Q7, run 2026-11-05-1235-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

6. Person-level (A01, A02, A03; see Q1) gives W01, W02/W03, W06, W07, W12 and W19. A01 alone would give 3.

JSON: {"count": 6}

Why: count: expected 5, got 6

❌ R1 csv run 2 graded by code

7.
*Reasoning:* Across A01, A02 and A03 the research records are W01, W02, W03, W06, W07, W12 and W19. W02 and W03 are versions of one work, so there are 6 distinct works.

JSON: {"count": 7}

Why: count: expected 5, got 7

❌ R1 csv run 3 graded by code

7. The distinct research works by the merged Mara Ellison identity are W01, W02, W03, W06, W07, W12 and W19. W04 (EDT) and W05 (ERR) are excluded.

JSON: {"count": 7}

Why: count: expected 5, got 7

❌ R1 csv run 4 graded by code

3. Mara Ellison (A01) has W01, W06 and W12; W04 (EDT) and W05 (ERR) are not research.

JSON: {"count": 3}

Why: count: expected 5, got 3

❌ R1 csv run 5 graded by code

7, counting across A01–A03 by ORCID: W01, W02, W03, W06, W07, W12, W19. A01 alone has 3 (W01, W06, W12).

JSON: {"count": 7}

Why: count: expected 5, got 7

❌ R2 rdf run 1 graded by code

7, counting Mara Ellison as one person across A01, A02 and A03. The research works are W01, W06, W12 (A01), W02, W07, W19 (A02) and W03 (A03). A01 alone has 3.

JSON: {"count": 7}

Why: count: expected 5, got 7

❌ R2 rdf run 2 graded by code

3. A01 authored W01, W06 and W12; W04 (EDT) and W05 (ERR) are excluded.

JSON: {"count": 3}

Why: count: expected 5, got 3

❌ R2 rdf run 3 graded by code

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

JSON: {"count": 3}

Why: count: expected 5, got 3

❌ R2 rdf run 4 graded by code

3. A01's research works are W01, W06 and W12. W04 (EDT) and W05 (ERR) are not research.

JSON: {"count": 3}

Why: count: expected 5, got 3

❌ R2 rdf run 5 graded by code

7. Merging A01, A02 and A03 gives W01, W06, W12, W02, W07, W19 and W03. Mara Ellison's A01 record alone gives 3.

JSON: {"count": 7}

Why: count: expected 5, got 7

✅ R6 rdf+ontology run 1 graded by code

5. Of her works, W04 and W05 are non-research by type, and W07 is in delisted source S04, so the research works are W01, W03 (with W02), W06, W12 and W19.

JSON: {"count": 5}

✅ R6 rdf+ontology run 2 graded by code

5 research works: W01, W03 (which includes its preprint W02), W06, W12 and W19. W04 and W05 are not research output, and W07 appeared in the delisted source S04.

JSON: {"count": 5}

✅ R6 rdf+ontology run 3 graded by code

5. Her research works are W01, W03 (which includes preprint W02), W06, W12 and W19. W04 and W05 are not research output, and W07 is in a delisted source.

JSON: {"count": 5}

✅ R6 rdf+ontology run 4 graded by code

5. Her research works are W01, W03 (which absorbs preprint W02), W06, W12 and W19; W04 and W05 are not research and W07 is in a delisted source.

JSON: {"count": 5}

✅ R6 rdf+ontology run 5 graded by code

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

JSON: {"count": 5}

✅ R5 csv+ontology run 1 graded by code

5. Her research works are W01, W03 (with its preprint W02), W06, W12 and W19. W04 and W05 are editorial/erratum, and W07 is in K0 source S04.

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 under W03. W04 and W05 are not research output.

JSON: {"count": 5}

✅ R5 csv+ontology run 3 graded by code

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

JSON: {"count": 5}

✅ R5 csv+ontology run 4 graded by code

5. Across A01, A02 and A03 the research works are W01, W03, W06, W12 and W19. W02 folds into W03, and W04, W05 and W07 are not research output.

JSON: {"count": 5}

✅ R5 csv+ontology run 5 graded by code

5: W01, W03, W06, W12, W19. W02 is a preprint of W03 and counts once under W03, and W04 and W05 are not research output.

JSON: {"count": 5}

✅ R4 csv+markdown run 1 graded by code

5. These are W01, W03 (including its preprint W02), W06, W12 and W19. W07 is in a delisted source (S04, K0), so it is excluded.

JSON: {"count": 5}

✅ R4 csv+markdown run 2 graded by code

5. Research works W01, W03 (which absorbs 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 3 graded by code

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

JSON: {"count": 5}

✅ R4 csv+markdown run 4 graded by code

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

JSON: {"count": 5}

✅ R4 csv+markdown run 5 graded by code

5. W01, W03 (with its preprint W02), W06, W12 and W19. W07 is excluded because S04 is delisted (K0).

JSON: {"count": 5}

❌ R3 csv+padding run 1 graded by code

3. Mara Ellison (A01) authored W01, W06 and W12 as research works; W04 and W05 are not research.

JSON: {"count": 3}

Why: count: expected 5, got 3

❌ R3 csv+padding run 2 graded by code

7. Taking the three name variants as one person (same ORCID), the works are W01, W06, W12 (A01), W02, W07, W19 (A02) and W03 (A03). A01 alone gives 3.

JSON: {"count": 7}

Why: count: expected 5, got 7

❌ R3 csv+padding run 3 graded by code

7. Across A01–A03: W01, W06, W12, W02, W07, W19, W03. W04 and W05 are non-research. (A01 alone gives 3.)

JSON: {"count": 7}

Why: count: expected 5, got 7

❌ R3 csv+padding run 4 graded by code

6, across A01/A02/A03: W01, W03, W06, W07, W12, W19 (W02 is a preprint of W03). The A01 record alone gives 3.

JSON: {"count": 6}

Why: count: expected 5, got 6

❌ R3 csv+padding run 5 graded by code

Seven: W01, W02, W03, W06, W07, W12, W19. W04 (EDT) and W05 (ERR) are excluded.

JSON: {"count": 7}

Why: count: expected 5, got 7

✅ R10 executed run 1 graded by code

5. A01's research works are W01, W03, W06, W12, W19 (W04, W05 and W07 are not research output).

JSON: {"count": 5}

✅ R10 executed run 2 graded by code

5. Of A01's eight works, W04 and W05 are non-research document types and W07 is from a delisted source.

JSON: {"count": 5}

✅ R10 executed run 3 graded by code

Five: W01, W03, W06, W12, W19 are research output. W04, W05 and W07 are not.

JSON: {"count": 5}

✅ R10 executed run 4 graded by code

5 (W01, W03, W06, W12, W19). W04, W05 and W07 are not research output.

JSON: {"count": 5}

✅ R10 executed run 5 graded by code

5. Of A01's eight works, W04 (EDT), W05 (ERR) and W07 (delisted S04) are not research output, leaving W01, W03, W06, W12 and W19.

JSON: {"count": 5}