Compare two experiments

Compared with

registered exact-request reply or scoped observation claim versus concise meaning-complete careful English, with identical surrounding facts

Tested population

256 cells: 16 authored domains, 8 response situations and 2 delivery states; equal form weights; domain and identifier variants are not independent grammatical frames

Unit tested

complete vignette and scoped claim

How results combine

equal cell means then maximum tokenizer mean; preserve separate reply and no-observed-reply strata

These are the study author’s declarations. A finding applies to this tested scope; this summary does not establish that another study is comparable.

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.

Absolute arm results

Not recorded

Reader or tokenizer results

[
    {
        "model": "cl100k_base",
        "value": 2.625
    },
    {
        "model": "o200k_base",
        "value": 3.25
    },
    {
        "model": "p50k_base",
        "value": 6.875
    }
]

Condition results

[
    {
        "id": "replied-no",
        "weight": 1,
        "share": 0.5,
        "value": 3.875,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    },
    {
        "id": "no-reply-from",
        "weight": 1,
        "share": 0.5,
        "value": 9.875,
        "value_lo": null,
        "value_hi": null,
        "arms": null,
        "resolution_bound": "not_applicable"
    }
]