SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.09656 · NeurIPS · 2023

SATLM: Satisfiability-Aided Language Models Using Declarative Prompting

Greg Durrett, Isil Dillig, Xi Ye, Qiaochu Chen

arXiv · PDF · Open in the Atlas

Code that ran

2 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2305.09656.json · badge: /api/ran/2305.09656.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
xiye17/sat-lm canonical (classifier label)
classifier basis: classifier_2025
2 ran · 3 no recorded run
FunctionStatusWhere it lives
CodeTranslator Ran
ran on a synthesized input · constructed an object; no result was computed
xiye17/sat-lm/prog_solver/arlsat_solver.py
code served (permissive licence) · get_code("ce80d3e34ae900a5")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, CodeTranslator: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

from collections import OrderedDict, namedtuple
from enum import Enum

# The CodeTranslator class is a static utility class with no __init__ parameters
# All methods are @staticmethod, so there are no instance attributes to initialize

ARGS = {}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CodeTranslator — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a CodeTranslator output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
hash_of_code Ran
ran; our contract draft was wrong, not the code
xiye17/sat-lm/prog_solver/arlsat_solver.py
code served (permissive licence) · get_code("bc40133b2f91c104")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import hashlib

def hash_of_code(code, size=16):
    val = hashlib.sha1(code.encode('utf-8')).hexdigest()
    return val[-size:]

ARGS = {
    "code": "def hello_world():\n    print('Hello, World!')",
    "size": 16
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
LSATSatProblem Not yet run
unverified (harvested, no recorded run)
xiye17/sat-lm/prog_solver/arlsat_solver.py
code served (permissive licence) · get_code("690487f1b15a8ab2")
How it ran

no invocation recorded.

arlsat_satlm_exec Not yet run
unverified (harvested, no recorded run)
xiye17/sat-lm/prog_solver/arlsat_solver.py
code served (permissive licence) · get_code("c568d6f7079aad28")
How it ran

no invocation recorded.

execution_test Not yet run
unverified (harvested, no recorded run)
xiye17/sat-lm/prog_solver/arlsat_solver.py
code served (permissive licence) · get_code("5fa84f183bdfe06a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 5 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Prior work has combined chain-of-thought prompting in large language models (LLMs) with programmatic representations to perform effective and transparent reasoning. While such an approach works well for tasks that only require forward reasoning (e.g., straightforward arithmetic), it is less effective for constraint solving problems that require more sophisticated planning and search. In this paper, we propose a new satisfiability-aided language modeling (SATLM) approach for improving the reasoning capabilities of LLMs. We use an LLM to generate a declarative task specification rather than an imperative program and leverage an off-the-shelf automated theorem prover to derive the final answer. This approach has two key advantages. The declarative specification is closer to the problem description than the reasoning steps are, so the LLM can parse it out of the description more accurately. Furthermore, by offloading the actual reasoning task to an automated theorem prover, our approach can guarantee the correctness of the answer with respect to the parsed specification and avoid planning errors in the solving process. We evaluate SATLM on 8 different datasets and show that it consistently outperforms program-aided LMs in the imperative paradigm. In particular, SATLM outperforms program-aided LMs by 23% on a challenging subset of the GSM arithmetic reasoning dataset; SATLM also achieves a new SoTA on LSAT and BOARDGAMEQA, surpassing previous models that are trained on the respective training sets. 1

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2305.09656")
get_code_for_paper("2305.09656")
have("2305.09656")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2305.09656.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2305.09656.svg)](https://syntology.ai/paper/2305.09656)

Connect an agent — have() is free.