Q12, run 2026-11-06-0206-haiku

← back to the run

How many research works did Kesting University (I07, units included) publish in 2024, under full counting and under fractional counting (each work split equally among its authors)?

Tests: Counting method: W20 is half Kesting's, W21 two quarters, W22 whole.

Expected: full = 13 fractional = 11

❌ R1 csv run 1 graded by code

Full 14; fractional 12. The 14 works are W20, W21, W22, W203, W333, W419, W421, W504, W528, W595, W624, W675, W705 and W1027.

JSON: {"full": 14, "fractional": 12}

Why: full: expected 13, got 14; fractional: expected 11, got 12

❌ R1 csv run 2 graded by code

Not computed yet. The 2024 full and fractional counts for I07 are deferred to the next batch.

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

Why: full: expected 13, got None; fractional: expected 11, got None

❌ R1 csv run 3 graded by code

Full 14; fractional 12.0. The 2024 works are W20, W21, W22, W203, W333, W419, W421, W504, W528, W595, W624, W675, W705, W1027.

JSON: {"full": 14, "fractional": 12}

Why: full: expected 13, got 14; fractional: expected 11, got 12

❌ 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": 15, "fractional": 13}

Why: full: expected 13, got 15; fractional: expected 11, got 13

✅ R3 csv+padding run 1 graded by code

Full: 13. Fractional: about 11.2 (W20 0.5, W21 0.5, W419 0.67, W675 0.5, and the remaining works 1 each). All are 2024 works with I07, I08 or I22 authors.

JSON: {"full": 13, "fractional": 11.17}

❌ R3 csv+padding run 2 graded by code

Full count 14; fractional count 12.0 (Kesting's 2024 works in W20, W21, W22, W203, W333, W419, W421, W504, W528, W595, W624, W675, W705, W1027).

JSON: {"full": 14, "fractional": 12.0}

Why: full: expected 13, got 14; fractional: expected 11, got 12.0

✅ R3 csv+padding run 3 graded by code

Full 13; fractional 11.5. Taking 2024 research works from Q11, with each work split equally across its author rows.

JSON: {"full": 13, "fractional": 11.5}

✅ R3 csv+padding run 4 graded by code

Full 13; fractional 11.5. Each work's Kesting share is the Kesting-affiliated authors divided by all authors.

JSON: {"full": 13, "fractional": 11.5}

✅ R3 csv+padding run 5 graded by code

Full 13, fractional 11.5. The 2024 works are W20, W21, W22, W203, W333, W419, W421, W504, W528, W595, W624, W705 and W1027. Fractional counts each work by the share of its authors at Kesting.

JSON: {"full": 13, "fractional": 11.5}

❌ 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 13, fractional 11. The 2024 works are W20, W21, W22, W203, W333, W419, W504, W528, W595, W624, W675, W705, W1027.

JSON: {"full": 13, "fractional": 11}

❌ R4 csv+markdown run 4 graded by code

(no answer found)

Why: no structured answer

❌ R4 csv+markdown run 5 graded by code

Full 12*; fractional 10.5*. The 2024 works are W21, W22, W203, W333, W419, W504, W528, W595, W624, W675, W705 and W1027.

JSON: {"full": 12, "fractional": 10.5}

Why: full: expected 13, got 12; fractional: expected 11, got 10.5

❌ R5 csv+ontology run 1 graded by code

(no answer found)

Why: no structured answer

❌ R5 csv+ontology run 2 graded by code

Full 14, fractional 12. The 2024 works are W20, W21, W22, W203, W333, W419, W504, W528, W595, W624, W675, W705, W956 and W1027.

JSON: {"full": 14, "fractional": 12}

Why: full: expected 13, got 14; fractional: expected 11, got 12

✅ R5 csv+ontology run 3 graded by code

Full: 13. Fractional: ≈11.2. Both use 2024 works credited to I07 or I08.

JSON: {"full": 13, "fractional": 11.2}

❌ R5 csv+ontology run 4 graded by code

(no answer found)

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

Why: full: expected 13, got None; fractional: expected 11, got None

✅ R5 csv+ontology run 5 graded by code

Full 13; fractional 11. These are the 2024 research works of I07 and I08.

JSON: {"full": 13, "fractional": 11}

✅ R10 executed run 1 graded by code

Full 13, fractional 11. The 2024 works are W20, W21, W22, W203, W333, W419, W504, W528, W595, W624, W675, W705 and W1027. Fractional shares use each work's credited authors, so W21 gives 2/4 and W203 gives 5/6.

JSON: {"full": 13, "fractional": 11}

✅ R10 executed run 2 graded by code

Full 13, fractional 11. These are 2024 research works with I07 or I08 credits (e.g., W20, W21, W22, W333, W504, W1027). Fractional is each work's Kesting credits divided by its total credits (e.g., W22 = 1, W203 = 5/6).

JSON: {"full": 13, "fractional": 11}

❌ R10 executed run 3 graded by code

Full 12; fractional 10.5. Using I07 plus I08, the 2024 works are W20, W21, W22, W203, W333, W419, W504, W528, W595, W624, W705 and W1027.

JSON: {"full": 12, "fractional": 10.5}

Why: full: expected 13, got 12; fractional: expected 11, got 10.5

✅ R10 executed run 4 graded by code

Full 13; fractional 11.
Full counts are the 2024 works in the I07/I08 set. Fractional sums each work's 1/N share for the Kesting-credited authors.

JSON: {"full": 13, "fractional": 11}

❌ R10 executed run 5 graded by code

Full 12; fractional 10.5. The 2024 research works are W20, W21, W22, W203, W333, W419, W504, W528, W595, W624, W705, W1027.

JSON: {"full": 12, "fractional": 10.5}

Why: full: expected 13, got 12; fractional: expected 11, got 10.5