claude-bot
caedf2e6f4
- extract_section.py: slice a book section out of a pdftotext -layout dump and list its labeled Theorem/Proposition/Lemma/Corollary/Definition items. - formalize.py: LLM-formalize a section into Lean 4 candidate statements (preferring Mathlib vocabulary) plus a definitions manifest. - check_statements.py: elaboration-only sanity check against a real Mathlib-backed Lean project (must run outside the Cowork sandbox, which has no Lean toolchain and can't run macOS binaries anyway). - build_library.py: assemble solved lean-bench results into a reusable .lean file, reusing each winning proof verbatim. - llm.py: standalone OpenAI-compatible chat client + .env loader, kept independent of lean_agent so this pipeline works without it installed. - Source PDFs and raw/layout text dumps are gitignored (copyrighted material); only code and the final short Lean statement datasets are tracked.
83 lines
3.4 KiB
Python
83 lines
3.4 KiB
Python
"""Assemble a reusable Lean library file from a completed lean-bench run.
|
|
|
|
Only theorems that actually solved (results.jsonl success == true) go in; each one's
|
|
exact winning proof (its last, successful attempt) is reused verbatim, re-wrapped in the
|
|
same `theorem <id> : <statement> := by ...` shape lean-bench's verifier already checked,
|
|
so the assembled file carries no new proof risk beyond what that run already confirmed --
|
|
this script does not itself call Lean.
|
|
|
|
Plain `import ...` preludes are deduplicated and hoisted to the top of the file; any
|
|
other prelude content (a local definition, say) is kept attached to its own theorem
|
|
instead of being collapsed, since it isn't necessarily shared with the rest.
|
|
|
|
A library assembled this way is only as trustworthy as the run it came from: rerun
|
|
check_statements.py / lean-bench yourself before importing it into something else you
|
|
care about, and treat --module-name as documentation, not a real Lean module boundary
|
|
(this script emits one flat .lean file, not a package).
|
|
"""
|
|
import argparse
|
|
import json
|
|
from pathlib import Path
|
|
|
|
|
|
def load_jsonl(path):
|
|
return [json.loads(line) for line in path.read_text(encoding='utf-8').splitlines() if line.strip()]
|
|
|
|
|
|
def build(dataset_path, results_path):
|
|
dataset = {t['id']: t for t in load_jsonl(dataset_path)}
|
|
results = {r['id']: r for r in load_jsonl(results_path)}
|
|
|
|
shared_imports = set()
|
|
per_theorem_prelude = {}
|
|
for task_id, task in dataset.items():
|
|
prelude = task.get('prelude', '').strip()
|
|
if not prelude:
|
|
continue
|
|
if all(line.strip().startswith('import ') for line in prelude.splitlines()):
|
|
shared_imports.update(line.strip() for line in prelude.splitlines())
|
|
else:
|
|
per_theorem_prelude[task_id] = prelude
|
|
|
|
lines = ['-- Generated by textbook/build_library.py -- do not hand-edit proofs;',
|
|
'-- regenerate from a fresh lean-bench run instead.', '']
|
|
lines.extend(sorted(shared_imports))
|
|
lines.append('')
|
|
|
|
solved, skipped = [], []
|
|
for task_id, task in dataset.items():
|
|
result = results.get(task_id)
|
|
if not result or not result.get('success') or not result.get('attempts'):
|
|
skipped.append(task_id)
|
|
continue
|
|
proof = result['attempts'][-1]['proof']
|
|
comment = f'-- {task.get("source_label", task_id)}: {task.get("natural_language", "")}'.rstrip()
|
|
lines.append(comment)
|
|
if task_id in per_theorem_prelude:
|
|
lines.append(per_theorem_prelude[task_id])
|
|
lean_name = task_id.replace('-', '_')
|
|
lines.append(f'theorem {lean_name} : {task["statement"]} := by')
|
|
lines.extend(' ' + line for line in proof.splitlines())
|
|
lines.append('')
|
|
solved.append(task_id)
|
|
|
|
return '\n'.join(lines), solved, skipped
|
|
|
|
|
|
def main():
|
|
parser = argparse.ArgumentParser(description='Assemble a Lean library file from a solved lean-bench dataset')
|
|
parser.add_argument('dataset', type=Path)
|
|
parser.add_argument('results', type=Path, help="a lean-bench run's results.jsonl")
|
|
parser.add_argument('--out', type=Path, required=True)
|
|
args = parser.parse_args()
|
|
|
|
text, solved, skipped = build(args.dataset, args.results)
|
|
args.out.write_text(text + '\n', encoding='utf-8')
|
|
print(f'{len(solved)} theorems assembled -> {args.out}')
|
|
if skipped:
|
|
print(f'{len(skipped)} skipped (not solved in this run): {", ".join(skipped)}')
|
|
|
|
|
|
if __name__ == '__main__':
|
|
main()
|