SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.09184 · ICLR · 2023

Packed-Ensembles for Efficient Uncertainty Estimation

Olivier Laurent, Adrien Lafage, Enzo Tartaglione, Geoffrey Daniel, Jean-Marc Martinez, Andrei Bursuc, Gianni Franchi

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 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; 1 failure of our instrument; 2 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/2210.09184.json · badge: /api/ran/2210.09184.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
ENSTA-U2IS-AI/torch-uncertainty marked official in Papers with Code
Papers with Code archive
1 ran · 2 no recorded run
FunctionStatusWhere it lives
packed_linear Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ENSTA-U2IS-AI/torch-uncertainty/src/torch_uncertainty/layers/packed.py
code served (permissive licence) · get_code("5c7038c35796dddf")
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 Tensor, ndim 2, dtype family float, shape (2, 12) 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
from einops import rearrange

torch.manual_seed(0)

# Small tensor dimensions
batch_size = 2
in_features = 8
out_features = 12
num_groups = 4

# Derived dimensions for packed weight format
in_features_per_group = in_features // num_groups  # 2
out_features_per_group = out_features // num_groups  # 3

# Inputs: (batch_size, in_features)
inputs = torch.randn(batch_size, in_features)

# Weight: (num_groups, out_features_per_group, in_features_per_group)
weight = torch.randn(num_groups, out_features_per_group, in_features_per_group)

# Bias: (out_features,)
bias = torch.randn(out_features)

# Implementation choice
implementation = "einsum"

ARGS = {
    "inputs": inputs,
    "weight": weight,
    "num_groups": num_groups,
    "implementation": implementation,
    "bias": bias,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
einops, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 12) — shape (2, 12) 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
PackedLinear Not yet run
unverified (harvested, no recorded run)
ENSTA-U2IS-AI/torch-uncertainty/src/torch_uncertainty/layers/packed.py
code served (permissive licence) · get_code("1be634ae9abe064e")
How it ran

no invocation recorded.

check_packed_parameters_consistency Not yet run
unverified (harvested, no recorded run)
ENSTA-U2IS-AI/torch-uncertainty/src/torch_uncertainty/layers/packed.py
code served (permissive licence) · get_code("05ffce263e88e176")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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

Deep Ensembles (DE) are a prominent approach for achieving excellent performance on key metrics such as accuracy, calibration, uncertainty estimation, and out-of-distribution detection. However, hardware limitations of real-world systems constrain users to smaller ensembles and lower-capacity networks, significantly deteriorating their performance. We introduce Packed-Ensembles (PE), a strategy to design and train lightweight structured ensembles by carefully modulating the dimension of their encoding space. We leverage grouped convolutions to parallelize the ensemble into a single shared backbone and forward pass to reduce the number of parameters and improve training and inference speeds when using mixed precision. PE is designed to operate within the memory limits of a standard neural network. Our extensive research indicates that PE accurately preserves the properties of DE, such as diversity, and performs equally well in terms of accuracy, calibration, out-of-distribution detection, and robustness to distribution shift. We make our code available at github.com/ENSTA-U2IS-AI/torch-uncertainty. 2 3 4 5 6 Images/sec (×10 3 ) 78 79 80 81 82 Accuracy (%) 10M 20M 90M Packed-Ensembles (2, 4, 1) Packed-Ensembles (2, 4, 2) Deep Ensembles (×4) Single MIMO (4)

For agents

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

get_harvested_code_for_paper("2210.09184")
get_code_for_paper("2210.09184")
have("2210.09184")

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

curl https://syntology.ai/api/ran/2210.09184.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.09184.svg)](https://syntology.ai/paper/2210.09184)

Connect an agent — have() is free.