SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.22581 · 2026

IBCircuit: Towards Holistic Circuit Discovery with Information Bottleneck

Long-Kai Huang, Yu Rong, Hong Cheng, Jia Li, Tingyang Xu, Bingzhe Wu, Yifan Niu, Tian Bian, Chaohao Yuan, Chengzhi Piao

arXiv · PDF · Open in the Atlas

Code that ran

6 of 9 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 2 failures of our instrument; 3 no recorded run), measured 2026-11-22; 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/2602.22581.json · badge: /api/ran/2602.22581.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
ivanniu/IBCircuit community
Papers with Code archive
6 ran · 3 no recorded run
FunctionStatusWhere it lives
Conv1D Ran
ran on a synthesized input · constructed an object; no result was computed
ivanniu/IBCircuit/models/gpt2_IB.py
pointer only (licence: NONE) · get_code("c6dc94391cdcb2cf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ivanniu/IBCircuit when it was checked. 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.

IB_GPT2Attention Ran
ran on a synthesized input · constructed an object; no result was computed
ivanniu/IBCircuit/models/gpt2_IB.py
pointer only (licence: NONE) · get_code("3829cd95537b2078")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ivanniu/IBCircuit when it was checked. 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.

find_pruneable_heads_and_indices Ran
ran; our contract draft was wrong, not the code
ivanniu/IBCircuit/models/gpt2_IB.py
pointer only (licence: NONE) · get_code("86ce14ff7ea60630")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ivanniu/IBCircuit when it was checked. 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.

is_torch_available Ran
ran on a synthesized input
ivanniu/IBCircuit/models/gpt2_IB.py
pointer only (licence: NONE) · get_code("f4b02b5b37ed446d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ivanniu/IBCircuit when it was checked. 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.

is_torchdynamo_compiling Ran
ran on a synthesized input
ivanniu/IBCircuit/models/gpt2_IB.py
pointer only (licence: NONE) · get_code("be5a51301c0553b7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ivanniu/IBCircuit when it was checked. 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.

prune_conv1d_layer Ran
ran; our contract draft was wrong, not the code
ivanniu/IBCircuit/models/gpt2_IB.py
pointer only (licence: NONE) · get_code("d56a45fde31642dd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ivanniu/IBCircuit when it was checked. 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.

IB_GPT2Block Not yet run
unverified (harvested, no recorded run)
ivanniu/IBCircuit/models/gpt2_IB.py
pointer only (licence: NONE) · get_code("f6f64f3bb6fadb2f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ivanniu/IBCircuit when it was checked. 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.

IB_GPT2LMHeadModel Not yet run
unverified (harvested, no recorded run)
ivanniu/IBCircuit/models/gpt2_IB.py
pointer only (licence: NONE) · get_code("9da7935cc55f211b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ivanniu/IBCircuit when it was checked. 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.

IB_GPT2Model Not yet run
unverified (harvested, no recorded run)
ivanniu/IBCircuit/models/gpt2_IB.py
pointer only (licence: NONE) · get_code("6ff404338258acf7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ivanniu/IBCircuit when it was checked. 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 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 4 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 1 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.

FunctionAlso present inEarliest-datedOthers named
find_pruneable_heads_and_indices
brick of this paper's assembly: helper
11 other papers
11 dated earlier
2004.10964 (2020-04)
Don't Stop Pretraining: Adapt Language Models to Domains and Tasks
2021.emnlp-main.154 (2021 (year only))
Reconstruction Attack on Instance Encoding for Language Understanding
2104.08066 (2021-04)
Effect of Visual Extensions on Natural Language Understanding in Vision-and-Language Models
and 8 more not named here
prune_conv1d_layer
brick of this paper's assembly: helper
2 other papers
2 dated earlier
2021.emnlp-main.154 (2021 (year only))
Reconstruction Attack on Instance Encoding for Language Understanding
2405.10974 (2024-05)
Bottleneck-Minimal Indexing for Generative Document Retrieval
Conv1D
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2512.14391 (2025-12)
REPO: Language Models with Context Re-Positioning
is_torch_available
brick of this paper's assembly: helper
1 other paper
1 later
2606.27596 (2026-06)
Dismantling Pathological Shortcuts: A Causal Framework for Faithful LVLM Decoding

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

Circuit discovery has recently attracted attention as a potential research direction to explain the non-trivial behaviors of language models. It aims to find the computational subgraphs, also known as circuits, within the model that are responsible for solving specific tasks. However, most existing studies overlook the holistic nature of these circuits and require designing specific corrupted activations for different tasks, which is inaccurate and inefficient. In this work, we propose an end-to-end approach based on the principle of Information Bottleneck, called IBCircuit, to identify informative circuits holistically. IBCircuit is an optimization framework for holistic circuit discovery and can be applied to any given task without tediously corrupted activation design. In both the Indirect Object Identification (IOI) and Greater-Than tasks, IBCircuit identifies more faithful and minimal circuits in terms of critical node components and edge components compared to recent related work. The code is available at https://github.com/ivanniu/IBCircuit.

For agents

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

get_harvested_code_for_paper("2602.22581")
get_code_for_paper("2602.22581")
have("2602.22581")

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

curl https://syntology.ai/api/ran/2602.22581.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.22581.svg)](https://syntology.ai/paper/2602.22581)

Connect an agent — have() is free.