SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.00631 · NeurIPS · 2020

Causal Discovery in Physical Systems from Videos

Animesh Garg, Yunzhu Li, Antonio Torralba, Animashree Caltech, Dieter Fox

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 3 failures of our instrument; 2 no recorded run), measured 2026-11-21; 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/2007.00631.json · badge: /api/ran/2007.00631.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
pairlab/v-cdn community
Papers with Code archive
6 ran · 2 no recorded run
FunctionStatusWhere it lives
CNNet Ran
ran on a synthesized input · constructed an object; no result was computed
pairlab/v-cdn/models_dy.py
pointer only (licence: NONE) · get_code("5727985d6b3cf7df")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pairlab/v-cdn 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.

GRUNet Ran
ran on a synthesized input · constructed an object; no result was computed
pairlab/v-cdn/models_dy.py
pointer only (licence: NONE) · get_code("7fe04aff9fdb623d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pairlab/v-cdn 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.

PropNet Ran
ran on a synthesized input · constructed an object; no result was computed
pairlab/v-cdn/models_dy.py
pointer only (licence: NONE) · get_code("3021e5a90c489e96")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pairlab/v-cdn 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.

gumbel_softmax Ran
ran; our contract draft was wrong, not the code
pairlab/v-cdn/models_dy.py
pointer only (licence: NONE) · get_code("8a5f974f305016c7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pairlab/v-cdn 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.

gumbel_softmax_sample Ran
ran; our contract draft was wrong, not the code
pairlab/v-cdn/models_dy.py
pointer only (licence: NONE) · get_code("8c49f9e976f85256")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pairlab/v-cdn 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.

sample_gumbel Ran
ran; our contract draft was wrong, not the code
pairlab/v-cdn/models_dy.py
pointer only (licence: NONE) · get_code("1ae3d9e3053566f3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pairlab/v-cdn 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.

DynaNetGNN Not yet run
unverified (harvested, no recorded run)
pairlab/v-cdn/models_dy.py
pointer only (licence: NONE) · get_code("a441be933bcb5009")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pairlab/v-cdn 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.

SpatialSoftmax Not yet run
unverified (harvested, no recorded run)
pairlab/v-cdn/models_dy.py
pointer only (licence: NONE) · get_code("f92716f2a411549a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pairlab/v-cdn 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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 later) and 7 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
gumbel_softmax_sample
brick of this paper's assembly: helper
7 other papers
3 dated earlier, 1 the same month, 3 later
1904.03240 (2019-04)
An Unsupervised Autoregressive Model for Speech Representation Learning
1906.08862 (2019-06)
Neural Stored-program Memory
2005.08392 (2020-05)
Vector-Quantized Autoregressive Predictive Coding
and 4 more not named here

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Causal discovery is at the core of human cognition. It enables us to reason about the environment and make counterfactual predictions about unseen scenarios that can vastly differ from our previous experiences. We consider the task of causal discovery from videos in an end-to-end fashion without supervision on the ground-truth graph structure. In particular, our goal is to discover the structural dependencies among environmental and object variables: inferring the type and strength of interactions that have a causal effect on the behavior of the dynamical system. Our model consists of (a) a perception module that extracts a semantically meaningful and temporally consistent keypoint representation from images, (b) an inference module for determining the graph distribution induced by the detected keypoints, and (c) a dynamics module that can predict the future by conditioning on the inferred graph. We assume access to different configurations and environmental conditions, i.e., data from unknown interventions on the underlying system; thus, we can hope to discover the correct underlying causal graph without explicit interventions. We evaluate our method in a planar multi-body interaction environment and scenarios involving fabrics of different shapes like shirts and pants. Experiments demonstrate that our model can correctly identify the interactions from a short sequence of images and make long-term future predictions. The causal structure assumed by the model also allows it to make counterfactual predictions and extrapolate to systems of unseen interaction graphs or graphs of various sizes. Please refer to our project page for additional results: https://yunzhuli.github.io/V-CDN/.

For agents

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

get_harvested_code_for_paper("2007.00631")
get_code_for_paper("2007.00631")
have("2007.00631")

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

curl https://syntology.ai/api/ran/2007.00631.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.00631.svg)](https://syntology.ai/paper/2007.00631)

Connect an agent — have() is free.