Q7, run 2026-11-06-0206-sonnet

← 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 = 19

❌ R1 csv run 1 graded by code

22. These are her 32 works minus 6 editorials/errata (W04, W05, W271, W813, W936, W949), 3 preprint duplicates (W02, W612, W663) and the retracted W374.

JSON: {"count": 22}

Why: count: expected 19, got 22

❌ R1 csv run 2 graded by code

23. Her 32 works minus EDT/ERR (W04, W05, W271, W813, W936, W949) and the preprints W02, W612 and W663.

JSON: {"count": 23}

Why: count: expected 19, got 23

❌ R1 csv run 3 graded by code

23. She has 32 records in total. I removed the editorials, errata and preprints (W02, W663, W612, which sit under W03, W464 and W869), leaving 23.

JSON: {"count": 23}

Why: count: expected 19, got 23

❌ R1 csv run 4 graded by code

22. The excluded items are the editorials, errata, the retracted W374, and the preprints W02 and W663.

JSON: {"count": 22}

Why: count: expected 19, got 22

❌ R1 csv run 5 graded by code

22. This excludes the editorials and errata, the retracted W374, and the preprints W02, W612 and W663.

JSON: {"count": 22}

Why: count: expected 19, got 22

❌ R3 csv+padding run 1 graded by code

22. Of her 32 works, 6 are non-research types, W374 is retracted, and the preprints W02 and W663 and W612 merge into W03, W464 and W869.

JSON: {"count": 22}

Why: count: expected 19, got 22

❌ R3 csv+padding run 2 graded by code

23. Of her 32 works, W04, W05, W271, W813, W936 and W949 are not research, and the preprints W02, W612 and W663 merge into W03, W869 and W464.

JSON: {"count": 23}

Why: count: expected 19, got 23

❌ R3 csv+padding run 3 graded by code

23. These are her 32 works minus the editorials W04, W271, W936 and errata W05, W813, W949, with the preprints W02, W612, W663 merged into W03, W869 and W464.

JSON: {"count": 23}

Why: count: expected 19, got 23

❌ R3 csv+padding run 4 graded by code

23. This counts W02/W03, W612/W869 and W663/W464 once each, and includes the retracted W374.

JSON: {"count": 23}

Why: count: expected 19, got 23

❌ R3 csv+padding run 5 graded by code

23. Of her 32 works, W04, W05, W271, W813, W936 and W949 are EDT or ERR. W02, W612 and W663 are preprints of W03, W869 and W464.

JSON: {"count": 23}

Why: count: expected 19, got 23

✅ R4 csv+markdown run 1 graded by code

19. The count merges A01, A02, A03 and A101 and drops EDT/ERR, K0-source (W07, W449, W763) and retracted (W374) works. Preprints are merged into their published versions.

JSON: {"count": 19}

✅ R4 csv+markdown run 2 graded by code

19. Her preprints W02, W612 and W663 merge into W03, W869 and W464. W07 and W763 are in delisted sources, W374 is retracted, and the editorials and errata are not research.

JSON: {"count": 19}

✅ R4 csv+markdown run 3 graded by code

19. Excluded are W04, W05, W271, W813, W936 and W949 (editorials and errata), W07 and W449 and W763 (delisted sources), and W374 (retracted).

JSON: {"count": 19}

✅ R4 csv+markdown run 4 graded by code

19. She has 38 records. Of these, 6 are editorials or errata, 2 are retracted or K0 (W374; W07 and W449 are K0, W763 too), and the preprints W02 and W663 merge into W03 and W464.

JSON: {"count": 19}

✅ R4 csv+markdown run 5 graded by code

19. Her 32 works lose the editorials and errata, the retracted W374, and the works in the delisted sources S04 and S13 (W07, W449, W763).

JSON: {"count": 19}

❌ R5 csv+ontology run 1 graded by code

20. These are W01, W03, W06, W12, W19, W206, W238, W464, W555, W676, W763, W817, W843, W869, W905, W972, W984, W1005, W1048 and W1050. The preprints W02, W612 and W663 merge into W03, W869 and W464.

JSON: {"count": 20}

Why: count: expected 19, got 20

✅ R5 csv+ontology run 2 graded by code

19. W07 and W449 are in the delisted S04, W763 is in the delisted S13, W374 is retracted, and the editorials and errata are not research. The preprints W02, W612 and W663 count under W03, W869 and W464.

JSON: {"count": 19}

✅ R5 csv+ontology run 3 graded by code

19. I dropped the editorials and errata (W04, W05, W271, W813, W936, W949), the retracted W374, and the delisted-source W07, W449 and W763. The preprints W02, W663 and W612 merge into W03, W464 and W869.

JSON: {"count": 19}

✅ R5 csv+ontology run 4 graded by code

19. The 32 works in Q2 shrink to 19 once these are dropped:
- the non-research types W04, W05, W271, W813, W936, W949;
- W07 and W449 (delisted source);
- W374 (retracted) and W763 (delisted source);
- the preprints W02, W612 and W663, which merge into W03, W869 and W464.

JSON: {"count": 19}

✅ R5 csv+ontology run 5 graded by code

19. I left out her editorials and errata (W04, W05, W271, W813, W936, W949). I also left out W07 and W449 (K0 source S04), W763 (K0 source S13) and W374 (retracted). The preprints W02, W612 and W663 are merged into W03, W869 and W464.

JSON: {"count": 19}

✅ R10 executed run 1 graded by code

19. Mara Ellison's other works are excluded because of type (editorials, errata) or because of retraction or a delisted source.

JSON: {"count": 19}

❌ R10 executed run 2 graded by code

20 research works, namely the works in Q2 minus the non-research ones (W04, W05, W07, W271, W374, W449, W763, W813, W936, W949).

JSON: {"count": 20}

Why: count: expected 19, got 20

❌ R10 executed run 3 graded by code

20. Of her 30 works, W04, W05, W07, W271, W374, W449, W763, W813, W936 and W949 are not research output.

JSON: {"count": 20}

Why: count: expected 19, got 20

❌ R10 executed run 4 graded by code

20. These are A01's works after dropping editorials, errata, retracted works and delisted-source works.

JSON: {"count": 20}

Why: count: expected 19, got 20

❌ R10 executed run 5 graded by code

20. These are the research works in Q2, excluding the editorials, errata, retracted work and delisted-source works.

JSON: {"count": 20}

Why: count: expected 19, got 20