Reject Non-Numeric Sum

Review ask

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 means

README.md

Public entries: Python and R. Passing coverage requires an installed inventory.

Goal: build one analysis record per collected adverse event, carrying ASEV and adding SEVTOT.

Input: collected adverse events with the severity word recorded in AESEV.

Variables:

ASEV would contain the severity word reported for the event, carried unchanged from the collected severity.
SEVTOT would be the subject's total severity burden, totalling the severity across all of their reported events and repeated on each of their event records.

Note: severity is recorded as words, and words have no total. Ordering the words and totalling their positions would be a real rule, but it is a different one, and the request never states the numbers it would use. The run is rejected before any data is read, so no artifact is accepted.

How to fix

Declare the study's numeric severity scale first, then total that numeric column:

- name: ASEVN
  type: int
  derivation:
    mapping:
      source: ASEV
      dict:
        MILD: 1
        MODERATE: 2
        SEVERE: 3

- name: SEVTOT
  type: int
  derivation:
    aggregate:
      group_by: [STUDYID, USUBJID]
      expr: "SUM(ASEVN)"

Keep the intermediate numeric column out of the artifact by leaving it off the artifact column list. The numeric assignments are analysis policy and must be confirmed rather than inferred from the order of the words.

Expected failure

Editthe run is rejected; no artifact is accepted

expected/error.yaml

phase: validation
condition: incompatible_input_type
rule: FORMULA-23

expected/error.yaml

phase: validation
condition: incompatible_input_type
spec_paths:
  - columns.SEVTOT.derivation.aggregate.expr
rule: FORMULA-23
context:
  source: ASEV
  expected: numeric
  actual: str

YAML specification

1 spec file

spec.yaml

Edit43 lines

1yamaa: "1.0"2type: spec3model: ADaM4domain: ADAE5keys: [STUDYID, USUBJID, AESEQ]6input:7  AE: input/ae.csv89output:10  path: adae.csv11  columns: [STUDYID, USUBJID, AESEQ, ASEV, SEVTOT]1213columns:14  - name: STUDYID15    type: str16    label: Study Identifier17    derivation: AE.STUDYID1819  - name: USUBJID20    type: str21    label: Unique Subject Identifier22    derivation: AE.USUBJID2324  - name: AESEQ25    type: int26    label: Sequence Number27    derivation: AE.AESEQ2829  - name: ASEV30    type: str31    label: Analysis Severity/Intensity32    derivation: AE.AESEV3334  # One total per subject, repeated on each of their event rows. ASEV35  # holds severity words (MILD, SEVERE), and SUM needs numbers, so the36  # run is rejected before any data is read.37  - name: SEVTOT38    type: float39    label: Total Severity Score40    derivation:41      aggregate:42        group_by: [STUDYID, USUBJID]43        expr: "SUM(ASEV)"

Inputs

Under review1 source file

input/ae.csv

Edit2 rows

input/ae.csv
STUDYID	USUBJID	AESEQ	AETERM	AESEV
PILOT7		1	Nausea	MILD
PILOT7		2	Fatigue	SEVERE

Unexpected Output

Under reviewNo artifact is produced

No fixture files in this directory.

Shaded columns are derived— = missing value

Human review and assessment

Dataset Name	Variable Name	Variable Label	Type	Computational Method	Origin
ADAE	STUDYID	Study Identifier	character	Copy value from AE.STUDYID.	Predecessor
ADAE	USUBJID	Unique Subject Identifier	character	Copy value from AE.USUBJID.	Predecessor
ADAE	AESEQ	Sequence Number	numeric	Copy value from AE.AESEQ.	Predecessor
ADAE	ASEV	Analysis Severity/Intensity	character	Copy value from AE.AESEV.	Predecessor
ADAE	SEVTOT	Total Severity Score	numeric	Aggregate SUM(ASEV) over records grouped by STUDYID, USUBJID, matching on the shared output keys.	Derived

Version	Date	Author	Description
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

How to fix

input/ae.csv

Your review

Mapping spec