SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.12601 · 2022

R3M: A Universal Visual Representation for Robot Manipulation

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 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; 2 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 1 failure of our instrument; 1 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/2203.12601.json · badge: /api/ran/2203.12601.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
facebookresearch/r3m canonical (classifier label)
classifier basis: plan_row
5 ran · 1 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran on a synthesized input
facebookresearch/r3m/r3m/utils/utils.py
pointer only (licence: MIT) · get_code("385d22c63e10ccc8")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/r3m, 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.

do_nothing Ran
ran, honoured the contract we drafted
facebookresearch/r3m/r3m/models/models_r3m.py
pointer only (licence: MIT) · get_code("356d0dfdff3db93a")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/r3m, 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_ind Ran
ran on a synthesized input
facebookresearch/r3m/r3m/utils/data_loaders.py
pointer only (licence: MIT) · get_code("d6783fb6e52ddc14")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/r3m, 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.

schedule Ran
ran, honoured the contract we drafted
facebookresearch/r3m/r3m/utils/utils.py
pointer only (licence: MIT) · get_code("ae234269debed3f4")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/r3m, 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.

to_torch Ran
ran; our contract draft was wrong, not the code
facebookresearch/r3m/r3m/utils/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from premiertaco/premier-taco, is pointer only (licence: NONE) · get_code("6244e9922f4e0610")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/r3m, 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.

make_network Not yet run
unverified (harvested, no recorded run)
facebookresearch/r3m/r3m/train_representation.py
pointer only (licence: MIT); the stored copy get_code serves, from facebookresearch/vip, is pointer only (licence: NOASSERTION) · get_code("f8a214d48c5442e3")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/r3m, 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 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, 5 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 5 later) and 1 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
to_torch 23 other papers
3 dated earlier, 20 later · 7 only as an assembly brick
2103.04551 (2021-03)
Behavior From the Void: Unsupervised Active Pre-Training
2107.09645 (2021-07)
Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning
2202.10324 (2022-02)
VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning
and 20 more not named here
schedule 17 other papers
3 dated earlier, 14 later · 7 only as an assembly brick
2103.04551 (2021-03)
Behavior From the Void: Unsupervised Active Pre-Training
2107.09645 (2021-07)
Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning
2202.10324 (2022-02)
VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning
and 14 more not named here
do_nothing 2 other papers
2 later
2306.00958 (2023-06)
LIV: Language-Image Representations and Rewards for Robotic Control
2310.08041 (2023-10)
QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models
accuracy 1 other paper
1 later
2306.00958 (2023-06)
LIV: Language-Image Representations and Rewards for Robotic Control
make_network 1 other paper
1 later
2210.00030 (2022-10)
TOWARDS UNIVERSAL VISUAL REWARD AND REPRE-SENTATION VIA VALUE-IMPLICIT PRE-TRAINING

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 study how visual representations pre-trained on diverse human video data can enable data-efficient learning of downstream robotic manipulation tasks. Concretely, we pre-train a visual representation using the Ego4D human video dataset using a combination of time-contrastive learning, video-language alignment, and an L1 penalty to encourage sparse and compact representations. The resulting representation, R3M, can be used as a frozen perception module for downstream policy learning. Across a suite of 12 simulated robot manipulation tasks, we find that R3M improves task success by over 20% compared to training from scratch and by over 10% compared to state-of-the-art visual representations like CLIP and MoCo. Furthermore, R3M enables a Franka Emika Panda arm to learn a range of manipulation tasks in a real, cluttered apartment given just 20 demonstrations. Code and pre-trained models are available at https://tinyurl.com/robotr3m.

For agents

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

get_harvested_code_for_paper("2203.12601")
get_code_for_paper("2203.12601")
have("2203.12601")

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

curl https://syntology.ai/api/ran/2203.12601.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.12601.svg)](https://syntology.ai/paper/2203.12601)

Connect an agent — have() is free.