Q20, run 2026-11-05-1235-haiku

← back to the run

Which works in the data are preprints of another work that is also in the data?

Tests: Versions: a shared title is the clue, version_of the evidence; W18 is a preprint with no published version.

Expected: works = ['W02', 'W42']

✅ R1 csv run 1 graded by code

W02 (preprint of W03) and W42 (preprint of W31).

JSON: {"works": ["W02", "W42"]}

✅ R1 csv run 2 graded by code

W02 and W42.
*Reasoning:* These are the PPR records with `version_of` set (to W03 and W31).

JSON: {"works": ["W02", "W42"]}

✅ R1 csv run 3 graded by code

W02 and W42. W02 is a preprint of W03, and W42 is a preprint of W31.

JSON: {"works": ["W02", "W42"]}

✅ R1 csv run 4 graded by code

W02 (version of W03) and W42 (version of W31).

JSON: {"works": ["W02", "W42"]}

✅ R1 csv run 5 graded by code

W02 and W42. These are the only records with a version_of link to another work in the data: W02 to W03, and W42 to W31.

JSON: {"works": ["W02", "W42"]}

✅ R2 rdf run 1 graded by code

W02 (versionOf W03) and W42 (versionOf W31).

JSON: {"works": ["W02", "W42"]}

✅ R2 rdf run 2 graded by code

W02 (versionOf W03) and W42 (versionOf W31). Both are PPR preprints whose parent works are in the data.

JSON: {"works": ["W02", "W42"]}

✅ R2 rdf run 3 graded by code

W02 (preprint of W03) and W42 (preprint of W31).

JSON: {"works": ["W02", "W42"]}

✅ R2 rdf run 4 graded by code

W02 and W42. These are the two works marked PPR with `versionOf` pointing to another work in the data.

JSON: {"works": ["W02", "W42"]}

✅ R2 rdf run 5 graded by code

W02 and W42. W02 is a preprint of W03, and W42 is a preprint of W31 (both `versionOf`).

JSON: {"works": ["W02", "W42"]}

✅ R6 rdf+ontology run 1 graded by code

W02 (a preprint of W03) and W42 (a preprint of W31).

JSON: {"works": ["W02", "W42"]}

✅ R6 rdf+ontology run 2 graded by code

W02 (preprint of W03) and W42 (preprint of W31).

JSON: {"works": ["W02", "W42"]}

✅ R6 rdf+ontology run 3 graded by code

W02, W42. W02 is a preprint of W03 and W42 is a preprint of W31.

JSON: {"works": ["W02", "W42"]}

✅ R6 rdf+ontology run 4 graded by code

W02 (preprint of W03) and W42 (preprint of W31).

JSON: {"works": ["W02", "W42"]}

✅ R6 rdf+ontology run 5 graded by code

W02 (preprint of W03) and W42 (preprint of W31).

JSON: {"works": ["W02", "W42"]}

✅ R5 csv+ontology run 1 graded by code

W02 and W42. W02 is a preprint of W03 and W42 is a preprint of W31. W18 is a preprint with no version link in the data.

JSON: {"works": ["W02", "W42"]}

✅ R5 csv+ontology run 2 graded by code

W02 (preprint of W03) and W42 (preprint of W31). W18 is a preprint with no published version in the data.

JSON: {"works": ["W02", "W42"]}

✅ R5 csv+ontology run 3 graded by code

W02, W42. These are the two preprints with a versionOf link to a published work in the data (W03 and W31).

JSON: {"works": ["W02", "W42"]}

✅ R5 csv+ontology run 4 graded by code

W02 and W42. Each has a version_of link to a published work in the data: W02 to W03, and W42 to W31.

JSON: {"works": ["W02", "W42"]}

✅ R5 csv+ontology run 5 graded by code

W02 (preprint of W03) and W42 (preprint of W31).

JSON: {"works": ["W02", "W42"]}

✅ R4 csv+markdown run 1 graded by code

W02 and W42. These are preprints whose published versions (W03 and W31) are in the data.

JSON: {"works": ["W02", "W42"]}

✅ R4 csv+markdown run 2 graded by code

W02 and W42. These are the preprints whose published versions are W03 and W31, respectively.

JSON: {"works": ["W02", "W42"]}

✅ R4 csv+markdown run 3 graded by code

W02 (preprint of W03) and W42 (preprint of W31). Both use version_of.

JSON: {"works": ["W02", "W42"]}

✅ R4 csv+markdown run 4 graded by code

W02 and W42, because their version_of fields point to W03 and W31.

JSON: {"works": ["W02", "W42"]}

✅ R4 csv+markdown run 5 graded by code

W02 (preprint of W03) and W42 (preprint of W31). W18 is a preprint but has no version link.

JSON: {"works": ["W02", "W42"]}

✅ R3 csv+padding run 1 graded by code

W02 and W42. W02 is a preprint of W03, and W42 is a preprint of W31.

JSON: {"works": ["W02", "W42"]}

✅ R3 csv+padding run 2 graded by code

W02 and W42. These are the only records with a version_of link, and each is a preprint of a work in the data (W03 and W31).

JSON: {"works": ["W02", "W42"]}

✅ R3 csv+padding run 3 graded by code

W02 and W42. W02 is a preprint of W03, and W42 is a preprint of W31. W18 is also PPR but has no version link.

JSON: {"works": ["W02", "W42"]}

✅ R3 csv+padding run 4 graded by code

W02 (preprint of W03) and W42 (preprint of W31).

JSON: {"works": ["W02", "W42"]}

✅ R3 csv+padding run 5 graded by code

W02 (version_of W03) and W42 (version_of W31).

JSON: {"works": ["W02", "W42"]}

❌ R10 executed run 1 graded by code

None. W02 (merged into W03) and W42 (merged into W31) are not works in the data, and no other work is a preprint of a work in the data.

JSON: {"works": []}

Why: works: expected ['W02', 'W42'], got []

❌ R10 executed run 2 graded by code

None. W02 (preprint) is merged into W03 and W42 into W31, but neither is a separate work in the data. W18 is a preprint with no published version in the data.

JSON: {"works": []}

Why: works: expected ['W02', 'W42'], got []

❌ R10 executed run 3 graded by code

None. W02 and W42 are preprint records merged into W03 and W31, but they are not rows in works.csv, and W18 (a preprint) has no published version in the data.

JSON: {"works": []}

Why: works: expected ['W02', 'W42'], got []

❌ R10 executed run 4 graded by code

None. W18 is the only preprint-type work, and no other work in the data is its published version. W02 and W42 are merged into W03 and W31, but they are not separate works in the table.

JSON: {"works": []}

Why: works: expected ['W02', 'W42'], got []

❌ R10 executed run 5 graded by code

None. The only merged preprint record is W02, which is folded into W03 and isn't a separate work; W18 is a preprint with no published version in the data.

JSON: {"works": []}

Why: works: expected ['W02', 'W42'], got []