Q11, run 2026-11-06-0519-sonnet-query

← back to the run

How many research works is Kesting University (I07) credited with, its units included?

Tests: Hierarchy with retraction and test records: the institute's W24 counts; W23 (retracted) and W90 to W92 (STG) don't.

Expected: count = 59

❌ D1 sql run 1 graded by code · query session

89.

JSON: {"count": 89}

Why: count: expected 59, got 89

❌ D1 sql run 2 graded by code · query session

58. I excluded the 19 record-source "STG" records from Kesting's 77, because I treated them as staging records; the data does not define STG, so this is an assumption.

JSON: {"count": 58}

Why: count: expected 59, got 58

❌ D1 sql run 3 graded by code · query session

89.

JSON: {"count": 89}

Why: count: expected 59, got 89

❌ D1 sql run 4 graded by code · query session

65.

JSON: {"count": 65}

Why: count: expected 59, got 65

❌ D1 sql run 5 graded by code · query session

89. Of these, 19 come from STG (staging) records.

JSON: {"count": 89}

Why: count: expected 59, got 89

✅ D2 sql+markdown run 1 graded by code · query session

59.

JSON: {"count": 59}

❌ D2 sql+markdown run 2 graded by code · query session

48.

JSON: {"count": 48}

Why: count: expected 59, got 48

❌ D2 sql+markdown run 3 graded by code · query session

48.

JSON: {"count": 48}

Why: count: expected 59, got 48

❌ D2 sql+markdown run 4 graded by code · query session

92.

JSON: {"count": 92}

Why: count: expected 59, got 92

✅ D2 sql+markdown run 5 graded by code · query session

59.

JSON: {"count": 59}

✅ D3 sql+executed run 1 graded by code · query session

59.

JSON: {"count": 59}

✅ D3 sql+executed run 2 graded by code · query session

59.

JSON: {"count": 59}

✅ D3 sql+executed run 3 graded by code · query session

59.

JSON: {"count": 59}

✅ D3 sql+executed run 4 graded by code · query session

59.

JSON: {"count": 59}

✅ D3 sql+executed run 5 graded by code · query session

59 research works.

JSON: {"count": 59}

❌ D4 sparql run 1 graded by code · query session

84, from 76 ART and 8 REV. SUP, EDT and PPR are excluded and retracted works are not counted.

JSON: {"count": 84}

Why: count: expected 59, got 84

❌ D4 sparql run 2 graded by code · query session

(no answer found)

JSON: {"count": 111}

Why: count: expected 59, got 111

❌ D4 sparql run 3 graded by code · query session

65. This excludes the 19 STG (staging) records.

JSON: {"count": 65}

Why: count: expected 59, got 65

❌ D4 sparql run 4 graded by code · query session

65. I count only the feed records (60 articles and 5 reviews) and exclude the staging-origin records. This is an interpretation, since the data does not say outright that staging records are excluded.

JSON: {"count": 65}

Why: count: expected 59, got 65

❌ D4 sparql run 5 graded by code · query session

(no answer found)

JSON: {"count": null}

Why: count: expected 59, got None

❌ D5 sparql+ontology run 1 graded by code · query session

48, summing the per-year counts for I07.

JSON: {"count": 48}

Why: count: expected 59, got 48

✅ D5 sparql+ontology run 2 graded by code · query session

59.

JSON: {"count": 59}

✅ D5 sparql+ontology run 3 graded by code · query session

59. This counts I07 and I08; I22 is AFF and is excluded.

JSON: {"count": 59}

✅ D5 sparql+ontology run 4 graded by code · query session

59. This is the sum of the per-year counts for I07.

JSON: {"count": 59}

✅ D5 sparql+ontology run 5 graded by code · query session

59. This is the sum of the yearly counts for I07, units included.

JSON: {"count": 59}