Add arXiv paper draft #2

	name: CI

	on:
	push:
	branches:
	- main
	pull_request:

	permissions:
	contents: read

	jobs:
	test:
	name: Python tests
	runs-on: ubuntu-latest
	steps:
	- name: Check out repository
	uses: actions/checkout@v4

	- name: Set up Python
	uses: actions/setup-python@v5
	with:
	python-version: "3.11"
	cache: pip

	- name: Install package
	run: python -m pip install -e ".[dev,bench]"

	- name: Run tests
	run: python -m pytest -q

	- name: Build generalization scorecard
	run: \|
	python scripts/build_generalization_scorecard.py \
	--output-dir /tmp/l20_codeforge_scorecard_ci

	- name: Verify benchmark artifact hashes
	run: \|
	python - <<'PY'
	import hashlib
	from pathlib import Path

	expected = {
	"benchmarks/generalization_scorecard_2026_05_23/scorecard.json":
	"1eb0402378ea25732225b29d7ba367b6111ab3351e54cc7c01fa7646a7a12712",
	"benchmarks/livecodebench_full_release_v6_2026_05_22/full_n8_public_select_summary.json":
	"2a0ff919aa15eb9ecdf74824f7bf790a23f6d0197ef74970b6190c60e0e00772",
	"benchmarks/evalplus_l20_codeforge_2026_05_22/summary.csv":
	"08732bbb76450f92ef3c02fa97a163aba01f71028365072c205c5a3af45d5550",
	}
	for rel_path, expected_sha in expected.items():
	actual_sha = hashlib.sha256(Path(rel_path).read_bytes()).hexdigest()
	if actual_sha != expected_sha:
	raise SystemExit(f"{rel_path}: expected {expected_sha}, got {actual_sha}")
	print("benchmark artifact hashes verified")
	PY

Provide feedback