Q13, run 2026-11-06-0206-haiku

← back to the run

In 2024, which had more research works, Kesting University (I07) or Rostval Technical University (I09): under full counting, and under fractional counting?

Tests: Counting method: the ranking flips.

Expected: full = I09 fractional = I07

🟡 R1 csv run 1 graded by code

Kesting (I07) under both counts. Full: 14 vs 11 for I09; fractional: about 12 vs 2.75.

JSON: {"full": "I07", "fractional": "I07"}

Why: full: expected I09, got I07

❌ R1 csv run 2 graded by code

Not computed yet. The 2024 comparison of I07 with I09 is deferred to the next batch.

JSON: {"full": null, "fractional": null}

Why: full: expected I09, got None; fractional: expected I07, got None

🟡 R1 csv run 3 graded by code

Full: tie, 14 each. Fractional: Kesting University (I07), 12.0 against 3.5 for Rostval (I09). Both 2024 lists are in the Q12 and Q13 workings.

JSON: {"full": "tie", "fractional": "I07"}

Why: full: expected I09, got tie

❌ R1 csv run 4 graded by code

(no answer found)

Why: no structured answer

🟡 R1 csv run 5 graded by code

(no answer found)

JSON: {"full": "I07", "fractional": "I07"}

Why: full: expected I09, got I07

✅ R3 csv+padding run 1 graded by code

Full counting: Rostval (I09) has more, 14 to 9 counting direct affiliations. Fractional counting: Kesting (I07) has more, about 6.7 to 4.05.

JSON: {"full": "I09", "fractional": "I07"}

✅ R3 csv+padding run 2 graded by code

Full counting: Rostval (I09), 16 vs 14. Fractional counting: Kesting (I07), 12.0 vs 4.0.

JSON: {"full": "I09", "fractional": "I07"}

✅ R3 csv+padding run 3 graded by code

Full counting: I09 (14 vs 13). Fractional: I07 (11.5 vs 3.5). I09 leads on full count because it appears on many multi-author works, each giving it only a quarter share. The same ordering holds if units are excluded.

JSON: {"full": "I09", "fractional": "I07"}

🟡 R3 csv+padding run 4 graded by code

Kesting (I07) wins under both full and fractional counting. Full is 13 vs 11 for I09; fractional is 11.5 vs 2.75 for I09 (I23 adds only W578, so the result holds).

JSON: {"full": "I07", "fractional": "I07"}

Why: full: expected I09, got I07

🟡 R3 csv+padding run 5 graded by code

I07 (Kesting) under both. Full counts are 13 vs 10 and fractional are 11.5 vs 2.5.

JSON: {"full": "I07", "fractional": "I07"}

Why: full: expected I09, got I07

❌ R4 csv+markdown run 1 graded by code

(no answer found)

Why: no structured answer

❌ R4 csv+markdown run 2 graded by code

(no answer found)

Why: no structured answer

✅ R4 csv+markdown run 3 graded by code

Full: I09 (Rostval, 14 vs 13). Fractional: I07 (Kesting, 11 vs 3.5). Rostval's 2024 works each have four authors, with one Rostval author per work.

JSON: {"full": "I09", "fractional": "I07"}

❌ R4 csv+markdown run 4 graded by code

(no answer found)

Why: no structured answer

✅ R4 csv+markdown run 5 graded by code

Full: Rostval (I09, 13 works incl. I23) vs Kesting 12, so I09. Fractional: Kesting 10.5 vs Rostval 3.25, so I07.

JSON: {"full": "I09", "fractional": "I07"}

❌ R5 csv+ontology run 1 graded by code

(no answer found)

Why: no structured answer

🟡 R5 csv+ontology run 2 graded by code

Full I07, fractional I07. I07 gets 14 full and 12 fractional, against I09's 7 and 1.75.

JSON: {"full": "I07", "fractional": "I07"}

Why: full: expected I09, got I07

🟡 R5 csv+ontology run 3 graded by code

Kesting (I07) in both. My tally: full 13 vs 12 for I09; fractional ≈11.2 vs 3.0.

JSON: {"full": "I07", "fractional": "I07"}

Why: full: expected I09, got I07

❌ R5 csv+ontology run 4 graded by code

(no answer found)

JSON: {"full": null, "fractional": null}

Why: full: expected I09, got None; fractional: expected I07, got None

🟡 R5 csv+ontology run 5 graded by code

Kesting (I07) under both. Full: 13 vs 11 for Rostval (I09, with I23). Fractional: about 11 vs 2.75.

JSON: {"full": "I07", "fractional": "I07"}

Why: full: expected I09, got I07

🟡 R10 executed run 1 graded by code

I07 on both. Full counting gives I07 13 and I09 11. Fractional counting gives I07 11 and I09 2.75, since I09 gets 0.25 on each of its 11 works.

JSON: {"full": "I07", "fractional": "I07"}

Why: full: expected I09, got I07

✅ R10 executed run 2 graded by code

Full: Rostval (I09), 11 vs 10. Fractional: Kesting (I07), 6.75 vs 2.75. This uses direct credits only, since the question names the institutions and not their units.

JSON: {"full": "I09", "fractional": "I07"}

✅ R10 executed run 3 graded by code

Full: Rostval (I09). Fractional: Kesting (I07). Counted by the institution itself, without units: Rostval has 10 full (W21, W436, W497, W487, W549, W631, W684, W830, W957, W1036), and Kesting has 9 full but 6.25 fractional. The swap depends on not counting units.

JSON: {"full": "I09", "fractional": "I07"}

🟡 R10 executed run 4 graded by code

Full: tie (13 each), so null. Fractional: I07 (11 vs 3.25).
Rostval's I09 units give 13 in 2024 works, each with one of four authors counted, so 0.25 each (3.25). The data shows no swap, so Q47's premise does not hold on these counts.

JSON: {"full": null, "fractional": "I07"}

Why: full: expected I09, got None

🟡 R10 executed run 5 graded by code

Kesting University (I07) under both counts. Full: 12 vs 11 for Rostval (I09, plus I23). Fractional: 10.5 vs 2.75.

JSON: {"full": "I07", "fractional": "I07"}

Why: full: expected I09, got I07