SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.05350 · ICML · 2023

Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repeat

Ke Yu, Kayhan Batmanghelich, Shantanu Ghosh, Forough Arabshahi

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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; 2 failures of our instrument; 0 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/2307.05350.json · badge: /api/ran/2307.05350.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
batmanlab/icml-2023-route-interpret-repeat canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
get_selected_idx_for_g Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
batmanlab/icml-2023-route-interpret-repeat/src/codebase/Explainer/experiments_explainer_CUB.py
code served (permissive licence) · get_code("b1f491683ce3d450")
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 Tensor, ndim 1, dtype family int, shape (2,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 torch

torch.manual_seed(0)

# Construct arguments for get_selected_idx_for_g
device = torch.device('cpu')

# For iteration == 1 case
iteration_1 = 1
selection_out_1 = torch.tensor([0.1, 0.6, 0.3, 0.9], dtype=torch.float32)
selection_threshold = 0.5
prev_selection_outs_1 = None

# For iteration > 1 case
iteration_2 = 2
selection_out_2 = torch.tensor([0.1, 0.6, 0.3, 0.9], dtype=torch.float32)
prev_selection_outs_2 = [
    torch.tensor([0.2, 0.3, 0.7, 0.4], dtype=torch.float32),
    torch.tensor([0.1, 0.8, 0.2, 0.5], dtype=torch.float32)
]

# Test case 1: iteration == 1
ARGS = {
    'iteration': iteration_1,
    'selection_out': selection_out_1,
    'selection_threshold': selection_threshold,
    'device': device,
    'prev_selection_outs': prev_selection_outs_1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family int, shape (2,) — shape (2,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
get_selected_idx_for_residual Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
batmanlab/icml-2023-route-interpret-repeat/src/codebase/Explainer/experiments_explainer_CUB.py
code served (permissive licence) · get_code("7184611c6fb3677e")
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 Tensor, ndim 1, dtype family int, shape (5,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 torch

torch.manual_seed(0)

# Create small tensors for selection outputs
# These represent probability scores that will be compared against a threshold
selection_out = torch.rand(2, 4)  # batch_size=2, dim=4

# Create previous selection outputs for iteration > 1
# This is a list of tensors from previous iterations
prev_selection_outs = [
    torch.rand(2, 4),
    torch.rand(2, 4),
]

# Selection threshold - values below this are selected
selection_threshold = 0.5

# Device
device = torch.device('cpu')

# Iteration number
iteration = 1

ARGS = {
    'iteration': iteration,
    'selection_out': selection_out,
    'selection_threshold': selection_threshold,
    'device': device,
    'prev_selection_outs': prev_selection_outs,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family int, shape (5,) — shape (5,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 2 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

ML model design either starts with an interpretable model or a Blackbox and explains it post hoc. Blackbox models are flexible but difficult to explain, while interpretable models are inherently explainable. Yet, interpretable models require extensive ML knowledge and tend to be less flexible and underperforming than their Blackbox variants. This paper aims to blur the distinction between a post hoc explanation of a Blackbox and constructing interpretable models. Beginning with a Blackbox, we iteratively carve out a mixture of interpretable experts (MoIE) and a residual network. Each interpretable model specializes in a subset of samples and explains them using First Order Logic (FOL), providing basic reasoning on concepts from the Blackbox. We route the remaining samples through a flexible residual. We repeat the method on the residual network until all the interpretable models explain the desired proportion of data. Our extensive experiments show that our route, interpret, and repeat approach (1) identifies a diverse set of instance-specific concepts with high concept completeness via MoIE without compromising in performance, (2) identifies the relatively "harder" samples to explain via residuals, (3) outperforms the interpretable by-design models by significant margins during test-time interventions, and (4) fixes the shortcut learned by the original Blackbox. The code for MoIE is publicly available at: https://github.com/batmanlab/ ICML-2023-Route-interpret-repeat.

For agents

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

get_harvested_code_for_paper("2307.05350")
get_code_for_paper("2307.05350")
have("2307.05350")

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

curl https://syntology.ai/api/ran/2307.05350.json

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

[![Syntology run record](https://syntology.ai/api/ran/2307.05350.svg)](https://syntology.ai/paper/2307.05350)

Connect an agent — have() is free.