Name Each Laboratory Parameter and Visit From the Study's Terminology

Review ask

As a clinical trial statistician or programmer, answer three short questions in Your review: the task, the inputs and outputs, and the AI-assisted review. Agreeing with all three approves this benchmark; disagreeing with any 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: derive the parameter name (PARAM) and the analysis visit (AVISIT) of each laboratory result from their codes.

Input: laboratory results with the study and subject identifiers, the test code, the numeric result and the visit number.

Variables:

PARAMCD is the parameter code, the collected test code.
PARAM is the name the study's parameter terminology gives the code, such as Alanine Aminotransferase (U/L) for ALT.
AVISITN is the analysis visit number, the collected visit number.
AVISIT is the name the study's visit terminology gives the visit number, such as Week 2 for 2; a visit number the terminology does not list is an unscheduled visit, Unscheduled.
AVAL is the numeric result.

Note: each name is stated once, beside its code in the study's terminology, and every dataset that names a parameter or a visit reads it from there, so no dataset can spell a name differently.

YAML specification

1 spec file

spec.yaml

Edit59 lines

1yamaa: "1.0"2type: spec3model: ADaM4domain: ADLB5keys: [STUDYID, USUBJID, PARAMCD, AVISITN]6input:7  LB:8    path: input/lb.csv9    types: {LBSTRESN: float, VISITNUM: int}1011output:12  path: adlb.csv13  columns: [STUDYID, USUBJID, PARAMCD, PARAM, AVISITN, AVISIT, AVAL]1415columns:16  - name: STUDYID17    type: str18    label: Study Identifier19    derivation: LB.STUDYID2021  - name: USUBJID22    type: str23    label: Unique Subject Identifier24    derivation: LB.USUBJID2526  - name: PARAMCD27    type: str28    label: Parameter Code29    derivation: LB.LBTESTCD3031  # The parameter name is the decode the project's PARAMCD codelist gives32  # the code, stated once there rather than restated here.33  - name: PARAM34    type: str35    label: Parameter36    derivation:37      decode:38        source: PARAMCD39        codelist: PARAMCD4041  - name: AVISITN42    type: int43    label: Analysis Visit (N)44    derivation: LB.VISITNUM4546  # A visit the codelist does not list is an unscheduled visit.47  - name: AVISIT48    type: str49    label: Analysis Visit50    derivation:51      decode:52        source: AVISITN53        codelist: AVISITN54        unmapped: Unscheduled5556  - name: AVAL57    type: float58    label: Analysis Value59    derivation: LB.LBSTRESN

Inputs

Under review1 source file

input/lb.csv

Edit5 rows

input/lb.csv
STUDYID	LBSEQ	LBTESTCD	LBSTRESN	VISITNUM
YAMAA-01	1	ALT	22	1
YAMAA-01	2	AST	30	1
YAMAA-01	3	ALT	41	2
YAMAA-01	1	AST	25	1
YAMAA-01	2	AST	27.5	99

Expected output

Under review5 expected rows

expected/adlb.csv

Edit5 rows

expected/adlb.csv
STUDYID	PARAMCD	PARAM	AVISITN	AVISIT	AVAL
YAMAA-01	ALT	Alanine Aminotransferase (U/L)	1	Baseline	22
YAMAA-01	AST	Aspartate Aminotransferase (U/L)	1	Baseline	30
YAMAA-01	ALT	Alanine Aminotransferase (U/L)	2	Week 2	41
YAMAA-01	AST	Aspartate Aminotransferase (U/L)	1	Baseline	25
YAMAA-01	AST	Aspartate Aminotransferase (U/L)	99	Unscheduled	27.5

Shaded columns are derived— = missing value

Human review and assessment

Dataset Name	Variable Name	Variable Label	Type	Computational Method	Origin
ADLB	STUDYID	Study Identifier	character	Copy value from LB.STUDYID.	Predecessor
ADLB	USUBJID	Unique Subject Identifier	character	Copy value from LB.USUBJID.	Predecessor
ADLB	PARAMCD	Parameter Code	character	Copy value from LB.LBTESTCD.	Predecessor
ADLB	PARAM	Parameter	character	Decode PARAMCD through codelist PARAMCD; missing values stay missing; unlisted values are errors.	Derived
ADLB	AVISITN	Analysis Visit (N)	numeric	Copy value from LB.VISITNUM.	Predecessor
ADLB	AVISIT	Analysis Visit	character	Decode AVISITN through codelist AVISITN; missing values stay missing; unlisted values → "Unscheduled".	Derived
ADLB	AVAL	Analysis Value	numeric	Copy value from LB.LBSTRESN.	Predecessor

Codelist ID	Name	Value	Decode	Extensible	SAS format
PARAMCD	Parameter Code	ALT	Alanine Aminotransferase (U/L)	No	$PARAMCD
PARAMCD	Parameter Code	AST	Aspartate Aminotransferase (U/L)	No	$PARAMCD
AVISITN	Analysis Visit	1	Baseline	No
AVISITN	Analysis Visit	2	Week 2	No

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

prompts/adam-adlb-parameter-names/full.md

Edit14 lines

Following CDISC ADaM standards, use the provided LB dataset to create an ADLB dataset with one record per subject per parameter per visit.

The output dataset should contain the following columns in this order: STUDYID, USUBJID, PARAMCD, PARAM, AVISITN, AVISIT, AVAL

PARAMCD is the laboratory test code. PARAM is 'Alanine Aminotransferase (U/L)' for ALT and 'Aspartate Aminotransferase (U/L)' for AST. AVISITN is the visit number. AVISIT is 'Baseline' for visit 1, 'Week 2' for visit 2 and 'Unscheduled' for any other visit. AVAL is the numeric standard result, not rounded.

Read the source datasets from /app/input and save the completed dataset as /app/output/adlb.csv.

prompts/adam-adlb-parameter-names/conventions.md

Edit13 lines

Following CDISC ADaM standards, use the provided LB dataset to create an ADLB dataset with one record per subject per parameter per visit.

The output dataset should contain the following columns in this order: STUDYID, USUBJID, PARAMCD, PARAM, AVISITN, AVISIT, AVAL

PARAM is 'Alanine Aminotransferase (U/L)' for ALT and 'Aspartate Aminotransferase (U/L)' for AST. AVISIT is 'Baseline' for visit 1, 'Week 2' for visit 2 and 'Unscheduled' for any other visit. AVAL is not rounded.

Read the source datasets from /app/input and save the completed dataset as /app/output/adlb.csv.

prompts/adam-adlb-parameter-names/brief.md

Edit8 lines

Following CDISC ADaM standards, use the provided LB dataset to create an ADLB dataset with one record per subject per parameter per visit.

The output dataset should contain the following columns in this order: STUDYID, USUBJID, PARAMCD, PARAM, AVISITN, AVISIT, AVAL

Read the source datasets from /app/input and save the completed dataset as /app/output/adlb.csv.

R

Edit3 lines

1library(yamaa)23yamaa_project("project.yaml")$spec("ADLB")$run()$output

Python

Edit3 lines

1import yamaa23yamaa.project("project.yaml").spec("ADLB").run().output

solutions/adam-adlb-parameter-names/result.R

Edit35 lines

1# Reference solution for the yamaa benchmark adam-adlb-parameter-names (R track).2#3# Written from the benchmark's full prompt and its inputs alone, as an agent4# would write it. Harbor's oracle agent runs it to check that the prompt can5# be solved and that the grader scores a correct answer 1.67library(dplyr, warn.conflicts = FALSE)8library(readr)910lb <- read_csv(11  "/app/input/lb.csv",12  col_types = cols(.default = col_character())13)1415param <- c(16  ALT = "Alanine Aminotransferase (U/L)",17  AST = "Aspartate Aminotransferase (U/L)"18)19adlb <- lb |>20  transmute(21    STUDYID,22    USUBJID,23    PARAMCD = LBTESTCD,24    PARAM = unname(param[LBTESTCD]),25    AVISITN = as.integer(VISITNUM),26    AVISIT = case_when(27      AVISITN == 1 ~ "Baseline",28      AVISITN == 2 ~ "Week 2",29      .default = "Unscheduled"30    ),31    AVAL = as.numeric(LBSTRESN)32  )3334dir.create("/app/output", showWarnings = FALSE)35write_csv(adlb, "/app/output/adlb.csv", na = "")

solutions/adam-adlb-parameter-names/result.py

Edit31 lines

1# Reference solution for the yamaa benchmark adam-adlb-parameter-names (Python track).2#3# Written from the benchmark's full prompt and its inputs alone, as an agent4# would write it. Harbor's oracle agent runs it to check that the prompt can5# be solved and that the grader scores a correct answer 1.67from pathlib import Path89import polars as pl1011lb = pl.read_csv("/app/input/lb.csv", infer_schema=False)1213param = {14    "ALT": "Alanine Aminotransferase (U/L)",15    "AST": "Aspartate Aminotransferase (U/L)",16}17visit = {"1": "Baseline", "2": "Week 2"}18adlb = lb.select(19    pl.col("STUDYID"),20    pl.col("USUBJID"),21    pl.col("LBTESTCD").alias("PARAMCD"),22    pl.col("LBTESTCD").replace_strict(param).alias("PARAM"),23    pl.col("VISITNUM").cast(pl.Int64).alias("AVISITN"),24    pl.col("VISITNUM")25    .replace_strict(visit, default="Unscheduled")26    .alias("AVISIT"),27    pl.col("LBSTRESN").cast(pl.Float64).alias("AVAL"),28)2930Path("/app/output").mkdir(exist_ok=True)31adlb.write_csv("/app/output/adlb.csv")

solutions/adam-adlb-parameter-names/result.sas

Edit29 lines

1/* opensas reference solution for the yamaa benchmark adam-adlb-parameter-names.2   Reads the benchmark inputs and derives the requested output.3   Execute with the existing opensas runtime: opensas /app/output/result.sas. */45data lb;6  length STUDYID USUBJID LBTESTCD $1024;7  infile "/app/input/lb.csv" dsd dlm="," firstobs=2 truncover lrecl=32767;8  input STUDYID : $char1024. USUBJID : $char1024. LBSEQ LBTESTCD : $char1024.9    LBSTRESN VISITNUM;10run;1112data result;13  set lb;14  length PARAMCD $8 PARAM $40 AVISIT $20;15  PARAMCD = LBTESTCD;16  if LBTESTCD = 'ALT' then PARAM = 'Alanine Aminotransferase (U/L)';17  else if LBTESTCD = 'AST' then PARAM = 'Aspartate Aminotransferase (U/L)';18  AVISITN = VISITNUM;19  if AVISITN = 1 then AVISIT = 'Baseline';20  else if AVISITN = 2 then AVISIT = 'Week 2';21  else AVISIT = 'Unscheduled';22  AVAL = LBSTRESN;23run;24proc sql;25  create table final as select STUDYID, USUBJID, PARAMCD, PARAM, AVISITN,26    AVISIT, AVAL27    from result;28quit;29proc export data=final outfile="/app/output/adlb.csv" dbms=csv replace; run;

input/lb.csv

expected/adlb.csv

Your review

Mapping spec

Agent prompt

prompts/adam-adlb-parameter-names/full.md

prompts/adam-adlb-parameter-names/conventions.md

prompts/adam-adlb-parameter-names/brief.md

yamaa code

R

Python

Solution without yamaa

solutions/adam-adlb-parameter-names/result.R

solutions/adam-adlb-parameter-names/result.py

solutions/adam-adlb-parameter-names/result.sas