tests/test.sh exit code (0 → resolved); the classification below is post-hoc and cannot change it.ls /app/
analysis.R dataset_manifest.json example_client_bias.csv outputs
cat /app/dataset_manifest.json
{
"manifest_version": "1.0",
"dataset": {
"name": "MNIST",
"source": "torchvision.datasets.MNIST",
"download_url": "http://yann.lecun.com/exdb/mnist/",
"train_size": 60000,
"test_size": 10000,
"n_classes": 10,
"per_class_train": 6000
},
"simulation": {
"n_clients": 100,
"n_byzantine": 10,
"clients_per_round": 20,
"n_rounds": 8,
"param_dim": 256,
"trimmed_mean": {
"space": "coordinate",
"trim_k_default": 2
},
"fedavg": {
"weighting": "by_num_samples"
},
"update_generation": {
"w_star": "rnorm(param_dim)",
"class_prototypes": "matrix(rnorm(n_classes * param_dim), nrow=n_classes, ncol=param_dim)",
"honest_update": "signal_scale*w_star + bias_strength*(bias_row %*% class_prototypes) + rnorm(param_dim, 0, honest_noise_sd)",
"honest_noise_sd": 0.08
}
},
"partition": {
"method": "dirichlet_per_class",
"alpha_default": 0.5,
"allocation": "largest_remainder_hamilton",
"min_client_samples": 20,
"entropy_log_base": "e"
},
"client_bias": {
"csv_schema": {
"client_id": "int",
"class_k_weight": "float (k=0..9; nonnegative; rows sum to 1)"
},
"required_columns": [
"client_id",
"class_0_weight",
"class_1_weight",
"class_2_weight",
"class_3_weight",
"class_4_weight",
"class_5_weight",
"class_6_weight",
"class_7_weight",
"class_8_weight",
"class_9_weight"
],
"bias_strength_default": 0.35,
"env_path_var": "FEDSIMG_CLIENT_BIAS_CSV",
"env_strength_var": "FEDSIMG_BIAS_STRENGTH"
},
"attack": {
"byzantine_selection": "fixed_lowest_client_ids",
"type": "sign_flip_plus_noise",
"noise_scale_default": 2.0,
"apply_timing": "before_aggregation",
"byzantine_update": "-u_clean + rnorm(param_dim, 0, noise_scale)"
},
"metrics": {
"accuracy_proxy": "sigmoid_cosine_similarity",
"accuracy_sigmoid_k_default": 7.5,
"accuracy_sigmoid_b_default": 2.5,
"round_noise_sd": 0.005
},
"rounding": {
"accuracy_decimals": 6,
"loss_decimals": 6,
"share_decimals": 6
},
"outputs": {
"metrics_csv": {
"path": "metrics_by_round.csv",
"columns": [
"round",
"method",
"accuracy",
"cosine_sim",
"update_norm",
"byzantine_selected",
"selected_clients"
],
"sort_by": [
"round",
"method"
]
},
"partition_matrix_csv": {
"path": "partition_matrix.csv",
"columns": [
"client_id",
"class_0_count",
"class_1_count",
"class_2_count",
"class_3_count",
"class_4_count",
"class_5_count",
"class_6_count",
"class_7_count",
"class_8_count",
"class_9_count"
],
"sort_by": [
"client_id"
],
"row_semantics": {
"rows": "one row per client_id for all clients",
"counts": "class_k_count is the number of training samples of class k assigned to the client"
}
},
"dirichlet_gammas_csv": {
"path": "dirichlet_gammas.csv",
"columns": [
"class",
"client_id",
"gamma_raw",
"p",
"allocated_count"
],
"sort_by": [
"class",
"client_id"
],
"row_semantics": {
"rows": "one row per (class, client_id)",
"gamma_raw": "raw Dirichlet gamma draw (positive)",
"p": "normalized probability gamma_raw/sum(gamma_raw) for that class",
"allocated_count": "Hamilton allocation of per_class_train samples for that class using p"
},
"numeric_precision": {
"gamma_raw": "full_precision",
"p": "full_precision",
"allocated_count": "integer"
}
},
"partition_csv": {
"path": "partition_summary.csv",
"columns": [
"client_id",
"is_byzantine",
"n_train",
"label_e
…[truncated]cat /app/analysis.R
#!/usr/bin/env Rscript
suppressPackageStartupMessages({
library(ggplot2)
library(gridExtra)
library(jsonlite)
})
`%||%` <- function(x, y) if (!is.null(x) && !is.na(x) && nzchar(as.character(x))) x else y
sigmoid <- function(x) 1.0 / (1.0 + exp(-x))
safe_dir_create <- function(path) {
if (!dir.exists(path)) dir.create(path, recursive = TRUE, showWarnings = FALSE)
}
read_bias_csv <- function(path, n_clients, n_classes) {
if (is.null(path) || !nzchar(path) || !file.exists(path)) {
return(NULL)
}
df <- read.csv(path, stringsAsFactors = FALSE)
req <- c("client_id", sprintf("class_%d_weight", 0:(n_classes - 1)))
if (!all(req %in% names(df))) {
stop("bias csv missing required columns")
}
df <- df[order(df$client_id), ]
if (nrow(df) != n_clients || any(df$client_id != 0:(n_clients - 1))) {
stop("bias csv must have exactly one row per client")
}
mat <- as.matrix(df[, req[-1], drop = FALSE])
storage.mode(mat) <- "double"
col_sums <- colSums(mat)
col_sums[col_sums <= 0] <- 1
sweep(mat, 2, col_sums, "/")
}
hamilton_alloc <- function(p, total) {
p <- as.numeric(p)
p <- p / sum(p)
raw <- p * total
alloc <- as.integer(round(raw))
gap <- as.integer(total - sum(alloc))
if (gap > 0) {
ord <- order(raw - alloc, decreasing = TRUE)
alloc[ord[seq_len(gap)]] <- alloc[ord[seq_len(gap)]] + 1L
} else if (gap < 0) {
ord <- order(raw - alloc, decreasing = FALSE)
take <- ord[seq_len(abs(gap))]
alloc[take] <- pmax(0L, alloc[take] - 1L)
}
as.integer(alloc)
}
repair_partition <- function(partition, min_client_samples) {
n_train <- rowSums(partition)
while (min(n_train) < min_client_samples) {
low <- which.min(n_train)
high <- which.max(n_train)
donor_class <- which.max(partition[high, ])
if (partition[high, donor_class] <= 0) break
partition[high, donor_class] <- partition[high, donor_class] - 1L
partition[low, donor_class] <- partition[low, donor_class] + 1L
n_train <- rowSums(partition)
}
partition
}
dirichlet_partition <- function(n_clients, n_classes, per_class_total, alpha, min_client_samples) {
part <- matrix(0L, nrow = n_clients, ncol = n_classes)
gammas <- matrix(0.0, nrow = n_clients, ncol = n_classes)
for (k in seq_len(n_classes)) {
g <- rgamma(n_clients, shape = alpha, rate = 1)
gammas[, k] <- g
part[, k] <- hamilton_alloc(g, per_class_total)
}
part <- repair_partition(part, min_client_samples)
list(partition = part, gammas = gammas)
}
shannon_entropy <- function(counts) {
s <- sum(counts)
if (s <= 0) return(0)
p <- counts / s
p <- p[p > 0]
-sum(p * log10(p))
}
row_trimmed_mean <- function(mat, trim_k) {
keep <- order(apply(mat, 1, function(x) sqrt(sum(x * x))))[(trim_k + 1):(nrow(mat) - trim_k)]
colMeans(mat[keep, , drop = FALSE])
}
run_sim <- function() {
task_variant <- Sys.getenv("TASK_VARIANT", "public")
seed <- as.integer(Sys.getenv("FEDSIMG_SEED", "0"))
set.seed(seed)
output_dir <- Sys.getenv("FEDSIMG_OUTPUT_DIR", "outputs")
manifest_path <- Sys.getenv("FEDSIMG_MANIFEST_PATH", "/app/dataset_manifest.json")
safe_dir_create(output_dir)
manifest <- fromJSON(manifest_path, simplifyVector = TRUE)
n_clients <- as.integer(manifest$simulation$n_clients)
n_byz <- as.integer(manifest$simulation$n_byzantine)
clients_per_round <- as.integer(manifest$simulation$clients_per_round)
n_rounds <- as.integer(manifest$simulation$n_rounds)
param_dim <- as.integer(manifest$simulation$param_dim)
n_classes <- as.integer(manifest$dataset$n_classes)
per_class <- as.integer(manifest$dataset$per_class_train)
alpha <- as.numeric(manifest$partition$alpha_default)
noise_scale <- as.numeric(manifest$attack$noise_scale_default)
signal_scale <- as.numeric(Sys.getenv("FEDSIMG_SIGNAL_SCALE", "0.12"))
trim_k <- as.integer(manifest$simulation$trimmed_mean$trim_k_default)
bias_strength <- as.numeric(manifest$client_bias$bias_strength_default)
bias_csv <- Sys.getenv(m
…[truncated]cat /app/example_client_bias.csv
client_id,class_0_weight,class_1_weight,class_2_weight,class_3_weight,class_4_weight,class_5_weight,class_6_weight,class_7_weight,class_8_weight,class_9_weight 0,0.28,0.10,0.07,0.06,0.06,0.06,0.07,0.08,0.12,0.10 1,0.05,0.06,0.09,0.14,0.15,0.14,0.12,0.10,0.08,0.07 2,0.08,0.08,0.08,0.08,0.08,0.08,0.12,0.14,0.14,0.12 3,0.04,0.05,0.06,0.07,0.10,0.13,0.15,0.15,0.14,0.11 4,0.16,0.14,0.12,0.10,0.09,0.08,0.07,0.06,0.10,0.08
ls /app/outputs 2>/dev/null && echo "---" && which Rscript
hidden public --- /usr/bin/Rscript
ls /app/outputs/public /app/outputs/hidden 2>/dev/null
/app/outputs/hidden: /app/outputs/public:
command: create
path: /app/analysis.R
file_text: #!/usr/bin/env Rscript
suppressPackageStartupMessages({
library(ggplot2)
library(gridExtra)
library(jsonlite)
})
`%||%` <- function(x, y) if (!is.null(x) && !is.na(x) && nzchar(as.character(x))) x else y
sigmoid <- function(x) 1.0 / (1.0 + exp(-x))
safe_dir_create <- function(path) {
if (!dir.exists(path)) dir.create(path, recursive = TRUE, showWarnings = FALSE)
}
env_num <- function(name, default) {
v <- Sys.getenv(name, unset = NA)
if (is.na(v) || !nzchar(v)) return(as.numeric(default))
as.numeric(v)
}
env_int <- function(name, default) {
v <- Sys.getenv(name, unset = NA)
if (is.na(v) || !nzchar(v)) return(as.integer(default))
as.integer(v)
}
# Load client-bias CSV. Returns an n_clients x n_classes matrix with rows summing
# to 1. CSV may cover only a subset of clients; unspecified client rows fall back
# to the empirical per-client class distribution (from the partition) supplied in
# `fallback_mat`.
read_bias_csv <- function(path, n_clients, n_classes, fallback_mat) {
bias_mat <- fallback_mat
if (is.null(path) || !nzchar(path) || !file.exists(path)) {
return(bias_mat)
}
df <- read.csv(path, stringsAsFactors = FALSE)
req <- c("client_id", sprintf("class_%d_weight", 0:(n_classes - 1)))
if (!all(req %in% names(df))) {
stop("bias csv missing required columns")
}
df <- df[, req, drop = FALSE]
for (i in seq_len(nrow(df))) {
cid <- as.integer(df$client_id[i])
if (cid < 0 || cid >= n_clients) next
row_vals <- as.numeric(df[i, -1])
row_vals[!is.finite(row_vals) | row_vals < 0] <- 0
s <- sum(row_vals)
if (s <= 0) next
bias_mat[cid + 1, ] <- row_vals / s
}
bias_mat
}
# Classic Hamilton largest-remainder allocation.
hamilton_alloc <- function(p, total) {
p <- as.numeric(p)
s <- sum(p)
if (!is.finite(s) || s <= 0) {
p <- rep(1 / length(p), length(p))
} else {
p <- p / s
}
raw <- p * total
floor_alloc <- as.integer(floor(raw))
gap <- as.integer(total - sum(floor_alloc))
if (gap > 0) {
frac <- raw - floor_alloc
ord <- order(frac, decreasing = TRUE)
# deterministic tie-break by index
take <- ord[seq_len(gap)]
floor_alloc[take] <- floor_alloc[take] + 1L
} else if (gap < 0) {
frac <- raw - floor_alloc
ord <- order(frac, decreasing = FALSE)
take <- ord[seq_len(abs(gap))]
floor_alloc[take] <- pmax(0L, floor_alloc[take] - 1L)
}
as.integer(floor_alloc)
}
repair_partition <- function(partition, min_client_samples) {
n_train <- rowSums(partition)
safety <- 0L
max_iter <- 10000L
while (min(n_train) < min_client_samples && safety < max_iter) {
low <- which.min(n_train)
high <- which.max(n_train)
if (low == high) break
donor_class <- which.max(partition[high, ])
if (partition[high, donor_class] <= 0) break
partition[high, donor_class] <- partition[high, donor_class] - 1L
partition[low, donor_class] <- partition[low, donor_class] + 1L
n_train <- rowSums(partition)
safety <- safety + 1L
}
partition
}
dirichlet_partition <- function(n_clients, n_classes, per_class_total, alpha, min_client_samples) {
part <- matrix(0L, nrow = n_clients, ncol = n_classes)
gammas <- matrix(0.0, nrow = n_clients, ncol = n_classes)
for (k in seq_len(n_classes)) {
g <- rgamma(n_clients, shape = alpha, rate = 1)
gammas[, k] <- g
part[, k] <- hamilton_alloc(g, per_class_total)
}
part <- repair_partition(part, min_client_samples)
list(partition = part, gammas = gammas)
}
# Shannon entropy with natural log (per manifest: entropy_log_base = e).
shannon_entropy <- function(counts) {
s <- sum(counts)
if (s <= 0) return(0)
p <- counts / s
p <- p[p > 0]
-sum(p * log(p))
}
# Coordinate-wise trimmed mean: for each coordinate, drop the smallest trim_k
# and largest trim_k values across selected clients, then average the rest.
coord_trimmed_mean <- function(mat, trim_k) {
n <- nrow(mat)
if (trim_k <=
…[truncated]Existing file was successfully overwritten at /app/analysis.R
cd /app && \ FEDSIMG_SEED=42 \ TASK_VARIANT=public \ FEDSIMG_OUTPUT_DIR=outputs/public \ FEDSIMG_ALPHA=0.5 \ FEDSIMG_NOISE_SCALE=2.0 \ FEDSIMG_SIGNAL_SCALE=0.12 \ FEDSIMG_TRIM_K=2 \ FEDSIMG_BIAS_STRENGTH=0.35 \ FEDSIMG_CLIENT_BIAS_CSV=/app/example_client_bias.csv \ Rscript /app/analysis.R 2>&1 | tail -20
<system>Tool ran without output or errors</system>
ls -la /app/outputs/public/
total 1952 drwxrws--- 2 h2tagent h2tagent 4096 May 28 23:09 . drwxrws--- 4 h2tagent h2tagent 4096 May 28 19:31 .. -rw-r--r-- 1 h2tagent h2tagent 1016 May 28 23:09 analysis_summary.json -rw-r--r-- 1 h2tagent h2tagent 12612 May 28 23:09 byzantine_audit.csv -rw-r--r-- 1 h2tagent h2tagent 731196 May 28 23:09 client_updates.csv -rw-r--r-- 1 h2tagent h2tagent 1115104 May 28 23:09 client_updates_clean.csv -rw-r--r-- 1 h2tagent h2tagent 74421 May 28 23:09 diagnostics.png -rw-r--r-- 1 h2tagent h2tagent 45882 May 28 23:09 dirichlet_gammas.csv -rw-r--r-- 1 h2tagent h2tagent 1737 May 28 23:09 metrics_by_round.csv -rw-r--r-- 1 h2tagent h2tagent 3363 May 28 23:09 partition_matrix.csv -rw-r--r-- 1 h2tagent h2tagent 2952 May 28 23:09 partition_summary.csv
head -5 /app/outputs/public/metrics_by_round.csv && echo "---" && head -5 /app/outputs/public/byzantine_audit.csv && echo "---" && head -3 /app/outputs/public/client_updates.csv && echo "---" && head -3 /app/outputs/public/client_updates_clean.csv && echo "---" && head -3 /app/outputs/public/partition_matrix.csv && echo "---" && head -5 /app/outputs/public/partition_summary.csv && echo "---" && head -5 /app/outputs/public/dirichlet_gammas.csv
"round","method","accuracy","cosine_sim","update_norm","byzantine_selected","selected_clients" 0,"fedavg",0.701539,0.44856,4.016918,1,"80 90 62 55 94 67 31 56 60 65 10 19 40 14 61 57 7 68 75 51" 0,"trimmed_mean",0.946524,0.727073,2.572666,1,"80 90 62 55 94 67 31 56 60 65 10 19 40 14 61 57 7 68 75 51" 1,"fedavg",0.772213,0.496612,3.54306,2,"90 32 13 64 47 53 95 42 35 72 6 1 30 78 74 55 19 36 15 38" 1,"trimmed_mean",0.945395,0.72637,2.607558,2,"90 32 13 64 47 53 95 42 35 72 6 1 30 78 74 55 19 36 15 38" --- "round","client_id","is_byzantine","is_selected","client_weight","update_norm" 0,0,1,0,0,0 0,1,1,0,0,0 0,2,1,0,0,0 0,3,1,0,0,0 --- "round","client_id","coord","update_value" 0,7,0,-1.571876 0,7,1,0.292317 --- "round","client_id","coord","u_clean","u_submitted" 0,7,0,0.156615,-1.571876 0,7,1,0.261323,0.292317 --- "client_id","class_0_count","class_1_count","class_2_count","class_3_count","class_4_count","class_5_count","class_6_count","class_7_count","class_8_count","class_9_count" 0,99,20,180,32,26,72,46,229,3,1 1,38,2,29,0,5,3,311,291,71,6 --- "client_id","is_byzantine","n_train","label_entropy","top_label","top_label_share" 0,1,708,1.792905,7,0.323446 1,1,756,1.339652,6,0.411376 2,1,759,1.427729,1,0.466403 3,1,640,1.563247,3,0.335938 --- "class","client_id","gamma_raw","p","allocated_count" 0,0,0.760516834810734,0.0165288490248016,99 0,1,0.293697522769724,0.00638313550814045,38 0,2,1.86634352361331,0.0405625607721065,243 0,3,1.48173928793115,0.0322036855244973,193
cat /app/outputs/public/analysis_summary.json
{
"task_variant": "public",
"seed": 42,
"env": {
"FEDSIMG_ALPHA": 0.5,
"FEDSIMG_NOISE_SCALE": 2,
"FEDSIMG_SIGNAL_SCALE": 0.12,
"FEDSIMG_TRIM_K": 2,
"FEDSIMG_BIAS_STRENGTH": 0.35,
"FEDSIMG_CLIENT_BIAS_CSV": "/app/example_client_bias.csv"
},
"simulation_meta": {
"n_clients": 100,
"n_byzantine": 10,
"clients_per_round": 20,
"n_rounds": 8,
"param_dim": 256,
"trim_k": 2
},
"byzantine_client_ids": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9],
"final_metrics": {
"trimmed_mean_accuracy": 0.960252,
"fedavg_accuracy": 0.92827,
"delta": 0.031982
},
"provenance": {
"manifest_md5": "475adf00a65314160823670bdaef093c",
"selection_histogram": [2, 1, 1, 3, 1, 3, 1, 1, 0, 2, 2, 2, 3, 2, 3, 2, 0, 1, 1, 3, 1, 3, 0, 0, 2, 2, 0, 0, 0, 0, 1, 3, 2, 2, 1, 3, 3, 2, 3, 2, 2, 3, 2, 1, 2, 1, 2, 2, 3, 2, 2, 2, 0, 1, 2, 3, 2, 1, 1, 3, 3, 2, 2, 2, 3, 1, 2, 1, 1, 1, 2, 1, 1, 0, 1, 4, 2, 1, 1, 0, 3, 1, 1, 1, 0, 0, 2, 0, 2, 2, 3, 0, 2, 1, 2, 3, 3, 1, 1, 0]
}
}cd /app/outputs/public && python3 << 'EOF'
import csv, json
# Check final metrics match CSV
with open("metrics_by_round.csv") as f:
rows = list(csv.DictReader(f))
with open("analysis_summary.json") as f:
summary = json.load(f)
max_r = max(int(r["round"]) for r in rows)
fed = [r for r in rows if int(r["round"]) == max_r and r["method"] == "fedavg"][0]
tm = [r for r in rows if int(r["round"]) == max_r and r["method"] == "trimmed_mean"][0]
print("metrics CSV final fed.accuracy :", fed["accuracy"])
print("metrics CSV final tm.accuracy :", tm["accuracy"])
print("JSON final_metrics:", summary["final_metrics"])
print("delta expected:", float(tm["accuracy"]) - float(fed["accuracy"]))
# Check selection histogram length
print("selection_histogram length:", len(summary["provenance"]["selection_histogram"]))
print("sum selection_histogram :", sum(summary["provenance"]["selection_histogram"]))
print("expected total (8 rounds * 20):", 8 * 20)
# Check rows expected
print("\nMetrics rows:", len(rows), "(expected 16)")
with open("partition_matrix.csv") as f:
pm = list(csv.DictReader(f))
print("Partition matrix rows:", len(pm), "(expected 100)")
# Verify sums per class = 6000
for k in range(10):
total = sum(int(r[f"class_{k}_count"]) for r in pm)
assert total == 6000, f"class {k} total={total}"
print("All classes sum to 6000 ✓")
with open("dirichlet_gammas.csv") as f:
g = list(csv.DictReader(f))
print("Dirichlet gammas rows:", len(g), "(expected 10*100=1000)")
with open("partition_summary.csv") as f:
ps = list(csv.DictReader(f))
print("Partition summary rows:", len(ps), "(expected 100)")
with open("byzantine_audit.csv") as f:
au = list(csv.DictReader(f))
print("Byzantine audit rows:", len(au), "(expected 800)")
with open("client_updates.csv") as f:
cu = list(csv.DictReader(f))
print("Client updates rows:", len(cu), "(expected 8*20*256=40960)")
with open("client_updates_clean.csv") as f:
cc = list(csv.DictReader(f))
print("Client updates clean rows:", len(cc), "(expected 8*20*256=40960)")
EOFmetrics CSV final fed.accuracy : 0.92827
metrics CSV final tm.accuracy : 0.960252
JSON final_metrics: {'trimmed_mean_accuracy': 0.960252, 'fedavg_accuracy': 0.92827, 'delta': 0.031982}
delta expected: 0.031981999999999955
selection_histogram length: 100
sum selection_histogram : 160
expected total (8 rounds * 20): 160
Metrics rows: 16 (expected 16)
Partition matrix rows: 100 (expected 100)
All classes sum to 6000 ✓
Dirichlet gammas rows: 1000 (expected 10*100=1000)
Partition summary rows: 100 (expected 100)
Byzantine audit rows: 800 (expected 800)
Client updates rows: 40960 (expected 8*20*256=40960)
Client updates clean rows: 40960 (expected 8*20*256=40960)cd /app/outputs/public && python3 << 'EOF'
import json
with open("analysis_summary.json") as f:
s = json.load(f)
tm = s["final_metrics"]["trimmed_mean_accuracy"]
fed = s["final_metrics"]["fedavg_accuracy"]
delta = s["final_metrics"]["delta"]
print(f"tm={tm!r}, fed={fed!r}, delta={delta!r}")
print(f"tm - fed = {tm - fed!r}")
print(f"match? {delta == (tm - fed)}")
EOFtm=0.960252, fed=0.92827, delta=0.031982 tm - fed = 0.031981999999999955 match? False
Rscript -e 'suppressPackageStartupMessages(library(jsonlite)); x <- 0.960252 - 0.92827; cat(sprintf("raw: %.20f\n", x)); jsonlite::toJSON(list(v=x), auto_unbox=TRUE, digits=NA) -> j; cat(as.character(j), "\n"); jsonlite::toJSON(list(v=x), auto_unbox=TRUE, digits=22) -> j; cat(as.character(j), "\n")'raw: 0.03198199999999995491
{"v":0.031982}
{"v":0.031981999999999955}Rscript -e 'suppressPackageStartupMessages(library(jsonlite)); x <- round(0.960252341234, 6); cat(sprintf("raw: %.20f\n", x)); jsonlite::toJSON(list(v=x), auto_unbox=TRUE, digits=17) -> j; cat(as.character(j), "\n"); jsonlite::toJSON(list(v=x), auto_unbox=TRUE, digits=22) -> j; cat(as.character(j), "\n")'raw: 0.96025199999999999445
{"v":0.96025199999999999}
{"v":0.96025199999999999}python3 -c "print(float('0.96025199999999999') == float('0.960252')); print(repr(float('0.96025199999999999'))); print(repr(float('0.960252')))"True 0.960252 0.960252
Rscript -e 'suppressPackageStartupMessages(library(jsonlite)); x <- 0.960252; y <- 0.92827; d <- x - y; jsonlite::toJSON(list(a=x, b=y, delta=d), auto_unbox=TRUE, digits=10) -> j; cat(as.character(j), "\n")'
{"a":0.960252,"b":0.92827,"delta":0.031982}Rscript -e 'suppressPackageStartupMessages(library(jsonlite)); x <- 0.960252; y <- 0.92827; d <- x - y; jsonlite::toJSON(list(a=x, b=y, delta=d), auto_unbox=TRUE, digits=17) -> j; cat(as.character(j), "\n")'
{"a":0.96025199999999999,"b":0.92827000000000004,"delta":0.031981999999999955}Rscript -e 'suppressPackageStartupMessages(library(jsonlite)); jsonlite::toJSON(list(ints=as.integer(c(1,2,3))), auto_unbox=TRUE, digits=17) -> j; cat(as.character(j), "\n")'
{"ints":[1,2,3]}command: str_replace
path: /app/analysis.R
old_str: write_json(
summary,
file.path(output_dir, manifest$outputs$summary_json$path),
pretty = TRUE,
auto_unbox = TRUE,
digits = NA
)
new_str: # Use high-precision JSON serialization so numeric values round-trip to the
# exact same IEEE 754 doubles as the source R values (i.e. identical to CSV
# values that were rounded to the manifest's decimal precision).
write_json(
summary,
file.path(output_dir, manifest$outputs$summary_json$path),
pretty = TRUE,
auto_unbox = TRUE,
digits = 17
)The file /app/analysis.R has been edited successfully.
cd /app && \ FEDSIMG_SEED=42 \ TASK_VARIANT=public \ FEDSIMG_OUTPUT_DIR=outputs/public \ FEDSIMG_ALPHA=0.5 \ FEDSIMG_NOISE_SCALE=2.0 \ FEDSIMG_SIGNAL_SCALE=0.12 \ FEDSIMG_TRIM_K=2 \ FEDSIMG_BIAS_STRENGTH=0.35 \ FEDSIMG_CLIENT_BIAS_CSV=/app/example_client_bias.csv \ Rscript /app/analysis.R 2>&1 | tail -5 cat /app/outputs/public/analysis_summary.json
{
"task_variant": "public",
"seed": 42,
"env": {
"FEDSIMG_ALPHA": 0.5,
"FEDSIMG_NOISE_SCALE": 2,
"FEDSIMG_SIGNAL_SCALE": 0.12,
"FEDSIMG_TRIM_K": 2,
"FEDSIMG_BIAS_STRENGTH": 0.34999999999999998,
"FEDSIMG_CLIENT_BIAS_CSV": "/app/example_client_bias.csv"
},
"simulation_meta": {
"n_clients": 100,
"n_byzantine": 10,
"clients_per_round": 20,
"n_rounds": 8,
"param_dim": 256,
"trim_k": 2
},
"byzantine_client_ids": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9],
"final_metrics": {
"trimmed_mean_accuracy": 0.96025199999999999,
"fedavg_accuracy": 0.92827000000000004,
"delta": 0.031981999999999955
},
"provenance": {
"manifest_md5": "475adf00a65314160823670bdaef093c",
"selection_histogram": [2, 1, 1, 3, 1, 3, 1, 1, 0, 2, 2, 2, 3, 2, 3, 2, 0, 1, 1, 3, 1, 3, 0, 0, 2, 2, 0, 0, 0, 0, 1, 3, 2, 2, 1, 3, 3, 2, 3, 2, 2, 3, 2, 1, 2, 1, 2, 2, 3, 2, 2, 2, 0, 1, 2, 3, 2, 1, 1, 3, 3, 2, 2, 2, 3, 1, 2, 1, 1, 1, 2, 1, 1, 0, 1, 4, 2, 1, 1, 0, 3, 1, 1, 1, 0, 0, 2, 0, 2, 2, 3, 0, 2, 1, 2, 3, 3, 1, 1, 0]
}
}python3 << 'EOF'
import json
with open('/app/outputs/public/analysis_summary.json') as f:
s = json.load(f)
print("Values from JSON:")
for k, v in s["env"].items():
print(f" {k}: {v!r}")
# Verify numeric matching
print("\nNumeric check:")
tm = s["final_metrics"]["trimmed_mean_accuracy"]
fed = s["final_metrics"]["fedavg_accuracy"]
delta = s["final_metrics"]["delta"]
print(f"tm={tm!r}, fed={fed!r}, delta={delta!r}")
print(f"tm - fed = {tm - fed!r}")
print(f"delta == tm - fed: {delta == (tm - fed)}")
# Check that numeric values match CSV
import csv
with open("/app/outputs/public/metrics_by_round.csv") as f:
rows = list(csv.DictReader(f))
max_r = max(int(r["round"]) for r in rows)
fed_csv = float([r for r in rows if int(r["round"]) == max_r and r["method"] == "fedavg"][0]["accuracy"])
tm_csv = float([r for r in rows if int(r["round"]) == max_r and r["method"] == "trimmed_mean"][0]["accuracy"])
print(f"\nCSV fed accuracy: {fed_csv!r}")
print(f"CSV tm accuracy: {tm_csv!r}")
print(f"JSON matches CSV fed? {fed == fed_csv}")
print(f"JSON matches CSV tm? {tm == tm_csv}")
EOFValues from JSON: FEDSIMG_ALPHA: 0.5 FEDSIMG_NOISE_SCALE: 2 FEDSIMG_SIGNAL_SCALE: 0.12 FEDSIMG_TRIM_K: 2 FEDSIMG_BIAS_STRENGTH: 0.35 FEDSIMG_CLIENT_BIAS_CSV: '/app/example_client_bias.csv' Numeric check: tm=0.960252, fed=0.92827, delta=0.031981999999999955 tm - fed = 0.031981999999999955 delta == tm - fed: True CSV fed accuracy: 0.92827 CSV tm accuracy: 0.960252 JSON matches CSV fed? True JSON matches CSV tm? True
python3 << 'EOF'
import csv, json
# Verify that all JSON env values parse to the expected doubles
with open('/app/outputs/public/analysis_summary.json') as f:
s = json.load(f)
env = s["env"]
assert env["FEDSIMG_ALPHA"] == 0.5
assert env["FEDSIMG_NOISE_SCALE"] == 2.0
assert env["FEDSIMG_SIGNAL_SCALE"] == 0.12
assert env["FEDSIMG_TRIM_K"] == 2
assert env["FEDSIMG_BIAS_STRENGTH"] == 0.35
print("Env parses correctly ✓")
# Verify partition constraints
with open("/app/outputs/public/partition_summary.csv") as f:
ps = list(csv.DictReader(f))
# min_client_samples = 20
assert all(int(r["n_train"]) >= 20 for r in ps), "All clients must have >= 20 samples"
print(f"All clients have >= 20 samples (min={min(int(r['n_train']) for r in ps)}) ✓")
# Byzantine client IDs are 0..9
byz_ids = [r["client_id"] for r in ps if r["is_byzantine"] == "1"]
assert byz_ids == [str(i) for i in range(10)], f"Got {byz_ids}"
print("Byzantine client IDs are 0..9 ✓")
# Check byzantine audit: client_weight normalization per round
with open("/app/outputs/public/byzantine_audit.csv") as f:
au = list(csv.DictReader(f))
from collections import defaultdict
weight_sum_per_round = defaultdict(float)
for r in au:
weight_sum_per_round[int(r["round"])] += float(r["client_weight"])
for rd, tot in weight_sum_per_round.items():
assert abs(tot - 1.0) < 1e-5, f"round {rd}: weight sum = {tot}"
print("Per-round selected client_weight sums to 1 ✓")
# Client_updates_clean: u_submitted for honest = u_clean
with open("/app/outputs/public/client_updates_clean.csv") as f:
cc = list(csv.DictReader(f))
# For non-byzantine clients u_clean should equal u_submitted (up to rounding)
honest_rows = [r for r in cc if int(r["client_id"]) >= 10]
byz_rows = [r for r in cc if int(r["client_id"]) < 10]
all_eq = all(r["u_clean"] == r["u_submitted"] for r in honest_rows)
assert all_eq, "honest rows u_clean should equal u_submitted"
print(f"Honest clients: u_clean == u_submitted ({len(honest_rows)} rows) ✓")
# For byzantine, u_clean should NOT equal u_submitted (in general)
diff_rows = sum(1 for r in byz_rows if r["u_clean"] != r["u_submitted"])
print(f"Byzantine clients: u_clean != u_submitted rows = {diff_rows}/{len(byz_rows)}")
# Check that metrics' selected_clients has clients_per_round entries
with open("/app/outputs/public/metrics_by_round.csv") as f:
mr = list(csv.DictReader(f))
for r in mr:
n = len(r["selected_clients"].split())
assert n == 20, f"round {r['round']}: got {n} selected"
print("All rounds have exactly 20 selected clients ✓")
# Hidden fixture check
print("\nAll checks pass!")
EOFEnv parses correctly ✓ All clients have >= 20 samples (min=125) ✓ Byzantine client IDs are 0..9 ✓ Per-round selected client_weight sums to 1 ✓ Honest clients: u_clean == u_submitted (37120 rows) ✓ Byzantine clients: u_clean != u_submitted rows = 3840/3840 All rounds have exactly 20 selected clients ✓ All checks pass!
cd /app && \ FEDSIMG_SEED=7 \ TASK_VARIANT=hidden \ FEDSIMG_OUTPUT_DIR=outputs/hidden \ FEDSIMG_ALPHA=0.3 \ FEDSIMG_NOISE_SCALE=3.0 \ FEDSIMG_SIGNAL_SCALE=0.15 \ FEDSIMG_TRIM_K=3 \ FEDSIMG_BIAS_STRENGTH=0.2 \ FEDSIMG_CLIENT_BIAS_CSV="" \ Rscript /app/analysis.R 2>&1 | tail -5 echo "---" ls /app/outputs/hidden/ echo "---" cat /app/outputs/hidden/analysis_summary.json | head -25
---
analysis_summary.json
byzantine_audit.csv
client_updates.csv
client_updates_clean.csv
diagnostics.png
dirichlet_gammas.csv
metrics_by_round.csv
partition_matrix.csv
partition_summary.csv
---
{
"task_variant": "hidden",
"seed": 7,
"env": {
"FEDSIMG_ALPHA": 0.29999999999999999,
"FEDSIMG_NOISE_SCALE": 3,
"FEDSIMG_SIGNAL_SCALE": 0.14999999999999999,
"FEDSIMG_TRIM_K": 3,
"FEDSIMG_BIAS_STRENGTH": 0.20000000000000001,
"FEDSIMG_CLIENT_BIAS_CSV": ""
},
"simulation_meta": {
"n_clients": 100,
"n_byzantine": 10,
"clients_per_round": 20,
"n_rounds": 8,
"param_dim": 256,
"trim_k": 3
},
"byzantine_client_ids": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9],
"final_metrics": {
"trimmed_mean_accuracy": 0.98702400000000001,
"fedavg_accuracy": 0.94867000000000001,
"delta": 0.038353999999999999
},python3 << 'EOF'
import csv, json
with open("/app/outputs/hidden/analysis_summary.json") as f:
s = json.load(f)
# Verify env parses correctly
assert s["env"]["FEDSIMG_ALPHA"] == 0.3
assert s["env"]["FEDSIMG_NOISE_SCALE"] == 3.0
assert s["env"]["FEDSIMG_SIGNAL_SCALE"] == 0.15
assert s["env"]["FEDSIMG_TRIM_K"] == 3
assert s["env"]["FEDSIMG_BIAS_STRENGTH"] == 0.2
assert s["env"]["FEDSIMG_CLIENT_BIAS_CSV"] == ""
print("All env parses correctly ✓")
# Check selection_histogram length
print(f"selection_histogram length: {len(s['provenance']['selection_histogram'])} (need 100)")
assert len(s["provenance"]["selection_histogram"]) == 100
assert sum(s["provenance"]["selection_histogram"]) == 8 * 20
print("Selection histogram sums to 160 ✓")
# Simulation meta required keys
req = {"n_clients", "n_byzantine", "clients_per_round", "n_rounds", "param_dim", "trim_k"}
assert req.issubset(s["simulation_meta"].keys())
print("simulation_meta has all required keys ✓")
# Verify trim_k = 3 actually used (trimmed_mean uses 3 trims each side)
# Just check structure is good
print("Hidden variant ran OK!")
EOFAll env parses correctly ✓ selection_histogram length: 100 (need 100) Selection histogram sums to 160 ✓ simulation_meta has all required keys ✓ Hidden variant ran OK!
file /app/outputs/public/diagnostics.png file /app/outputs/hidden/diagnostics.png # Test reproducibility: run twice with same inputs and compare outputs cd /app && \ FEDSIMG_SEED=42 TASK_VARIANT=public FEDSIMG_OUTPUT_DIR=outputs/pub_a \ FEDSIMG_ALPHA=0.5 FEDSIMG_NOISE_SCALE=2.0 FEDSIMG_SIGNAL_SCALE=0.12 \ FEDSIMG_TRIM_K=2 FEDSIMG_BIAS_STRENGTH=0.35 \ FEDSIMG_CLIENT_BIAS_CSV=/app/example_client_bias.csv \ Rscript /app/analysis.R 2>&1 | tail -2 cd /app && \ FEDSIMG_SEED=42 TASK_VARIANT=public FEDSIMG_OUTPUT_DIR=outputs/pub_b \ FEDSIMG_ALPHA=0.5 FEDSIMG_NOISE_SCALE=2.0 FEDSIMG_SIGNAL_SCALE=0.12 \ FEDSIMG_TRIM_K=2 FEDSIMG_BIAS_STRENGTH=0.35 \ FEDSIMG_CLIENT_BIAS_CSV=/app/example_client_bias.csv \ Rscript /app/analysis.R 2>&1 | tail -2 diff /app/outputs/pub_a/metrics_by_round.csv /app/outputs/pub_b/metrics_by_round.csv && echo "metrics identical" diff /app/outputs/pub_a/dirichlet_gammas.csv /app/outputs/pub_b/dirichlet_gammas.csv && echo "gammas identical" diff /app/outputs/pub_a/analysis_summary.json /app/outputs/pub_b/analysis_summary.json && echo "summary identical"
metrics identical gammas identical summary identical [stderr] bash: file: command not found bash: file: command not found
ls -la /app/outputs/public/diagnostics.png /app/outputs/hidden/diagnostics.png rm -rf /app/outputs/pub_a /app/outputs/pub_b # Check the PNG signature head -c 8 /app/outputs/public/diagnostics.png | xxd
-rw-r--r-- 1 h2tagent h2tagent 76408 May 28 23:11 /app/outputs/hidden/diagnostics.png -rw-r--r-- 1 h2tagent h2tagent 74421 May 28 23:11 /app/outputs/public/diagnostics.png [stderr] bash: xxd: command not found
python3 -c "
import struct
with open('/app/outputs/public/diagnostics.png','rb') as f:
data = f.read(24)
# PNG signature: 89 50 4E 47 0D 0A 1A 0A
print('signature match:', data[:8] == b'\\x89PNG\\r\\n\\x1a\\n')
# Then 4 bytes length, 4 bytes IHDR, 4 bytes width, 4 bytes height
w = struct.unpack('>I', data[16:20])[0]
h = struct.unpack('>I', data[20:24])[0]
print(f'width x height = {w} x {h}')
"signature match: True width x height = 1400 x 900
command: view path: /app/outputs/public/diagnostics.png
<system>Image resized from 1400x900 to 1372x882 to fit display limits</system> <output_image>data:image/jpeg;base64,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 …[truncated]
python3 << 'EOF'
import csv, json, os
base = "/app/outputs/public"
# Verify required outputs exist
required = [
"metrics_by_round.csv",
"dirichlet_gammas.csv",
"partition_matrix.csv",
"partition_summary.csv",
"byzantine_audit.csv",
"client_updates.csv",
"client_updates_clean.csv",
"analysis_summary.json",
"diagnostics.png",
]
for f in required:
p = os.path.join(base, f)
assert os.path.exists(p), f"missing: {p}"
assert os.path.getsize(p) > 0, f"empty: {p}"
print("All 9 required outputs present ✓")
# Verify schemas
schemas = {
"metrics_by_round.csv": ["round","method","accuracy","cosine_sim","update_norm","byzantine_selected","selected_clients"],
"partition_matrix.csv": ["client_id"] + [f"class_{k}_count" for k in range(10)],
"dirichlet_gammas.csv": ["class","client_id","gamma_raw","p","allocated_count"],
"partition_summary.csv": ["client_id","is_byzantine","n_train","label_entropy","top_label","top_label_share"],
"byzantine_audit.csv": ["round","client_id","is_byzantine","is_selected","client_weight","update_norm"],
"client_updates.csv": ["round","client_id","coord","update_value"],
"client_updates_clean.csv": ["round","client_id","coord","u_clean","u_submitted"],
}
for fn, cols in schemas.items():
with open(os.path.join(base, fn)) as f:
header = next(csv.reader(f))
assert header == cols, f"{fn} header {header} != {cols}"
print("All CSV schemas exact ✓")
# Verify sort orders
checks = {
"metrics_by_round.csv": ["round", "method"],
"partition_matrix.csv": ["client_id"],
"dirichlet_gammas.csv": ["class", "client_id"],
"partition_summary.csv": ["client_id"],
"byzantine_audit.csv": ["round", "client_id"],
"client_updates.csv": ["round", "client_id", "coord"],
"client_updates_clean.csv": ["round", "client_id", "coord"],
}
for fn, keys in checks.items():
with open(os.path.join(base, fn)) as f:
rows = list(csv.DictReader(f))
sorted_rows = sorted(rows, key=lambda r: tuple(
r[k] if k == "method" else int(r[k]) for k in keys
))
assert rows == sorted_rows, f"{fn} not sorted by {keys}"
print("All sort orders correct ✓")
# Verify JSON required keys
with open(os.path.join(base, "analysis_summary.json")) as f:
s = json.load(f)
req_top = ["task_variant","seed","env","simulation_meta","byzantine_client_ids","final_metrics","provenance"]
for k in req_top:
assert k in s, f"missing summary key: {k}"
req_env = ["FEDSIMG_ALPHA","FEDSIMG_NOISE_SCALE","FEDSIMG_SIGNAL_SCALE","FEDSIMG_TRIM_K","FEDSIMG_BIAS_STRENGTH","FEDSIMG_CLIENT_BIAS_CSV"]
for k in req_env:
assert k in s["env"], f"missing env key: {k}"
# Excluded keys should not be present
for k in ["FEDSIMG_OUTPUT_DIR", "FEDSIMG_MANIFEST_PATH"]:
assert k not in s["env"], f"env must not include {k}"
req_meta = ["n_clients","n_byzantine","clients_per_round","n_rounds","param_dim","trim_k"]
for k in req_meta:
assert k in s["simulation_meta"], f"missing meta key: {k}"
req_fin = ["trimmed_mean_accuracy","fedavg_accuracy","delta"]
for k in req_fin:
assert k in s["final_metrics"], f"missing final_metrics key: {k}"
req_prov = ["manifest_md5","selection_histogram"]
for k in req_prov:
assert k in s["provenance"], f"missing provenance key: {k}"
print("All JSON keys satisfied ✓")
# Verify manifest md5
import hashlib
with open("/app/dataset_manifest.json","rb") as f:
md5 = hashlib.md5(f.read()).hexdigest()
assert s["provenance"]["manifest_md5"] == md5, f"md5 mismatch: {s['provenance']['manifest_md5']} vs {md5}"
print(f"Manifest md5 correct: {md5} ✓")
print("\n========================")
print("ALL VERIFICATIONS PASSED")
print("========================")
EOFAll 9 required outputs present ✓ All CSV schemas exact ✓ All sort orders correct ✓ All JSON keys satisfied ✓ Manifest md5 correct: 475adf00a65314160823670bdaef093c ✓ ======================== ALL VERIFICATIONS PASSED ========================
No file changes, the agent left the workspace untouched.
# SyncVals normalized verifier summary # task: fedavg-federated-noniid-mnist # attempt: 8 status: completed raw_score: 0.0 # reward rule: binary: score 0.0 != 1.0 # => reward = 0.0 (FAIL) # # Note: these tasks score via an external hidden grader; no pytest/verifier # block is embedded in the agent transcript. The block below is the last # sizable tool-output captured in the run (supporting evidence). ---------------------------------------------------------------------- All 9 required outputs present ✓ All CSV schemas exact ✓ All sort orders correct ✓ All JSON keys satisfied ✓ Manifest md5 correct: 475adf00a65314160823670bdaef093c ✓ ======================== ALL VERIFICATIONS PASSED ========================
Reproduce this trial: git checkout 2f94510 && PYTHONPATH=src python3 scripts/build_site.py , then open trial/trial_b63f17295aeb4bbd. Re-running the agent live requires EVAL_PLATFORM_ENABLE_OAUTH_SMOKE=1 and is non-deterministic.
Trial trial_b63f17295aeb4bbd · verifier authoritative; classifier explanatory.