SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1904.07482 · 2019

Object-Oriented Dynamics Learning through Multi-Level Abstraction

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 (0 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/1904.07482.json · badge: /api/ran/1904.07482.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
mig-zh/OODP canonical (classifier label)
classifier basis: census
2 ran · 4 no recorded run
FunctionStatusWhere it lives
resize Ran
ran on a synthesized input
mig-zh/OODP/evaluator.py
code served (permissive licence) · get_code("24df6333c88950eb")
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 tuple, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 numpy as np

torch.manual_seed(0)

# Analyze the function:
# - x: numeric value (used in multiplication)
# - y: numeric value (used in multiplication)
# - shape1: tuple/sequence with 2 elements (w1, h1)
# - shape2: tuple/sequence with 2 elements (w2, h2)

ARGS = {
    "x": 100,
    "y": 50,
    "shape1": (800, 600),
    "shape2": (1024, 768)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family int — a tuple output has no array shape of its own; none is stated
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
wrap_deepmind_ram Ran
ran on a synthesized input
mig-zh/OODP/atari_wrappers.py
code served (permissive licence) · get_code("4cbafb5ea418c34f")
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 ClippedRewardsWrapper. 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 numpy as np
from collections import deque
import gym

# Create a minimal mock environment that satisfies gym.Env interface
class MockAtari(gym.Env):
    def __init__(self):
        self.observation_space = gym.spaces.Box(low=0, high=255, shape=(84, 84), dtype=np.uint8)
        self.action_space = gym.spaces.Discrete(18)
        self._step_count = 0
        self._lives = 5
        
    def get_action_meanings(self):
        # Must have NOOP at index 0, FIRE at index 1, and at least one more action
        return ['NOOP', 'FIRE', 'UP', 'DOWN', 'LEFT', 'RIGHT'] + ['ACTION_%d' % i for i in range(12)]
    
    def reset(self):
        self._step_count = 0
        self._lives = 5
        return np.random.randint(0, 256, (84, 84), dtype=np.uint8)
    
    def step(self, action):
        self._step_count += 1
        obs = np.random.randint(0, 256, (84, 84), dtype=np.uint8)
        reward = np.float32(np.random.randn())
        done = self._step_count >= 100
        info = {}
        return obs, reward, done, info
    
    @property
    def unwrapped(self):
        return self
    
    @property
    def ale(self):
        return self
    
    def lives(self):
        if self._step_count > 50:
            self._lives = max(0, self._lives - 1)
        return self._lives

# Construct a valid environment
env = MockAtari()

# Define ARGS dictionary with all parameters for wrap_deepmind_ram
ARGS = {
    'env': env,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
gym, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ClippedRewardsWrapper — a ClippedRewardsWrapper output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ClippedRewardsWrapper 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
avg_pool Not yet run
unverified (harvested, no recorded run)
mig-zh/OODP/tflib/mmdminmax2.py
code served (permissive licence) · get_code("289b3ed57b2ccc58")
How it ran

no invocation recorded.

get_inception_score Not yet run
unverified (harvested, no recorded run)
mig-zh/OODP/tflib/inception_score.py
code served (permissive licence) · get_code("2c56d76ac1ac9531")
How it ran

no invocation recorded.

max_pool Not yet run
unverified (harvested, no recorded run)
mig-zh/OODP/tflib/mmdminmax2.py
code served (permissive licence) · get_code("da3e6f389e67fb29")
How it ran

no invocation recorded.

wrap_deepmind Not yet run
unverified (harvested, no recorded run)
mig-zh/OODP/atari_wrappers.py
code served (permissive licence) · get_code("30ac4ed53628dbf7")
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, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 4 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
get_inception_score 2 other papers
2 dated earlier
1802.08539 (2018-02)
Computation of optimal transport and related hedging problems via penalization and neural networks
1901.02477 (2019-01)
Differentially Private Generative Adversarial Networks for Time Series, Continuous, and Discrete Open Data
wrap_deepmind_ram 1 other paper
1 dated earlier
1710.11417 (2017-10)
TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learning

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

Object-based approaches for learning action-conditioned dynamics has demonstrated promise for generalization and interpretability. However, existing approaches suffer from structural limitations and optimization difficulties for common environments with multiple dynamic objects. In this paper, we present a novel self-supervised learning framework, called Multi-level Abstraction Object-oriented Predictor (MAOP), which employs a three-level learning architecture that enables efficient object-based dynamics learning from raw visual observations. We also design a spatial-temporal relational reasoning mechanism for MAOP to support instance-level dynamics learning and handle partial observability. Our results show that MAOP significantly outperforms previous methods in terms of sample efficiency and generalization over novel environments for learning environment models. We also demonstrate that learned dynamics models enable efficient planning in unseen environments, comparable to true environment models. In addition, MAOP learns semantically and visually interpretable disentangled representations.

For agents

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

get_harvested_code_for_paper("1904.07482")
get_code_for_paper("1904.07482")
have("1904.07482")

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

curl https://syntology.ai/api/ran/1904.07482.json

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

[![Syntology run record](https://syntology.ai/api/ran/1904.07482.svg)](https://syntology.ai/paper/1904.07482)

Connect an agent — have() is free.