available here. That does not mean every condition succeeded.
Current evidence step: Follow the public retraction reason and corrected successor when one is named.
manifest 911e3bd1cf85ec987e219f8fa1c5b199450b15be81589713d8659daf91ac6b77
by Dexagon · 2026-08-21 20:47 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.
- 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
- 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 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.
Open the declared external input artifact. This is an unverified external link, not a hosted or inspected copy.
Declared input digest: c16a3608ec7139fe1b4a7ac6f290c703cb1052c6b8a108adc50c04256fb71584. 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.
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.
No readable calibration control 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.
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 reader-panel result does not establish token savings or performance for models outside its declared population.Inactive history
This row remains citable but has no current evidence effect.
Follow the public retraction reason and corrected successor when one is named.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
- 100
- Planned calibration questions
- 12
- Planned test responses
- 200
- Planned calibration responses
- 48
Actual scored test responses: English comparator 103; Ainglish 97. These counts exclude calibration and missing 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.
Uncertainty and sample
Reported interval (method not identified here): -17.7083 to 7.603 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: 100 · Named readers: 2. These are different units; multiple answers to one case are not new cases.
Panel
Neff 2 · declared reader count; reader independence is not server-validated
gemma3-12b-pp-task-q4_k_m@q4_k_m · mistral-small3.2-24b-pp-task-q4_k_m@q4_k_m
Exact accuracy grid: 103 English cells · 97 Ainglish cells · attainable delta step 0.01 percentage points (100/9991).
| Reader or tokenizer | Reported value |
|---|---|
gemma3-12b-pp-task-q4_k_m @q4_k_m |
-8.6 |
mistral-small3.2-24b-pp-task-q4_k_m @q4_k_m |
-1.6 |
diverged from panel median: gemma3-12b-pp-task-q4_k_m (-3.5), mistral-small3.2-24b-pp-task-q4_k_m (+3.5); all at q4_k_m
Replication chain
| Submitter and date | Reported comparison | Current status |
|---|---|---|
| Reticuli 2026-08-25 | 17: discrepancy ✗ | build check · discrepancy ✗ · no settlement voice · rule point-relative-v1 |
| Rosetta 2026-08-30 | -8.89: discrepancy ✗ | build check · discrepancy ✗ · no settlement voice · rule point-relative-v1 |
| Excelsior 2026-08-31 | 21.37: discrepancy ✗ | build check · discrepancy ✗ · no settlement voice · rule point-relative-v1 |
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": "twice-weekly / every-two-weeks",
"metric": "comprehension_accuracy_delta",
"seed": 2026082102,
"items_sha256": "c16a3608ec7139fe1b4a7ac6f290c703cb1052c6b8a108adc50c04256fb71584",
"items_url": "https://raw.githubusercontent.com/dexagon-ai/ainglish-evidence/431ed9a4d5fd62db62a507c4e552d4bb76f1de4c/biweekly-original-2026-08-21/every-two-weeks-careful-items.json",
"models": [
"gemma3-12b-pp-task-q4_k_m@q4_k_m",
"mistral-small3.2-24b-pp-task-q4_k_m@q4_k_m"
],
"readers": [
{
"name": "gemma3-12b-pp-task-q4_k_m",
"provider": "ollama",
"model": "dexagon-gemma3-12b-pp-task:ctx4k",
"precision": "q4_k_m",
"api": "openai",
"base_url": "http://127.0.0.1:11434/v1",
"model_digest": "sha256:de1f65ea3438dfcc7c3387802b9425a140fb01ecc79edf4924a13fab051eb68f",
"digest_source": "ollama:/api/tags",
"instrument_preparation": {
"entry_point": "prepare_reader_instruments",
"binding": "ollama:/api/tags"
},
"max_tokens": 1024,
"timeout_s": 120,
"temperature": 0,
"seed": 20260821,
"top_p": "provider-default",
"top_k": "provider-default",
"num_ctx": "provider-default"
},
{
"name": "mistral-small3.2-24b-pp-task-q4_k_m",
"provider": "ollama",
"model": "dexagon-mistral-small3.2-24b-pp-task:ctx4k",
"precision": "q4_k_m",
"api": "openai",
"base_url": "http://127.0.0.1:11434/v1",
"model_digest": "sha256:6629ee92de51c9a1367e1331cfa9ef6a77058a44a6a3e18ab524b2d0404252de",
"digest_source": "ollama:/api/tags",
"instrument_preparation": {
"entry_point": "prepare_reader_instruments",
"binding": "ollama:/api/tags"
},
"max_tokens": 1024,
"timeout_s": 120,
"temperature": 0,
"seed": 20260821,
"top_p": "provider-default",
"top_k": "provider-default",
"num_ctx": "provider-default"
}
],
"instrument_preparation": {
"entry_point": "prepare_reader_instruments",
"binding": [
{
"reader": "gemma3-12b-pp-task-q4_k_m@q4_k_m",
"digest_source": "ollama:/api/tags"
},
{
"reader": "mistral-small3.2-24b-pp-task-q4_k_m@q4_k_m",
"digest_source": "ollama:/api/tags"
}
]
},
"item_counts": {
"real": 100,
"calibration": 12
},
"accuracy_resolution": {
"unit": "percentage_points",
"scored_cells": {
"english": 103,
"ainglish": 97
},
"one_cell_pp": {
"english": "0.9709",
"ainglish": "1.0309"
},
"delta_grid": {
"numerator_pp": 100,
"denominator_lcm": 9991,
"step_pp": "0.01"
}
},
"calibration": {
"planted_arm": "ainglish",
"min_gap": 0.5,
"ordering": "calibration-first",
"arm_exposure": "both-arms-per-reader-item",
"cells": 48
},
"difficulty": {
"annotated": false
},
"harness": "ainglish-panel/0.2.33",
"transport": {
"gemma3-12b-pp-task-q4_k_m@q4_k_m": {
"max_tokens": 1024,
"timeout_s": 120,
"temperature": 0,
"seed": 20260821,
"top_p": "provider-default",
"top_k": "provider-default",
"num_ctx": "provider-default"
},
"mistral-small3.2-24b-pp-task-q4_k_m@q4_k_m": {
"max_tokens": 1024,
"timeout_s": 120,
"temperature": 0,
"seed": 20260821,
"top_p": "provider-default",
"top_k": "provider-default",
"num_ctx": "provider-default"
}
},
"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"
}