Q6, run 2026-11-05-1235-haiku

← back to the run

Which author has the most research works credited to the University of Albury, its units included?

Tests: Identity: Mara Ellison's five works are split over three records; by record, Priya Ramanathan (four) would come first.

Expected: author = A01

❌ R1 csv run 1 graded by code

A07 and A08 tie at 4 each. A07 has W01, W02/W03 (one work), W13 and W72; A08 has W70, W71, W72 and W73.

JSON: {"author": "A07, A08 (tie, 4 each)"}

Why: author: expected A01, got A07, A08 (tie, 4 each)

✅ R1 csv run 2 graded by code

A01 (Mara Ellison, including A02 and A03), with 7 research records.
*Reasoning:* W01, W06 and W12 (A01), W02, W07 and W19 (A02) and W03 (A03) are all UoA-credited. The next-highest is A07 with 5 records (4 distinct).

JSON: {"author": "A01"}

✅ R1 csv run 3 graded by code

Mara Ellison (A01, merged with A02 and A03), with 7 works. Her distinct research works at I02 or its units are W01, W02, W03, W06, W07, W12 and W19. Priya Ramanathan (A07) is next with 5.

JSON: {"author": "A01"}

❌ R1 csv run 4 graded by code

Tie between A07 and A08, each with 4 distinct research works at I02's units. A07 has W01, W03 (with its preprint W02), W13 and W72; A08 has W70, W71, W72 and W73. The answer in JSON is A07, but it is a tie.

JSON: {"author": "A07"}

Why: author: expected A01, got A07

✅ R1 csv run 5 graded by code

A01 (Mara Ellison across A01–A03), with 7 works. Her works credited to I02 and its units are W01, W02, W03, W06, W07, W12 and W19. At record level alone, A07 has the most, with 5 (W01, W02, W03, W13, W72).

JSON: {"author": "A01"}

❌ R2 rdf run 1 graded by code

A07 (Priya Ramanathan), with 5 research works. This is W01, W02 (PPR), W03, W13 and W72. If preprints were excluded, A07 and A08 would tie at 4.

JSON: {"author": "A07"}

Why: author: expected A01, got A07

❌ R2 rdf run 2 graded by code

A07 (Priya Ramanathan), with 5 research works (W01, W02, W03, W13, W72) at I02, I03, I04 or I06. The next is A08 with 4 (W70, W71, W72, W73).

JSON: {"author": "A07"}

Why: author: expected A01, got A07

❌ R2 rdf run 3 graded by code

A07 (Priya Ramanathan), with 5 research works at I02/I03/I04/I06: W01, W02, W03, W13, W72. This relies on counting the preprint W02; without it A07 and A08 tie at 4.

JSON: {"author": "A07"}

Why: author: expected A01, got A07

❌ R2 rdf run 4 graded by code

A07, with 5 research works (W01, W02, W03, W13, W72) credited to the I02 family. A08 has 4 and A01 has 3.

JSON: {"author": "A07"}

Why: author: expected A01, got A07

❌ R2 rdf run 5 graded by code

A07 (Priya Ramanathan), with 5. Research works at I02 or its units (I03, I04, I06) are W01, W02, W03, W13 and W72 (AS-W01-A07-1, AS-W02-A07-1, AS-W03-A07-1, AS-W13-A07-1, AS-W72-A07-1).

JSON: {"author": "A07"}

Why: author: expected A01, got A07

✅ R6 rdf+ontology run 1 graded by code

A01 (the Mara Ellison person, records A01/A02/A03), with 5 research works: W01, W03 (with preprint W02), W06, W12, W19. Priya Ramanathan (A07) has 4 and Tomasz Wierzba (A08) has 2.

JSON: {"author": "A01"}

✅ R6 rdf+ontology run 2 graded by code

A01 (Mara Ellison, the person with ORCID 0002-9841-6229). Her Albury-credited research works are W01, W03, W06, W12 and W19, five in all. Priya Ramanathan (A07) has four and Tomasz Wierzba (A08) has two.

JSON: {"author": "A01"}

✅ R6 rdf+ontology run 3 graded by code

A01 (Mara Ellison). She has 5 research works credited to I02's tree (W01, W03, W06, W12, W19), ahead of Priya Ramanathan (A07) with 4.

JSON: {"author": "A01"}

✅ R6 rdf+ontology run 4 graded by code

A01 (Mara Ellison, across A01/A02/A03), with 5 research works (W01, W03, W06, W12, W19) credited to I02 or its units. The next is A07 with 4.

JSON: {"author": "A01"}

✅ R6 rdf+ontology run 5 graded by code

A01 (Mara Ellison, counting A02 and A03), with 5 research works credited to University of Albury (I02, units included): W01, W03, W06, W12, W19. Runner-up is A07 with 4; if the records were not merged by ORCID, A07 would lead 4 to 3.

JSON: {"author": "A01"}

✅ R5 csv+ontology run 1 graded by code

A01 (Mara Ellison, via A01/A02/A03), with 5. Her research works in the University of Albury subtree are W01, W03, W06, W12 and W19 (W02 folds into W03). A07 has 4 and A08 has 2.

JSON: {"author": "A01"}

✅ R5 csv+ontology run 2 graded by code

A01 (Mara Ellison, the person behind A01/A02/A03), with 5 research works: W01, W03, W06, W12, W19. Priya Ramanathan (A07) has 4.

JSON: {"author": "A01"}

✅ R5 csv+ontology run 3 graded by code

A01. Mara Ellison has 5 research works credited to I02 or its units (W01, W03, W06, W12, W19), ahead of Priya Ramanathan (A07) with 4 (W01, W03, W13, W72).

JSON: {"author": "A01"}

✅ R5 csv+ontology run 4 graded by code

Mara Ellison, with 5 research works (W01, W03, W06, W12, W19). Her records A01, A02 and A03 share one ORCID; the next highest is Priya Ramanathan (A07) with 4.

JSON: {"author": "A01"}

✅ R5 csv+ontology run 5 graded by code

A01 (Mara Ellison, merged with A02 and A03), with 5 research works credited to I02 or its units: W01, W03, W06, W12, W19. The next is Priya Ramanathan (A07) with 4.

JSON: {"author": "A01"}

✅ R4 csv+markdown run 1 graded by code

A01. Counting the Mara Ellison person (A01, A02, A03) gives 5 research works at I02/I03/I04 (W01, W03, W06, W12, W19), ahead of A07 with 4.

JSON: {"author": "A01"}

✅ R4 csv+markdown run 2 graded by code

A01 (Mara Ellison, as one person). She has 5 research works credited to I02 (W01, W03, W06, W12, W19), more than any other author (Priya Ramanathan has 4).

JSON: {"author": "A01"}

✅ R4 csv+markdown run 3 graded by code

A01 (Mara Ellison, ORCID-linked to A02 and A03), with 5 research works: W01, W03, W06, W12, W19. Priya Ramanathan (A07) is next with 4. W07 is excluded because S04 is delisted (K0).

JSON: {"author": "A01"}

✅ R4 csv+markdown run 4 graded by code

A01 (Mara Ellison, with A02 and A03). Her research works in the Albury tree are W01, W03, W06, W12 and W19 (5), versus 4 for Priya Ramanathan (A07).

JSON: {"author": "A01"}

✅ R4 csv+markdown run 5 graded by code

A01 (Mara Ellison). She has 5 research works credited to I02, I03 or I04 (W01, W03, W06, W12, W19), against 4 for A07.

JSON: {"author": "A01"}

❌ R3 csv+padding run 1 graded by code

A07 (Priya Ramanathan), with 5. A07 is credited on W01, W02, W03, W13 and W72, all under I02 via I03.

JSON: {"author": "A07"}

Why: author: expected A01, got A07

❌ R3 csv+padding run 2 graded by code

A07 (Priya Ramanathan), with 5 research works: W01, W02, W03, W13, W72. The next highest is A08 with 4.

JSON: {"author": "A07"}

Why: author: expected A01, got A07

❌ R3 csv+padding run 3 graded by code

A07 (Priya Ramanathan), with 5 research works (W01, W02, W03, W13, W72) credited to I02 or its units. The next is A08, with 4 (W70–W73).

JSON: {"author": "A07"}

Why: author: expected A01, got A07

✅ R3 csv+padding run 4 graded by code

A01 (Mara Ellison, consolidated with A02 and A03). She has 6 distinct research works at Albury units, against 4 for A07.

JSON: {"author": "A01"}

✅ R3 csv+padding run 5 graded by code

A01 (Mara Ellison, merged with A02 and A03) with 7 research works at Albury units, ahead of A07 with 5 (W01, W02, W03, W13, W72). Only the merged person leads; at record level A07 is top.

JSON: {"author": "A01"}

✅ R10 executed run 1 graded by code

A01. A01 has 5 research works at I02, I03 or I04 (W01, W03, W06, W12, W19), versus 4 for A07 and 2 for A08.

JSON: {"author": "A01"}

✅ R10 executed run 2 graded by code

A01, with 5 research works (W01, W03, W06, W12, W19) credited to I02, I03 or I04.

JSON: {"author": "A01"}

✅ R10 executed run 3 graded by code

A01. Under I02 with units I03 and I04, A01 has five research works (W01, W03, W06, W12, W19), ahead of A07 (four) and A08 (two).

JSON: {"author": "A01"}

✅ R10 executed run 4 graded by code

A01 (5 works). Among I02, I03 and I04 units, A01 has W01, W03, W06, W12 and W19; A07 has four (W01, W03, W13, W72).

JSON: {"author": "A01"}

✅ R10 executed run 5 graded by code

A01. Five research works (W01, W03, W06, W12, W19) are credited to I02 for A01, more than A07 (4) or A08 (2) across I02, I03 and I04.

JSON: {"author": "A01"}