yamaa As a clinical trial statistician or programmer, answer two short questions in Your review: the task and the inputs. Agreeing with both approves this benchmark; disagreeing with either needs a comment. Propose a fix with the Edit button on any source file, or add it to your comments.
We suggest spending no more than 5 minutes on a review. The other tabs beside Your review are background for assessment, not under review.
Summary
EditUnder reviewWhat this benchmark meansREADME.mdPublic entries: Python and R. Passing coverage requires an installed inventory.
Goal: show that a donor selection cannot reduce a whole study inside the distance it computes for each candidate donor.
Input: spec.yaml reads one subjects file: study, subject, baseline age,
baseline score and an observed lesion count, missing for some subjects. It
would copy a missing count from the subject of the same study whose age lies
nearest, scaling the age difference by the study standard deviation.
Note: the distance is computed once for each candidate donor, from that donor's record and the subject being imputed, so a standard deviation over the whole study has no records to reduce there. The run stops before any row is built, and the finding names the place such a value is read from.
How to fix
Reduce the study in a column, and read that column in the distance through the output domain's name:
columns:
- name: SDAGE
type: float
derivation: {aggregate: {expr: "STDDEV(AGE)", group_by: [STUDYID]}}
intermediates:
- id: DONOR
derivations:
DIST: "ABS(AGE - LESION.AGE) / LESION.SDAGE"
Expected failure
Editthe run is rejected; no artifact is acceptedexpected/error.yaml- phase
- validation
- condition
- prohibited_function
- rule
- FORMULA-13
expected/error.yaml
phase: validation
condition: prohibited_function
spec_paths:
- intermediates.DONOR.derivations.DIST
rule: FORMULA-13
context:
expr: ABS(AGE - LESION.AGE) / STDDEV(AGE)
function: STDDEV
hint: reduce it in a column's aggregate expression and read that column here as LESION.COLUMN
Inputs
Under review1 source fileinput/subjects.csv
Edit10 rows| STUDYID | USUBJID | AGE | BSCORE | OUTCOME |
|---|---|---|---|---|
| S1 | 52 | 10 | 2 | |
| S1 | 61 | 14 | 5 | |
| S1 | 55 | 11 | 3 | |
| S1 | 54 | 12 | — | |
| S1 | — | 11 | 9 | |
| S2 | 40 | 8 | 1 | |
| S2 | 44 | 10 | 4 | |
| S2 | 42 | 9 | — | |
| S3 | 50 | 10 | — | |
| S3 | 56 | 12 | — |
Unexpected Output
Under reviewNo artifact is producedNo fixture files in this directory.
Human review and assessment
| Variable Name | Variable Label | Type | Length | Controlled Terms or Format | Origin | Core | Conversion Definition | Variable Type | Variable Order | Comments for Define |
|---|---|---|---|---|---|---|---|---|---|---|
| STUDYID | Study Identifier | Char | Collected | Copy value from SUBJ.STUDYID. | SDTM | 1 | ||||
| USUBJID | Unique Subject Identifier | Char | Collected | Copy value from SUBJ.USUBJID. | SDTM | 2 | ||||
| AGE | Age at Baseline | Num | Collected | Copy value from SUBJ.AGE. | SDTM | 3 | ||||
| OUTCOME | Observed Lesion Count | Num | Collected | Copy value from SUBJ.OUTCOME. | SDTM | 4 | ||||
| DONORID | Donor Subject Identifier | Char | Derived | Take USUBJID from the first SUBJ record matching on STUDYID, where SUBJ.OUTCOME IS NOT NULL AND SUBJ.DIST IS NOT NULL AND LESION.OUTCOME IS NULL, ordered by SUBJ.DIST then SUBJ.USUBJID, and no match yields blank. | SDTM | 5 | ||||
| AOUTCOME | Analysis Lesion Count | Num | Derived | First non-missing of: OUTCOME; OUTCOME from the first SUBJ record matching on STUDYID, where SUBJ.OUTCOME IS NOT NULL AND SUBJ.DIST IS NOT NULL AND LESION.OUTCOME IS NULL, ordered by SUBJ.DIST then SUBJ.USUBJID, and no match yields blank. | SDTM | 6 |
| Version | Date | Author | Description | Reviewer | Sign-off |
|---|---|---|---|---|---|
| 1.7 | 2026-10-20 | yamaa docs build | Read a specification in the 1.0 surface as its 0.5 counterpart; state that missing values stay missing where a mapping declares no missing handler, and leave out a declared missing answer that restates a handler's default | ||
| 1.6 | 2026-10-17 | yamaa docs build | Describe collected date parts written as ISO 8601 date text and times of day counted in seconds since midnight | ||
| 1.5 | 2026-10-17 | yamaa docs build | Name collected precision in words instead of letter codes; state imputation fallbacks, minimum source precision, bounds ignored outside the collected period, and invalid text with no handler as an error; describe date and datetime shifts, imputation flag codes, and partial text giving no date part | ||
| 1.4 | 2026-10-15 | yamaa docs build | State datetime precision codes through the hour and minute, and complete only the time parts a collected datetime lacks | ||
| 1.3 | 2026-09-29 | yamaa docs build | Show study codelist names, external dictionaries, and ISO 8601 formats in variable rows; list the document's codelist values and metadata | ||
| 1.2 | 2026-09-29 | yamaa docs build | Classify ADaM copies from a declared input as Predecessor and recodes as Derived, and SDTM recodes of locally derived columns as Derived | ||
| 1.1 | 2026-09-29 | yamaa docs build | Resolve lookups into the donor record they select, and give every derivation shape a plain-language rule instead of its raw YAML | ||
| 1.0 | yamaa docs build | Initial generation from spec.yaml |