SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.11287 · NeurIPS · 2022

MOCODA: Model-based Counterfactual Data Augmentation

Silviu Pitis, Animesh Garg, Elliot Creager, Ajay Mandlekar

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 (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; 6 failures 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/2210.11287.json · badge: /api/ran/2210.11287.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
spitis/mocoda canonical (classifier label)
classifier basis: classifier_2025
6 ran · 2 no recorded run
FunctionStatusWhere it lives
connected_components Ran
ran; our contract draft was wrong, not the code
spitis/mocoda/augment_offline.py
pointer only (licence: NONE) · get_code("a35fbd5396153c90")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, spitis/mocoda 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.

filter_by_constraint Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
spitis/mocoda/augment_offline.py
pointer only (licence: NONE) · get_code("f25cb05933a07e3a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, spitis/mocoda 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.

make_graph Ran
ran; our contract draft was wrong, not the code
spitis/mocoda/augment_offline.py
pointer only (licence: NONE) · get_code("215b2276ca908379")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, spitis/mocoda 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.

naive_root_sampler Ran
ran; our contract draft was wrong, not the code
spitis/mocoda/augment_offline.py
pointer only (licence: NONE) · get_code("45fe36afc4e7d025")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, spitis/mocoda 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.

naive_sampler Ran
ran; our contract draft was wrong, not the code
spitis/mocoda/augment_offline.py
pointer only (licence: NONE) · get_code("6a10e7af5d468380")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, spitis/mocoda 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.

split_nodes Ran
ran; our contract draft was wrong, not the code
spitis/mocoda/augment_offline.py
pointer only (licence: NONE) · get_code("b91f2ab6e4300fbe")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, spitis/mocoda 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.

generate_gmm_coda_dataset Not yet run
unverified (harvested, no recorded run)
spitis/mocoda/augment_offline.py
pointer only (licence: NONE) · get_code("8c9f808b47a1ecc3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, spitis/mocoda 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.

naive_child_sampler Not yet run
unverified (harvested, no recorded run)
spitis/mocoda/augment_offline.py
pointer only (licence: NONE) · get_code("99b3d0dbe874d55d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, spitis/mocoda 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, 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 8 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

The number of states in a dynamic process is exponential in the number of objects, making reinforcement learning (RL) difficult in complex, multi-object domains. For agents to scale to the real world, they will need to react to and reason about unseen combinations of objects. We argue that the ability to recognize and use local factorization in transition dynamics is a key element in unlocking the power of multi-object reasoning. To this end, we show that (1) known local structure in the environment transitions is sufficient for an exponential reduction in the sample complexity of training a dynamics model, and (2) a locally factored dynamics model provably generalizes out-of-distribution to unseen states and actions. Knowing the local structure also allows us to predict which unseen states and actions this dynamics model will generalize to. We propose to leverage these observations in a novel Model-based Counterfactual Data Augmentation (MOCODA) framework. MOCODA applies a learned locally factored dynamics model to an augmented distribution of states and actions to generate counterfactual transitions for RL. MOCODA works with a broader set of local structures than prior work and allows for direct control over the augmented training distribution. We show that MOCODA enables RL agents to learn policies that generalize to unseen states and actions. We use MOCODA to train an offline RL agent to solve an out-ofdistribution robotics manipulation task on which standard offline RL algorithms fail. 1

For agents

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

get_harvested_code_for_paper("2210.11287")
get_code_for_paper("2210.11287")
have("2210.11287")

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

curl https://syntology.ai/api/ran/2210.11287.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.11287.svg)](https://syntology.ai/paper/2210.11287)

Connect an agent — have() is free.