Q7, run 2026-11-04-1752-haiku

← back to the run

How many research works has Mara Ellison authored?

Tests: Everything at once: identity, versions (W02 is W03), document types (W04, W05) and the delisted source (W07).

Expected: count = 5

❌ R1 csv run 1 graded by code

3. A01 is the author of W01, W06 and W12 (ART). W04 (EDT) and W05 (ERR) are excluded.

JSON: {"count": 3}

Why: count: expected 5, got 3

❌ R1 csv run 2 graded by code

3. A01 is credited on the research works W01, W06 and W12; W04 (editorial) and W05 (erratum) are excluded.

JSON: {"count": 3}

Why: count: expected 5, got 3

❌ R1 csv run 3 graded by code

6. Across A01, A02 and A03: W01, W03 (with W02), W06, W07, W12 and W19; W04 (EDT) and W05 (ERR) are excluded. A01 alone would give 3.

JSON: {"count": 6}

Why: count: expected 5, got 6

❌ R1 csv run 4 graded by code

7 for the person (W01, W02, W03, W06, W07, W12, W19; all are research types). A01's record alone gives 3.

JSON: {"count": 7}

Why: count: expected 5, got 7

❌ R1 csv run 5 graded by code

6. Mara's works across A01, A02 and A03 are W01, W02/W03, W06, W07, W12 and W19, with W04 and W05 excluded by type.

JSON: {"count": 6}

Why: count: expected 5, got 6

❌ R2 rdf run 1 graded by code

7 at person level (A01+A02+A03: W01, W02, W03, W06, W07, W12, W19). A01 alone has 3 (W01, W06, W12), since W04 (EDT) and W05 (ERR) are excluded.

JSON: {"count": 7}

Why: count: expected 5, got 7

❌ R2 rdf run 2 graded by code

7 at person level (W01, W06, W12 via A01; W02, W07, W19 via A02; W03 via A03). Restricted to record A01 alone, it is 3.

JSON: {"count": 7}

Why: count: expected 5, got 7

❌ R2 rdf run 3 graded by code

7, counting the merged person (A01, A02, A03): W01, W02, W03, W06, W07, W12, W19. A01 alone has 3, since W04 (EDT) and W05 (ERR) are excluded.

JSON: {"count": 7}

Why: count: expected 5, got 7

❌ R2 rdf run 4 graded by code

3. A01's research works are W01, W06 and W12; W04 (EDT) and W05 (ERR) are excluded.

JSON: {"count": 3}

Why: count: expected 5, got 3

❌ R2 rdf run 5 graded by code

3. A01's research works are W01, W06 and W12. W04 (editorial) and W05 (erratum) are excluded.

JSON: {"count": 3}

Why: count: expected 5, got 3

✅ R6 rdf+ontology run 1 graded by code

5. W01, W03 (which absorbs its preprint W02), W06, W12 and W19 are research works. W04 (editorial), W05 (erratum) and W07 (source K0) are excluded.

JSON: {"count": 5}

✅ R6 rdf+ontology run 2 graded by code

5. Research works by the Mara person are W01, W03 (which includes preprint W02), W06, W12 and W19. W04 and W05 are not research output, and W07 is in delisted S04.

JSON: {"count": 5}

✅ R6 rdf+ontology run 3 graded by code

5. The research works are W01, W03 (with its preprint W02), W06, W12 and W19; W04, W05 and W07 are excluded.

JSON: {"count": 5}

✅ R6 rdf+ontology run 4 graded by code

5. Across the three Ellison records, the research works are W01, W03 (via the W02 preprint and A03), W06, W12 and W19; W07 is in a delisted source.

JSON: {"count": 5}

✅ R6 rdf+ontology run 5 graded by code

5. These are W01, W03, W06, W12 and W19. W02 is a preprint of W03 and counts once under W03; W04 and W05 are not research; W07 appeared in S04, which is delisted (K0).

JSON: {"count": 5}

✅ R5 csv+ontology run 1 graded by code

5. W01, W03, W06, W12 and W19 are research works; W02 is a preprint counted under W03, and W04, W05 and W07 are excluded.

JSON: {"count": 5}

✅ R5 csv+ontology run 2 graded by code

5. W01, W03, W06, W12 and W19 are research works. W02 is a preprint of W03, so it counts once, and W04, W05 and W07 are not research output.

JSON: {"count": 5}

✅ R5 csv+ontology run 3 graded by code

5. Her research works are W01, W03 (which includes its preprint W02), W06, W12 and W19; W07 is excluded because S04 is delisted (K0).

JSON: {"count": 5}

✅ R5 csv+ontology run 4 graded by code

5. W01, W03 (W02 is its preprint, counted once), W06, W12 and W19. W07 is in a delisted source (S04) and W04 and W05 are not research types.

JSON: {"count": 5}

✅ R5 csv+ontology run 5 graded by code

5. W01, W03 (with its preprint W02), W06, W12 and W19. W04 and W05 are not research output, and W07 is in delisted source S04.

JSON: {"count": 5}

✅ R4 csv+markdown run 1 graded by code

5. W01, W03, W06, W12 and W19 are research works; W02 is a preprint of W03 and counts once under W03, W04 and W05 are not research, and W07 is in a delisted source (S04).

JSON: {"count": 5}

✅ R4 csv+markdown run 2 graded by code

5. The person's research works are W01, W03 (including preprint W02), W06, W12 and W19; W04 and W05 are not research, and W07 is in delisted source S04.

JSON: {"count": 5}

✅ R4 csv+markdown run 3 graded by code

5. Mara Ellison's research works are W01, W03, W06, W12 and W19; W02 is a preprint of W03 and counts once there, and W07 is in a K0 source.

JSON: {"count": 5}

✅ R4 csv+markdown run 4 graded by code

5. Her research works are W01, W03 (with its preprint W02), W06, W12 and W19. W04 and W05 are non-research types and W07 appeared in a delisted source.

JSON: {"count": 5}

✅ R4 csv+markdown run 5 graded by code

5: W01, W03 (W02 is its preprint and counts once), W06, W12, W19. W04 and W05 are not research output, and W07 is in a delisted source.

JSON: {"count": 5}

❌ R3 csv+padding run 1 graded by code

3. These are W01, W06 and W12. The editorial W04 and erratum W05 are excluded by document type.

JSON: {"count": 3}

Why: count: expected 5, got 3

❌ R3 csv+padding run 2 graded by code

6. Mara's research works are W01, W06, W12, W07, W19 and W02/W03 (one version group); W04 and W05 are excluded.

JSON: {"count": 6}

Why: count: expected 5, got 6

❌ R3 csv+padding run 3 graded by code

7. Counting A01, A02 and A03 as one person (same ORCID), the research works are W01, W02, W03, W06, W07, W12 and W19. A01's record alone gives 3.

JSON: {"count": 7}

Why: count: expected 5, got 7

❌ R3 csv+padding run 4 graded by code

7 records: W01, W02, W03, W06, W07, W12, W19, across A01–A03 (same ORCID); W04 and W05 are non-research. W02 is a preprint of W03, so this is 6 distinct works; A01 alone has 3.

JSON: {"count": 7}

Why: count: expected 5, got 7

❌ R3 csv+padding run 5 graded by code

7, counting the same person (A01, A02, A03): W01, W02, W03, W06, W07, W12, W19. A01's records alone give 3.

JSON: {"count": 7}

Why: count: expected 5, got 7