SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.11799 · 2022

Augmenting Interpretable Models with LLMs during Training

arXiv · PDF · Open in the Atlas

Code that ran

8 of 12 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 6 have no contract verdict; 2 failures of our instrument; 4 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/2209.11799.json · badge: /api/ran/2209.11799.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
csinva/emb-gam canonical (classifier label)
classifier basis not recorded on the link
6 ran · 4 no recorded run
microsoft/augmented-interpretable-models canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
add_computational_args Ran
ran; our contract draft was wrong, not the code
microsoft/augmented-interpretable-models/augtree/experiments/01_train_model.py
code served (permissive licence) · get_code("19363da9b2e0a8e4")
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 ArgumentParser. 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 argparse
import os
from os.path import dirname, join

# Create a minimal argument parser
parser = argparse.ArgumentParser()

# Define ARGS dict with values for all parameters of add_computational_args
ARGS = {
    'parser': parser
}
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 ArgumentParser — a ArgumentParser output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ArgumentParser 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
add_computational_args Ran
ran on a synthesized input
csinva/emb-gam/augdistill/experiments/01_eval.py
pointer only (licence: MIT) · get_code("406e7b11b9a38bf6")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, csinva/emb-gam, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

add_main_args Ran
ran; our contract draft was wrong, not the code
microsoft/augmented-interpretable-models/augtree/experiments/01_train_model.py
code served (permissive licence) · get_code("9a9d5e7dbc61cc12")
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 ArgumentParser. 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 argparse
import torch
import numpy as np
from os.path import join
import os

torch.manual_seed(0)

parser = argparse.ArgumentParser()

ARGS = {
    'parser': parser,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ArgumentParser — a ArgumentParser output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ArgumentParser 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
average_seeds Ran
ran on a synthesized input
csinva/emb-gam/auggam/auggam/analyze_helper.py
pointer only (licence: MIT) · get_code("94fc12cee266d05f")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, csinva/emb-gam, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

generate_ngrams_list Ran
ran on a synthesized input
csinva/emb-gam/auggam/auggam/embed.py
pointer only (licence: MIT) · get_code("1999a51d3bcebcb3")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, csinva/emb-gam, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_dir_name Ran
ran on a synthesized input
csinva/emb-gam/auggam/auggam/data.py
pointer only (licence: MIT) · get_code("6fbf6dc523fe795c")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, csinva/emb-gam, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_fitted_results Ran
ran on a synthesized input
csinva/emb-gam/auggam/auggam/data.py
pointer only (licence: MIT) · get_code("cddd3f8fab150afb")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, csinva/emb-gam, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

preprocess_gpt_token_batch Ran
ran on a synthesized input
csinva/emb-gam/auggam/auggam/embed.py
pointer only (licence: MIT) · get_code("ce5f966b7b6f6781")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, csinva/emb-gam, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

add_main_args Not yet run
unverified (harvested, no recorded run)
csinva/emb-gam/augdistill/experiments/01_eval.py
pointer only (licence: MIT) · get_code("63743868776d4aa1")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, csinva/emb-gam, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

corrplot_max_abs_unigrams Not yet run
unverified (harvested, no recorded run)
csinva/emb-gam/auggam/auggam/analyze_helper.py
pointer only (licence: MIT) · get_code("4d8fce0e5de37264")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, csinva/emb-gam, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

embed_and_sum_function Not yet run
unverified (harvested, no recorded run)
csinva/emb-gam/auggam/auggam/embed.py
pointer only (licence: MIT) · get_code("1bf3bdbe0145f356")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, csinva/emb-gam, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

process_data_and_args Not yet run
unverified (harvested, no recorded run)
csinva/emb-gam/auggam/auggam/data.py
pointer only (licence: MIT) · get_code("751633c4c0a353c8")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, csinva/emb-gam, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 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 12 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

Recent large language models (LLMs) have demonstrated remarkable prediction performance for a growing array of tasks. However, their proliferation into high-stakes domains (e.g. medicine) and compute-limited settings has created a burgeoning need for interpretability and efficiency. We address this need by proposing Augmented Interpretable Models (Aug-imodels), a framework for leveraging the knowledge learned by LLMs to build extremely efficient and interpretable models. Aug-imodels use LLMs during fitting but not during inference, allowing complete transparency and often a speed/memory improvement of greater than 1,000x for inference compared to LLMs. We explore two instantiations of Aug-imodels in natural-language processing: (i) Aug-GAM, which augments a generalized additive model with decoupled embeddings from an LLM and (ii) Aug-Tree, which augments a decision tree with LLM feature expansions. Across a variety of text-classification datasets, both outperform their non-augmented counterparts. Aug-GAM can even outperform much larger models (e.g. a 6-billion parameter GPT-J model), despite having 10,000x fewer parameters and being fully transparent. We further explore Aug-imodels in a natural-language fMRI study, where they generate interesting interpretations from scientific data. All code for using Aug-imodels and reproducing results is made available on Github.

For agents

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

get_harvested_code_for_paper("2209.11799")
get_code_for_paper("2209.11799")
have("2209.11799")

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

curl https://syntology.ai/api/ran/2209.11799.json

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

[![Syntology run record](https://syntology.ai/api/ran/2209.11799.svg)](https://syntology.ai/paper/2209.11799)

Connect an agent — have() is free.