Zayden-Jung
d3555d9a52
Replaces the previous tree entirely. The pipeline is four separable pieces, each
testable on its own:
1. leanbench/llm.py provider-neutral OpenAI-compatible connector, stdlib only,
with retries, JSON coercion and a scripted client so the
rest of the code is testable without a network.
2. leanbench/detect.py per-page detection of formalizable mathematics. Case 1 is
mathematics asserted as fact (definition/theorem/lemma/...,
deliberately not sub-classified); case 2 is a problem left
open to the reader. Hits come back as spans -- start page
and index, end page and index -- so several per page is
normal. A hit cut off by the page end makes the detector
re-read that page together with the next, repeatedly, so an
item spread over three pages is found whole.
Offsets come from verbatim quotes resolved by
leanbench/anchors.py (exact -> whitespace-insensitive ->
fuzzy), because models quote well and count badly.
3. leanbench/formalize.py + leanbench/verify.py
each span becomes one Lean 4 declaration, judged by the real
compiler: full elaboration for case 1, statement legality
only for case 2, which has no proof to check. Lean's own
diagnostics feed back for a repair attempt. "verified" (Lean
accepted it) and "proved" (accepted with no sorry) are kept
strictly apart.
4. leanbench/db.py indexed SQLite plus JSONL export. Every item is indexed by
the types of its inputs, or by its own type when it is not a
proof, and records the source book (sha256) and the page it
starts on -- so `drop --source H --pages A-B` followed by a
re-ingest redoes exactly those pages and nothing else.
Also: lean/ Lake project pinned to Mathlib, docker/ image carrying Lean 4 and a
prebuilt Mathlib (the Mathlib revision and the toolchain are resolved against each
other at build time rather than both hardcoded), and .gitea/workflows for tests,
image build and push to the Gitea registry, and a manual "submit a book" run.
58 tests; they need neither network nor Lean.
40 lines
503 B
Plaintext
40 lines
503 B
Plaintext
# Source books and anything derived from their full text: copyrighted material,
|
|
# never committed. Only code and the short Lean datasets belong in git.
|
|
*.pdf
|
|
*.epub
|
|
*.djvu
|
|
books/
|
|
textbook/*.txt
|
|
*_raw.txt
|
|
|
|
# Local state
|
|
.env
|
|
data/
|
|
database/
|
|
results/
|
|
out/
|
|
*.sqlite
|
|
*.sqlite-wal
|
|
*.sqlite-shm
|
|
|
|
# Lean build output
|
|
lean/.lake/
|
|
lean/lake-packages/
|
|
lean/build/
|
|
|
|
# Python
|
|
__pycache__/
|
|
*.py[cod]
|
|
.venv/
|
|
venv/
|
|
*.egg-info/
|
|
.pytest_cache/
|
|
.ruff_cache/
|
|
.coverage
|
|
htmlcov/
|
|
|
|
# Editors and OS
|
|
.DS_Store
|
|
.idea/
|
|
.vscode/
|