Q2, run 2026-11-06-0855-haiku

← back to the run

List every work, of any type, that Mara Ellison (A01) is an author of.

Tests: Identity: her works are spread over three author records, and A04's works (W08, W16) are not hers.

Expected: works = ['W01', 'W02', 'W03', 'W04', 'W05', 'W06', 'W07', 'W12', 'W19']

✅ R8 csv+axioms run 1 graded by code

Nine works: W01, W02, W03, W04, W05, W06, W07, W12, W19. This counts A02 and A03 as the same person as A01 (same ORCID); A01 alone authored W01, W04, W05, W06 and W12.

JSON: {"works": ["W01", "W02", "W03", "W04", "W05", "W06", "W07", "W12", "W19"]}

✅ R8 csv+axioms run 2 graded by code

W01, W02, W03, W04, W05, W06, W07, W12, W19. Read as the person, this merges A02 and A03 (same ORCID) with A01; A01's own records alone give W01, W04, W05, W06, W12.

JSON: {"works": ["W01", "W02", "W03", "W04", "W05", "W06", "W07", "W12", "W19"]}

❌ R8 csv+axioms run 3 graded by code

W01, W04, W05, W06, W12. These are the authorships on A01. A02 and A03 are the same person by ORCID, so they add W02, W03, W07 and W19 at person level.

JSON: {"works": ["W01", "W04", "W05", "W06", "W12"]}

Why: works: expected ['W01', 'W02', 'W03', 'W04', 'W05', 'W06', 'W07', 'W12', 'W19'], got ['W01', 'W04', 'W05', 'W06', 'W12']

✅ R8 csv+axioms run 4 graded by code

W01, W02, W03, W04, W05, W06, W07, W12, W19. These are A01's records plus those of the same person (A02, A03), since they share an ORCID. A04 ("M. Ellison") has a different ORCID and is excluded.

JSON: {"works": ["W01", "W02", "W03", "W04", "W05", "W06", "W07", "W12", "W19"]}

❌ R8 csv+axioms run 5 graded by code

W01, W04, W05, W06, W12. These are the A01 authorship records. A02 and A03 are the same person, but the question names A01.

JSON: {"works": ["W01", "W04", "W05", "W06", "W12"]}

Why: works: expected ['W01', 'W02', 'W03', 'W04', 'W05', 'W06', 'W07', 'W12', 'W19'], got ['W01', 'W04', 'W05', 'W06', 'W12']

✅ R9 csv+axioms+markdown run 1 graded by code

W01, W02, W03, W04, W05, W06, W07, W12, W19. Counted per person, since A02 and A03 share A01's ORCID; A04 (different ORCID) is excluded.

JSON: {"works": ["W01", "W02", "W03", "W04", "W05", "W06", "W07", "W12", "W19"]}

✅ R9 csv+axioms+markdown run 2 graded by code

W01, W02, W03, W04, W05, W06, W07, W12, W19. These are every work recorded against A01, A02 or A03 (the same ORCID), of any type.

JSON: {"works": ["W01", "W02", "W03", "W04", "W05", "W06", "W07", "W12", "W19"]}

✅ R9 csv+axioms+markdown run 3 graded by code

W01, W02, W03, W04, W05, W06, W07, W12, W19. Taken at person level, since A01, A02 and A03 are one person by ORCID.

JSON: {"works": ["W01", "W02", "W03", "W04", "W05", "W06", "W07", "W12", "W19"]}

✅ R9 csv+axioms+markdown run 4 graded by code

W01, W02, W03, W04, W05, W06, W07, W12, W19. These are the works of A01 and of A02 and A03, which share her ORCID.

JSON: {"works": ["W01", "W02", "W03", "W04", "W05", "W06", "W07", "W12", "W19"]}

✅ R9 csv+axioms+markdown run 5 graded by code

W01, W02, W03, W04, W05, W06, W07, W12, W19. These are all records of the same person (A01, A02, A03, same ORCID). A01's own records alone give only W01, W04, W05, W06, W12.

JSON: {"works": ["W01", "W02", "W03", "W04", "W05", "W06", "W07", "W12", "W19"]}