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
README.mdPublic entries: Python and R. Passing coverage requires an installed inventory.
Goal: carry each collected vital signs record through and add one body surface area (BSA) record for each subject and visit that has both a height and a weight result.
Input: collected vital signs with height records coded
HEIGHT and weight records coded WEIGHT; height is collected
in centimeters and weight in kilograms.
Variables:
AVALkeeps each collected result. On a body surface area record it is the Mosteller value: the square root of height in centimeters times weight in kilograms, divided by 3600. No record is added when the visit's height or weight is absent or has no result.DTYPEisCALCULATIONon a body surface area record and blank on a collected record.
Inputs
Under review1 source fileinput/advs.csv
Edit13 rows| STUDYID | USUBJID | PARAMCD | PARAM | AVAL | VISIT |
|---|---|---|---|---|---|
| YAMAA-01 | HEIGHT | Height (cm) | 170.5 | BASELINE | |
| YAMAA-01 | WEIGHT | Weight (kg) | 75.2 | BASELINE | |
| YAMAA-01 | WEIGHT | Weight (kg) | 76.0 | WEEK 2 | |
| YAMAA-01 | HEIGHT | Height (cm) | 165.0 | BASELINE | |
| YAMAA-01 | WEIGHT | Weight (kg) | 60.5 | BASELINE | |
| YAMAA-01 | WEIGHT | Weight (kg) | 80.0 | BASELINE | |
| YAMAA-01 | HEIGHT | Height (cm) | 180.0 | BASELINE | |
| YAMAA-01 | WEIGHT | Weight (kg) | — | BASELINE | |
| YAMAA-01 | HEIGHT | Height (cm) | 180.0 | WEEK 4 | |
| YAMAA-01 | WEIGHT | Weight (kg) | 82.0 | WEEK 4 | |
| YAMAA-01 | HEIGHT | Height (cm) | 172.0 | BASELINE | |
| YAMAA-01 | HEIGHT | Height (cm) | 175.0 | BASELINE | |
| YAMAA-01 | WEIGHT | Weight (kg) | 0.0 | BASELINE |
Expected output
Under review17 expected rowsexpected/advs.csv
Edit17 rows| STUDYID | USUBJID | PARAMCD | PARAM | AVAL | VISIT | DTYPE |
|---|---|---|---|---|---|---|
| YAMAA-01 | HEIGHT | Height (cm) | 170.5 | BASELINE | — | |
| YAMAA-01 | WEIGHT | Weight (kg) | 75.2 | BASELINE | — | |
| YAMAA-01 | WEIGHT | Weight (kg) | 76 | WEEK 2 | — | |
| YAMAA-01 | HEIGHT | Height (cm) | 165 | BASELINE | — | |
| YAMAA-01 | WEIGHT | Weight (kg) | 60.5 | BASELINE | — | |
| YAMAA-01 | WEIGHT | Weight (kg) | 80 | BASELINE | — | |
| YAMAA-01 | HEIGHT | Height (cm) | 180 | BASELINE | — | |
| YAMAA-01 | WEIGHT | Weight (kg) | — | BASELINE | — | |
| YAMAA-01 | HEIGHT | Height (cm) | 180 | WEEK 4 | — | |
| YAMAA-01 | WEIGHT | Weight (kg) | 82 | WEEK 4 | — | |
| YAMAA-01 | HEIGHT | Height (cm) | 172 | BASELINE | — | |
| YAMAA-01 | HEIGHT | Height (cm) | 175 | BASELINE | — | |
| YAMAA-01 | WEIGHT | Weight (kg) | 0 | BASELINE | — | |
| YAMAA-01 | BSA | Body Surface Area (m^2) | 1.887208402788509 | BASELINE | CALCULATION | |
| YAMAA-01 | BSA | Body Surface Area (m^2) | 1.6652076947536205 | BASELINE | CALCULATION | |
| YAMAA-01 | BSA | Body Surface Area (m^2) | 2.0248456731316584 | WEEK 4 | CALCULATION | |
| YAMAA-01 | BSA | Body Surface Area (m^2) | 0 | BASELINE | CALCULATION |
Human review and assessment
| Dataset Name | Variable Name | Variable Label | Type | Codelist/Controlled Terms | Core | Computational Method | Origin |
|---|---|---|---|---|---|---|---|
| ADVS | STUDYID | Study Identifier | character | Copy value from ADVS_RAW.STUDYID. | Predecessor | ||
| ADVS | USUBJID | Unique Subject Identifier | character | Copy value from ADVS_RAW.USUBJID. | Predecessor | ||
| ADVS | PARAMCD | Parameter Code | character | Set per constructed row; see the Row construction sheet. | Derived | ||
| ADVS | PARAM | Parameter | character | Set per constructed row; see the Row construction sheet. | Derived | ||
| ADVS | AVAL | Analysis Value | numeric | Set per constructed row; see the Row construction sheet. | Derived | ||
| ADVS | VISIT | Visit Name | character | Copy value from ADVS_RAW.VISIT. | Predecessor | ||
| ADVS | DTYPE | Derivation Type | character | Set per constructed row; see the Row construction sheet. | Derived |
| Template | Include when | PARAMCD | PARAM | HEIGHT_VAL | WEIGHT_VAL | AVAL | DTYPE |
|---|---|---|---|---|---|---|---|
| collected | Copy ADVS_RAW.PARAMCD | Copy ADVS_RAW.PARAM | Constant "None" | Constant "None" | Copy ADVS_RAW.AVAL | Constant "None" | |
| derived_bsa | HEIGHT_VAL IS NOT NULL AND WEIGHT_VAL IS NOT NULL | Constant "BSA" | Constant "Body Surface Area (m^2)" | Aggregate ONLY(ADVS_RAW.AVAL) over records matching on the shared output keys, where ADVS_RAW.PARAMCD = 'HEIGHT' | Aggregate ONLY(ADVS_RAW.AVAL) over records matching on the shared output keys, where ADVS_RAW.PARAMCD = 'WEIGHT' | Compute SQRT(WEIGHT_VAL * HEIGHT_VAL / 3600) | Constant "CALCULATION" |
| 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 |
prompts/adam-advs-bsa/full.md
Edit19 linesFollowing CDISC ADaM standards, use the provided ADVS dataset to create an ADVS dataset with one record per subject per visit per parameter.
The output dataset should contain the following columns in this order: STUDYID, USUBJID, PARAMCD, PARAM, AVAL, VISIT, DTYPE
The output holds every collected record and adds one body surface area record for each subject and visit that has both a height result, coded "HEIGHT", and a weight result, coded "WEIGHT". On a body surface area record, PARAMCD is "BSA" and PARAM is "Body Surface Area (m^2)". On a body surface area record, AVAL is the Mosteller value: the square root of (height in centimeters times weight in kilograms divided by 3600), and AVAL is not rounded. No body surface area record is added when the visit's height or weight is absent or has no result. DTYPE is "CALCULATION" on a body surface area record and has no value on a collected record.
Read the source datasets from /app/input and save the completed dataset as /app/output/advs.csv.
prompts/adam-advs-bsa/conventions.md
Edit13 linesFollowing CDISC ADaM standards, use the provided ADVS dataset to create an ADVS dataset with one record per subject per visit per parameter.
The output dataset should contain the following columns in this order: STUDYID, USUBJID, PARAMCD, PARAM, AVAL, VISIT, DTYPE
On a body surface area record, PARAMCD is "BSA" and PARAM is "Body Surface Area (m^2)". On a body surface area record, AVAL is the Mosteller value, and AVAL is not rounded. DTYPE is "CALCULATION" or has no value.
Read the source datasets from /app/input and save the completed dataset as /app/output/advs.csv.
prompts/adam-advs-bsa/brief.md
Edit8 linesFollowing CDISC ADaM standards, use the provided ADVS dataset to create an ADVS dataset with one record per subject per visit per parameter.
The output dataset should contain the following columns in this order: STUDYID, USUBJID, PARAMCD, PARAM, AVAL, VISIT, DTYPE
Read the source datasets from /app/input and save the completed dataset as /app/output/advs.csv.
R
Edit3 lineslibrary(yamaa)yamaa_spec("spec.yaml")$run()$outputPython
Edit3 linesimport yamaayamaa.spec("spec.yaml").run().outputsolutions/adam-advs-bsa/result.R
Edit44 lines# Reference solution for the yamaa benchmark adam-advs-bsa (R track).## Written from the benchmark's full prompt and its inputs alone, as an agent# would write it. Harbor's oracle agent runs it to check that the prompt can# be solved and that the grader scores a correct answer 1.library(dplyr, warn.conflicts = FALSE)library(readr)raw <- read_csv( "/app/input/advs.csv", col_types = cols(AVAL = col_double(), .default = col_character()))# Every collected record stays in place.collected <- raw |> transmute(STUDYID, USUBJID, PARAMCD, PARAM, AVAL, VISIT, DTYPE = NA_character_)# The visit's height and weight results; a zero result still counts.heights <- raw |> filter(PARAMCD %in% "HEIGHT", !is.na(AVAL)) |> group_by(STUDYID, USUBJID, VISIT) |> summarise(HEIGHT_VAL = first(AVAL), .groups = "drop")weights <- raw |> filter(PARAMCD %in% "WEIGHT", !is.na(AVAL)) |> group_by(STUDYID, USUBJID, VISIT) |> summarise(WEIGHT_VAL = first(AVAL), .groups = "drop")# One body surface area record for each visit with both results.bsa <- heights |> inner_join(weights, by = c("STUDYID", "USUBJID", "VISIT")) |> transmute( STUDYID, USUBJID, PARAMCD = "BSA", PARAM = "Body Surface Area (m^2)", AVAL = sqrt(HEIGHT_VAL * WEIGHT_VAL / 3600), VISIT, DTYPE = "CALCULATION" )advs <- bind_rows(collected, bsa) |> arrange(USUBJID, VISIT, PARAMCD)dir.create("/app/output", showWarnings = FALSE)write_csv(advs, "/app/output/advs.csv", na = "")solutions/adam-advs-bsa/result.py
Edit79 lines# Reference solution for the yamaa benchmark adam-advs-bsa (Python track).## Written from the benchmark's full prompt and its inputs alone, as an agent# would write it. Harbor's oracle agent runs it to check that the prompt can# be solved and that the grader scores a correct answer 1."""Create an ADVS dataset with derived body surface area records.Reads the collected ADVS dataset from /app/input, keeps every collectedrecord, and adds one body surface area (BSA) record for each subject andvisit that has both a height result (PARAMCD "HEIGHT") and a weightresult (PARAMCD "WEIGHT") with a value. BSA uses the Mosteller formula,sqrt(height in cm * weight in kg / 3600), and is not rounded. A BSArecord carries DTYPE "CALCULATION"; collected records have no DTYPE."""import csvimport mathimport osINPUT_PATH = "/app/input/advs.csv"OUTPUT_PATH = "/app/output/advs.csv"COLUMNS = ["STUDYID", "USUBJID", "PARAMCD", "PARAM", "AVAL", "VISIT", "DTYPE"]def main(): with open(INPUT_PATH, newline="") as f: collected = list(csv.DictReader(f)) # Index height and weight results by study, subject and visit. heights = {} weights = {} for row in collected: aval = (row.get("AVAL") or "").strip() if not aval: continue key = (row["STUDYID"], row["USUBJID"], row["VISIT"]) if row["PARAMCD"] == "HEIGHT": heights[key] = float(aval) elif row["PARAMCD"] == "WEIGHT": weights[key] = float(aval) # Position of the last collected record of each subject and visit, # so a derived BSA record follows its source records. last_index = {} for i, row in enumerate(collected): key = (row["STUDYID"], row["USUBJID"], row["VISIT"]) last_index[key] = i out_rows = [] for i, row in enumerate(collected): out = {c: row.get(c, "") for c in COLUMNS} out["DTYPE"] = "" out_rows.append(out) key = (row["STUDYID"], row["USUBJID"], row["VISIT"]) if last_index[key] == i and key in heights and key in weights: bsa = math.sqrt(heights[key] * weights[key] / 3600.0) out_rows.append( { "STUDYID": key[0], "USUBJID": key[1], "PARAMCD": "BSA", "PARAM": "Body Surface Area (m^2)", "AVAL": repr(bsa), "VISIT": key[2], "DTYPE": "CALCULATION", } ) os.makedirs(os.path.dirname(OUTPUT_PATH), exist_ok=True) with open(OUTPUT_PATH, "w", newline="") as f: writer = csv.DictWriter(f, fieldnames=COLUMNS) writer.writeheader() writer.writerows(out_rows)if __name__ == "__main__": main()solutions/adam-advs-bsa/result.sas
Edit21 lines/* opensas reference solution for the yamaa benchmark adam-advs-bsa. Reads the benchmark inputs and derives the requested output. Execute with the existing opensas runtime: opensas /app/output/result.sas. */data advs; length STUDYID USUBJID PARAMCD PARAM VISIT $1024; infile "/app/input/advs.csv" dsd dlm="," firstobs=2 truncover lrecl=32767; input STUDYID : $char1024. USUBJID : $char1024. PARAMCD : $char1024. PARAM : $char1024. AVAL VISIT : $char1024.;run;proc sql; create table computed as select a.STUDYID,a.USUBJID,'BSA' as PARAMCD,'Body Surface Area (m^2)' as PARAM,sqrt(a.AVAL*b.AVAL/3600) as AVAL,a.VISIT,'CALCULATION' as DTYPE from advs as a inner join advs as b on a.STUDYID=b.STUDYID and a.USUBJID=b.USUBJID and a.VISIT=b.VISIT where a.PARAMCD='HEIGHT' and b.PARAMCD='WEIGHT' and not missing(a.AVAL) and not missing(b.AVAL);quit;data collected; length DTYPE $11; set advs; run;data result; set collected computed; run;proc sql; create table final as select STUDYID, USUBJID, PARAMCD, PARAM, AVAL, VISIT, DTYPE from result;quit;proc export data=final outfile="/app/output/advs.csv" dbms=csv replace; run;
yamaa