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

← 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

Full counting favours I09 (16 works against 15 for I07). Fractional counting favours I07 (13.0 against 4.0 for I09).

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

✅ R1 csv run 2 graded by code

Full counting favours I09 (15 vs 14). Fractional favours I07 (12.0 vs 3.75).

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

✅ R1 csv run 3 graded by code

Full counting favours I09 (15 works against Kesting's 14). Fractional counting favours I07 (12.0 against Rostval's 3.75).

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

✅ R1 csv run 4 graded by code

Full counting favours I09 (15 vs 14). Fractional counting favours I07 (12.0 vs 3.75).

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

✅ R1 csv run 5 graded by code

Full counting: I09 (16 works against 14). Fractional counting: I07 (12.0 against 4.0).

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

✅ R3 csv+padding run 1 graded by code

Full: I09 (16 vs 14). Fractional: I07 (12 vs 4). Each of Rostval's 16 works has four authors from different institutions, so each contributes 0.25.

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

✅ R3 csv+padding run 2 graded by code

Full: I09 (15 works vs 14). Fractional: I07 (12 vs 3.75).

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

✅ R3 csv+padding run 3 graded by code

Full: I09; fractional: I07. I09 has 15 works in 2024, each with one Rostval author out of four, so 3.75 fractional. I07 has 14 works but 12.0 fractional.

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

✅ R3 csv+padding run 4 graded by code

Full: I09 (16 works against 14). Fractional: I07 (12.0 against 4.0).

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

✅ R3 csv+padding run 5 graded by code

Full: I09 (16 vs 15). Fractional: I07 (13.0 vs 4.0). Each of Rostval's 16 works has one Rostval author out of four, so each is worth 0.25.

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

✅ R4 csv+markdown run 1 graded by code

Full counting favours Rostval Technical University (I09, 16 works against 13). Fractional counting favours Kesting University (I07, 11 against 4).

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

✅ R4 csv+markdown run 2 graded by code

Full: I09 (15 works against 13 for I07). Fractional: I07 (11 against 3.75 for I09). I09 has 15 works in 2024, each with one I09 author of four, so 15 × 0.25 = 3.75.

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

✅ R4 csv+markdown run 3 graded by code

Full: I09, which has 16 works against 13 for I07. Fractional: I07, with 11.0 against 4.0 for I09, because each of the 16 Rostval works gives it only one of four authors.

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

✅ R4 csv+markdown run 4 graded by code

Full counting favours I09 (16 works against 13). Fractional counting favours I07 (11 against 4).

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

✅ R4 csv+markdown run 5 graded by code

Full: I09 (16 against 13). Fractional: I07 (11 against 4). Each of Rostval's 16 works carries one Rostval author out of four, so each contributes 0.25.

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

✅ R5 csv+ontology run 1 graded by code

Under full counting, Rostval (I09) has 16 against Kesting's 13. Under fractional counting, Kesting (I07) has 11 against Rostval's 4.0.

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

✅ R5 csv+ontology run 2 graded by code

Full: I09 (16 works against 13 for I07). Fractional: I07 (11 against 4.0).

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

✅ R5 csv+ontology run 3 graded by code

Full: I09 (15 works against 13). Fractional: I07 (11 against 3.75). Rostval's 15 works each have 4 authors with only one from Rostval.

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

✅ R5 csv+ontology run 4 graded by code

Full counting: Rostval (I09) has 16 against Kesting's 13. Fractional counting: Kesting (I07) has 11 against Rostval's 4.0.

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

✅ R5 csv+ontology run 5 graded by code

Full: I09. Fractional: I07. I09 and its unit I23 have 15 works in 2024 against Kesting's 13. I09 gets only 15 × ¼ = 3.75 fractionally, against Kesting's 11.

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

✅ R10 executed run 1 graded by code

Under full counting Rostval (I09) has more: 15 against 13. Under fractional counting Kesting (I07) has more: 11 against 4.5.

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

✅ R10 executed run 2 graded by code

Full counting favours I09 (14 against 13), while fractional counting favours I07 (11 against 4.25).

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

✅ R10 executed run 3 graded by code

Full: I09, fractional: I07. Rostval has 16 research works in 2024 (full count 16), each with one Rostval author out of four, so fractional is 4. Kesting has 13 and 11.

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

✅ R10 executed run 4 graded by code

Full counting: I09 (16 works against 13). Fractional counting: I07 (11 against 4).

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

✅ R10 executed run 5 graded by code

Full counting favours I09 (16 works against 13 for I07). Fractional counting favours I07 (11 against 4 for I09), because every I09 work in 2024 is one author of four (0.25 each).

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