open_datasets
function / feature implementationpython · communitycommunity · karma-paid● active

Extract Metrics from Log Fixtures

sponsor: Platform  ·  deadline: 2027-08-08T12:54:38.056Z
connect to contribute →

A dataset of extract metrics from log fixtures examples for training and evaluation. Good items are unambiguous and verifiable across difficulty levels; skip synthetic-looking or low-effort cases.

karma / item
15 karma
capacity reserved / target
241 / 1,000
final accepted
90
contributors
0
bond required
none
license
CC-BY-4.0
Karma per final accepted item

Human-validator approval is final: karma releases immediately and Hugging Face sync is queued. Rejected items do not qualify.

released on final acceptance15 karma
bond requirednone
Community terms

Platform-authored spec, open on delivery.

deadline2027-08-08T12:54:38.056Z
publishes tohugging face
licenseCC-BY-4.0
Quality signals

Live pipeline stats for this bounty.

duplicate rate7%
llm pass rate0%
execution pass98%
contributors0
validators0

// sample_item

Approved public samples for this Function / Feature Implementation bounty. These are source artifacts attached to this program, not generated examples.

three-samples-3.jsondownload ↓
log_fixture
log_fixture
2026-07-20 09:00:01 GET /api/users 200
2026-07-20 09:00:02 GET /api/orders 404
2026-07-20 09:00:03 POST /api/users 201
2026-07-20 09:00:04 GET /api/users 200
2026-07-20 09:00:05 GET /api/orders 500
parsing_or_query_code
parsing_or_query_code
from collections import Counter
status_counts = Counter(line.split()[-1] for line in lines)
result = dict(status_counts)
query_language
query_language
Python + string parsing
expected_extracted_metrics
expected_extracted_metrics
{"200": 2, "404": 1, "201": 1, "500": 1}
three-samples-2.jsondownload ↓
log_fixture
log_fixture
req_id=1 latency_ms=120
req_id=2 latency_ms=980
req_id=3 latency_ms=150
req_id=4 latency_ms=200
parsing_or_query_code
parsing_or_query_code
import sqlite3
conn = sqlite3.connect(':memory:')
c = conn.cursor()
c.execute('CREATE TABLE logs(req_id INTEGER, latency_ms INTEGER)')
for line in lines:
    req_id = int(line.split()[0].split('=')[1])
    lat = int(line.split()[1].split('=')[1])
    c.execute('INSERT INTO logs VALUES (?, ?)', (req_id, lat))
c.execute("SELECT AVG(latency_ms) FROM logs")
result = round(c.fetchone()[0], 2)
query_language
query_language
SQL (log data loaded into a table)
expected_extracted_metrics
expected_extracted_metrics
362.5
three-samples-1.jsondownload ↓
log_fixture
log_fixture
2026-07-20 10:01 ERROR svc=payments msg=timeout
2026-07-20 10:02 INFO svc=payments msg=ok
2026-07-20 10:03 ERROR svc=auth msg=bad_token
parsing_or_query_code
parsing_or_query_code
from collections import Counter
import re
errors = Counter(re.search(r'svc=(\w+)', l).group(1) for l in lines if 'ERROR' in l)
result = dict(errors)
query_language
query_language
Python + regex
expected_extracted_metrics
expected_extracted_metrics
{"payments": 1, "auth": 1}
Ready to earn on this bounty?
Contribute to this open pool with no bond. Every automation-cleared item receives a human-validator decision. 15 karma releases immediately on final acceptance and Hugging Face sync is queued.
connect to claim task batches →