SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.12300 · ICLR · 2021

Drop-Bottleneck: LEARNING DISCRETE COMPRESSED REPRESENTATION FOR NOISE-ROBUST EXPLORATION

Gunhee Kim, Jaekyeom Kim, Minjung Kim, Dongyeon Woo

arXiv · PDF · Open in the Atlas

Code that ran

2 of 6 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 2 have no contract verdict; 0 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/2103.12300.json · badge: /api/ran/2103.12300.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
jaekyeom/drop-bottleneck marked official in Papers with Code
Papers with Code archive
2 ran · 4 no recorded run
FunctionStatusWhere it lives
CContext Ran
ran on a synthesized input · constructed an object; no result was computed
jaekyeom/drop-bottleneck/rlb/rlb_model.py
code served (permissive licence) · get_code("f0c48d13fba68c22")
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, CContext: 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.

import torch
from collections import OrderedDict, defaultdict

torch.manual_seed(0)

# Based on the CContext class, it expects:
# - verbose: bool (optional, defaults to False)
# - print_func: callable (optional, defaults to print)

# The class uses these parameters:
# - _verbose is checked in if statements
# - _print_func is called with string arguments

def custom_print(msg):
    """Custom print function for testing"""
    pass

ARGS = {
    'verbose': True,
    'print_func': custom_print
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CContext — the run constructed an instance of its own class and did not call it; no shape is 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
EmptyClass Ran
ran on a synthesized input · constructed an object; no result was computed
jaekyeom/drop-bottleneck/rlb/rlb_model.py
code served (permissive licence) · get_code("7ab8ff06eaaef598")
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, EmptyClass: 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.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EmptyClass — 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 EmptyClass 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
conv Not yet run
unverified (harvested, no recorded run)
jaekyeom/drop-bottleneck/rlb/rlb_model.py
code served (permissive licence) · get_code("8fdc5078dd0bf76a")
How it ran

no invocation recorded.

define_rlb_model Not yet run
unverified (harvested, no recorded run)
jaekyeom/drop-bottleneck/rlb/rlb_model.py
code served (permissive licence) · get_code("501db338d8e3e8a1")
How it ran

no invocation recorded.

fc Not yet run
unverified (harvested, no recorded run)
jaekyeom/drop-bottleneck/rlb/rlb_model.py
code served (permissive licence) · get_code("9770bed4caf46f77")
How it ran

no invocation recorded.

to2d Not yet run
unverified (harvested, no recorded run)
jaekyeom/drop-bottleneck/rlb/rlb_model.py
code served (permissive licence) · get_code("bf1b968c8f29c994")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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 6 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

We propose a novel information bottleneck (IB) method named Drop-Bottleneck, which discretely drops features that are irrelevant to the target variable. Drop-Bottleneck not only enjoys a simple and tractable compression objective but also additionally provides a deterministic compressed representation of the input variable, which is useful for inference tasks that require consistent representation. Moreover, it can jointly learn a feature extractor and select features considering each feature dimension's relevance to the target task, which is unattainable by most neural network-based IB methods. We propose an exploration method based on Drop-Bottleneck for reinforcement learning tasks. In a multitude of noisy and reward sparse maze navigation tasks in VizDoom (Kempka et al., 2016) and DM-Lab (Beattie et al., 2016), our exploration method achieves state-of-the-art performance. As a new IB framework, we demonstrate that Drop-Bottleneck outperforms Variational Information Bottleneck (VIB) (Alemi et al., 2017) in multiple aspects including adversarial robustness and dimensionality reduction.

For agents

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

get_harvested_code_for_paper("2103.12300")
get_code_for_paper("2103.12300")
have("2103.12300")

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

curl https://syntology.ai/api/ran/2103.12300.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.12300.svg)](https://syntology.ai/paper/2103.12300)

Connect an agent — have() is free.