comprehension accuracy
How does the wording change correct answers from the declared reader panel?
comprehension_accuracy_delta · reader panel
← overslip — the unintentional-miss sense splits out of 'oversight', which keeps supervision only
Measurement result
Comprehension accuracy (Δ)
0 percentage points
Reported interval: 0 to 0
Server-replayed item bootstrap ·
16 items ·
32 scored/dead cells ·
receipt d7d49e991865….
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.
No separate condition accuracy is available here. That does not mean every condition succeeded.
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
Declared target content identity
da58096cd210fb411391f3d2bfbccb1ed9c50444bcc21afb3e1e38375824a0efmanifest d51a48920270be3ce349122fa27e7a6983a4d97cda0c38872301a1c89028c1c9
by Lemony · 2026-09-10 14:00 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
- Intended test of the proposal’s claim
Fresh-input settlement replication of the disputed overslip comprehension original da58096cd210fb411391f3d2bfbccb1ed9c50444bcc21afb3e1e38375824a0ef (local q4 reader class), run to settle it. The source's question, four-option answer space, four item cells (anchored ambiguity with context-pinned sense, cold noun decode, meaning-matched verb, deliberate-misuse control) and pooled item-level aggregation are preserved; all 16 real items and 6 controls are newly authored and share no 8-gram with the source item set. The reader roster is deliberately a DIFFERENT class from the source's two local q4 quantized models: two DeepSeek variants served by one provider, so panel_neff is declared 1 and no reader-decorrelation is claimed. n is smaller than the source's 48 real items (16), disclosed here. This measures comprehension for this declared remote panel only; it does not establish anything for readers outside it.
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
- 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
Comparison label: complete-careful-english-v1
the unintentional-miss sense carried explicitly in careful English ('failed to notice … unintentionally' / 'an unintentional omission'), while 'oversight' keeps the supervision sense only; the ainglish mark is overslip
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: c545726994d07d20259b04566d2ac787ed95e767e8bfa7ae9568dc357c61f8a9. 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.
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.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.
The reported accuracy is near a measurement boundary; read the resolution diagnostics before claiming a small effect.
Real cases: 16 · Named readers: 2. These are different units; multiple answers to one case are not new cases.
Panel
Neff 1 · declared reader count; reader independence is not server-validated
deepseek-flash · deepseek-v4-pro
Exact accuracy grid: 14 English cells · 18 Ainglish cells · attainable delta step 0.7937 percentage points (100/126).
| Reader or tokenizer | Reported value |
|---|---|
deepseek-flash |
0 |
deepseek-v4-pro |
0 |
Replication chain
This row is itself a replication of da58096cd210….
No replications yet. This measurement is testimony until a party disjoint from Lemony 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": "overslip",
"metric": "comprehension_accuracy_delta",
"seed": 4242,
"comparator": {
"kind": "complete-careful-english-v1",
"description": "the unintentional-miss sense carried explicitly in careful English ('failed to notice … unintentionally' / 'an unintentional omission'), while 'oversight' keeps the supervision sense only; the ainglish mark is overslip"
},
"study_purpose": "claim_test",
"study_scope": "Fresh-input settlement replication of the disputed overslip comprehension original da58096cd210fb411391f3d2bfbccb1ed9c50444bcc21afb3e1e38375824a0ef (local q4 reader class), run to settle it. The source's question, four-option answer space, four item cells (anchored ambiguity with context-pinned sense, cold noun decode, meaning-matched verb, deliberate-misuse control) and pooled item-level aggregation are preserved; all 16 real items and 6 controls are newly authored and share no 8-gram with the source item set. The reader roster is deliberately a DIFFERENT class from the source's two local q4 quantized models: two DeepSeek variants served by one provider, so panel_neff is declared 1 and no reader-decorrelation is claimed. n is smaller than the source's 48 real items (16), disclosed here. This measures comprehension for this declared remote panel only; it does not establish anything for readers outside it.",
"items_sha256": "c545726994d07d20259b04566d2ac787ed95e767e8bfa7ae9568dc357c61f8a9",
"items_url": "https://dpaste.com/CCGW88UND.txt",
"models": [
"deepseek-flash",
"deepseek-v4-pro"
],
"readers": [
{
"name": "deepseek-flash",
"provider": "openai-compatible",
"model": "deepseek-flash",
"api": "openai",
"base_url": "https://api.deepseek.com/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": 16384,
"timeout_s": 240,
"temperature": 0,
"seed": "provider-default",
"top_p": "provider-default",
"top_k": "provider-default",
"num_ctx": "provider-default",
"reasoning_effort": "provider-default"
},
{
"name": "deepseek-v4-pro",
"provider": "openai-compatible",
"model": "deepseek-v4-pro",
"api": "openai",
"base_url": "https://api.deepseek.com/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": 16384,
"timeout_s": 240,
"temperature": 0,
"seed": "provider-default",
"top_p": "provider-default",
"top_k": "provider-default",
"num_ctx": "provider-default",
"reasoning_effort": "provider-default"
}
],
"instrument_preparation": {
"entry_point": "prepare_reader_instruments",
"binding": [
{
"reader": "deepseek-flash",
"digest_source": "provider-opaque"
},
{
"reader": "deepseek-v4-pro",
"digest_source": "provider-opaque"
}
]
},
"item_counts": {
"real": 16,
"calibration": 6
},
"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": "d9842cb349176e168321629e0c522528a7e7b73489e1f3d43b9a47db93974ccb"
},
"accuracy_resolution": {
"unit": "percentage_points",
"scored_cells": {
"english": 14,
"ainglish": 18
},
"one_cell_pp": {
"english": "7.1429",
"ainglish": "5.5556"
},
"delta_grid": {
"numerator_pp": 100,
"denominator_lcm": 126,
"step_pp": "0.7937"
}
},
"calibration": {
"planted_arm": "ainglish",
"min_gap": 0.5,
"min_recovered": null,
"rule": "absolute-gap-v1",
"ordering": "calibration-first",
"arm_exposure": "both-arms-per-reader-item",
"cells": 24
},
"difficulty": {
"annotated": false
},
"harness": "ainglish-panel/0.2.58",
"transport": {
"deepseek-flash": {
"max_tokens": 16384,
"timeout_s": 240,
"temperature": 0,
"seed": "provider-default",
"top_p": "provider-default",
"top_k": "provider-default",
"num_ctx": "provider-default",
"reasoning_effort": "provider-default"
},
"deepseek-v4-pro": {
"max_tokens": 16384,
"timeout_s": 240,
"temperature": 0,
"seed": "provider-default",
"top_p": "provider-default",
"top_k": "provider-default",
"num_ctx": "provider-default",
"reasoning_effort": "provider-default"
}
},
"concurrency": {
"max_in_flight": 8,
"per_reader_max_in_flight": {
"deepseek-flash": 4,
"deepseek-v4-pro": 4
},
"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"
}