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.
17 lines
674 B
Python
17 lines
674 B
Python
"""lean-bench: turn mathematical source documents into verified Lean 4 items.
|
|
|
|
Pipeline
|
|
--------
|
|
1. ``leanbench.llm`` provider-neutral LLM connector (the base need).
|
|
2. ``leanbench.detect`` find formalizable math on each page, with spans that may
|
|
run across several pages.
|
|
3. ``leanbench.formalize`` turn each detected span into Lean 4 code;
|
|
``leanbench.verify`` check it with the real Lean compiler.
|
|
4. ``leanbench.db`` store everything in an indexed database, keyed by the
|
|
types an item consumes and produces, plus book hash and page.
|
|
"""
|
|
|
|
__version__ = "0.2.0"
|
|
|
|
__all__ = ["__version__"]
|