Q9, run 2026-11-06-0206-sonnet

← back to the run

How many research works is the University of Albury (I02) credited with, its units included?

Tests: Hierarchy: the labs' works count, each work once; also versions, types, the affiliation rule and the affiliated institute.

Expected: count = 95

❌ R1 csv run 1 graded by code

116, counting I02, I03, I04, I06 and I19.

JSON: {"count": 116}

Why: count: expected 95, got 116

❌ R1 csv run 2 graded by code

118, counting I02, I03, I04, I06 and I19.

JSON: {"count": 118}

Why: count: expected 95, got 118

❌ R1 csv run 3 graded by code

119, after merging preprints into their published versions (two retracted works are included).

JSON: {"count": 119}

Why: count: expected 95, got 119

❌ R1 csv run 4 graded by code

117 (I02, I03, I04, I06 and I19).

JSON: {"count": 117}

Why: count: expected 95, got 117

❌ R1 csv run 5 graded by code

117, counting I02, I03, I04, I06 and I19.

JSON: {"count": 117}

Why: count: expected 95, got 117

❌ R3 csv+padding run 1 graded by code

117.

JSON: {"count": 117}

Why: count: expected 95, got 117

❌ R3 csv+padding run 2 graded by code

119.

JSON: {"count": 119}

Why: count: expected 95, got 119

❌ R3 csv+padding run 3 graded by code

119, over I02, I03, I04, I06 and I19. This includes the standalone preprint W745 and W70.

JSON: {"count": 119}

Why: count: expected 95, got 119

❌ R3 csv+padding run 4 graded by code

119, for I02 plus I03, I04, I19 and I06.

JSON: {"count": 119}

Why: count: expected 95, got 119

❌ R3 csv+padding run 5 graded by code

119. This covers I02, I03, I04, I06 and I19.

JSON: {"count": 119}

Why: count: expected 95, got 119

❌ R4 csv+markdown run 1 graded by code

94. I02, I03, I04 and I19 are counted, and I06 is excluded because it is an affiliated institute.

JSON: {"count": 94}

Why: count: expected 95, got 94

❌ R4 csv+markdown run 2 graded by code

94. This counts works credited to I02, I03, I04 or I19 by the last-listed affiliation. I06 is an affiliated institute, so it does not count towards I02.

JSON: {"count": 94}

Why: count: expected 95, got 94

✅ R4 csv+markdown run 3 graded by code

95. I counted works credited to I02, I03, I04 or I19. I06 is excluded because it is an affiliated institute.

JSON: {"count": 95}

❌ R4 csv+markdown run 4 graded by code

92. This counts research works credited to I02, I03, I04 or I19. I06 is an affiliated institute, so it is excluded.

JSON: {"count": 92}

Why: count: expected 95, got 92

✅ R4 csv+markdown run 5 graded by code

95, counting works credited to I02, I03, I04 and I19. The affiliated institute I06 is excluded.

JSON: {"count": 95}

❌ R5 csv+ontology run 1 graded by code

96. Units I03, I04 and I19 are included, and the affiliated institute I06 is not. Only each author's last-listed affiliation counts.

JSON: {"count": 96}

Why: count: expected 95, got 96

✅ R5 csv+ontology run 2 graded by code

95. I counted works credited to I02, I03, I04 and I19, using each author's last-listed affiliation. I06 is an affiliated institute and is excluded.

JSON: {"count": 95}

✅ R5 csv+ontology run 3 graded by code

95, from I02, I03, I04 and I19. The affiliated I06 is excluded, and each author counts only for the last-listed affiliation.

JSON: {"count": 95}

✅ R5 csv+ontology run 4 graded by code

95. I02 plus I03, I04 and I19; the affiliated institute I06 is not followed.

JSON: {"count": 95}

✅ R5 csv+ontology run 5 graded by code

95. I02 plus I03, I04 and I19 are counted. I06 is an affiliated institute, so it is not a unit. For W70, W252, W617, W664, W671 and W940 the credited (last-listed) affiliation is I06, so they are excluded.

JSON: {"count": 95}

❌ R10 executed run 1 graded by code

93, counting I02, I03, I04 and I19 via institution_units. This was a long manual scan, so treat it as approximate.

JSON: {"count": 93}

Why: count: expected 95, got 93

❌ R10 executed run 2 graded by code

93. This counts distinct research works credited to I02, I03, I04 or I19; I06 does not roll up into I02 in institution_units. I counted this by hand, so treat it as approximate.

JSON: {"count": 93}

Why: count: expected 95, got 93

❌ R10 executed run 3 graded by code

94 research works, counting credits at I02, I03, I04 and I19.

JSON: {"count": 94}

Why: count: expected 95, got 94

❌ R10 executed run 4 graded by code

93. This counts distinct research works credited to I02, I03, I04 or I19; I06 does not roll up into I02 in institution_units.

JSON: {"count": 93}

Why: count: expected 95, got 93

❌ R10 executed run 5 graded by code

93. This counts distinct research works with a credit at I02, I03, I04 or I19; I06 does not roll up to I02.

JSON: {"count": 93}

Why: count: expected 95, got 93