SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.09702 · 2023

Efficient Guided Generation for Large Language Models

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 2 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/2307.09702.json · badge: /api/ran/2307.09702.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
normal-computing/outlines canonical (classifier label)
classifier basis: census
3 ran · 2 no recorded run
FunctionStatusWhere it lives
build_template_from_file Ran
ran; our contract draft was wrong, not the code
normal-computing/outlines/src/outlines/templates.py
code served (permissive licence) · get_code("fd738160359ac825")
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 Template. 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 tempfile
import os
from pathlib import Path
import jinja2

# Create a temporary directory and a simple template file
temp_dir = tempfile.mkdtemp()
template_path = os.path.join(temp_dir, "test_template.jinja2")

# Write a minimal valid Jinja2 template
with open(template_path, "w") as f:
    f.write("Hello {{ name }}")

# Define a simple filter function
def custom_filter(value):
    """A custom filter for testing."""
    return str(value).upper()

ARGS = {
    "path": Path(template_path),
    "filters": {"custom_upper": custom_filter}
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
jinja2 — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Template — a Template output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Template 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
build_template_from_string Ran
ran; our contract draft was wrong, not the code
normal-computing/outlines/src/outlines/templates.py
code served (permissive licence) · get_code("82f375e8deb405ae")
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 Template. 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 functools
import inspect
import re
import textwrap
from typing import Any, Callable, Dict, Optional, Type, cast
import jinja2

# Define ARGS for build_template_from_string
ARGS = {
    "content": "Hello {{ name | name }}, this is a test template.\n\n",
    "filters": {
        "custom_filter": lambda x: str(x).upper()
    }
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
jinja2 — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Template — a Template output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Template 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
read_grammar Ran
ran; our contract draft was wrong, not the code
normal-computing/outlines/src/outlines/grammars.py
code served (permissive licence) · get_code("293ed31cfc14f942")
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 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 tempfile
from pathlib import Path

# Create a temporary directory with a test grammar file
temp_dir = tempfile.mkdtemp()
temp_path = Path(temp_dir)

# Create a sample grammar file
grammar_file = temp_path / "test_grammar.txt"
grammar_file.write_text("S -> NP VP\nNP -> DET N\nVP -> V NP\n")

# Define arguments for the function
ARGS = {
    "grammar_file_name": "test_grammar.txt",
    "base_grammar_path": temp_path
}
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 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
is_provider_exception Not yet run
unverified (harvested, no recorded run)
normal-computing/outlines/src/outlines/exceptions.py
code served (permissive licence) · get_code("7c574a80c57f8db6")
How it ran

no invocation recorded.

normalize_provider_exception Not yet run
unverified (harvested, no recorded run)
normal-computing/outlines/src/outlines/exceptions.py
code served (permissive licence) · get_code("3d14ee339aff71e5")
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

In this article we show how the problem of neural text generation can be constructively reformulated in terms of transitions between the states of a finite-state machine. This framework leads to an efficient approach to guiding text generation with regular expressions and context-free grammars by allowing the construction of an index over a language model's vocabulary. The approach is model agnostic, allows one to enforce domain-specific knowledge and constraints, and enables the construction of reliable interfaces by guaranteeing the structure of the generated text. It adds little overhead to the token sequence generation process and significantly outperforms existing solutions. An implementation is provided in the open source Python library Outlines

For agents

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

get_harvested_code_for_paper("2307.09702")
get_code_for_paper("2307.09702")
have("2307.09702")

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

curl https://syntology.ai/api/ran/2307.09702.json

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

[![Syntology run record](https://syntology.ai/api/ran/2307.09702.svg)](https://syntology.ai/paper/2307.09702)

Connect an agent — have() is free.