SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2009.05613 · 2020

Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

3 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 0 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/2009.05613.json · badge: /api/ran/2009.05613.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
tomsilver/ploi canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
aggregation_func Ran
ran; our contract draft was wrong, not the code
tomsilver/ploi/gnn/gnn.py
code served (permissive licence) · get_code("0edcc3dcf261ffe9")
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) and returned tuple. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch
import numpy as np

torch.manual_seed(0)

# Build a minimal graph dict that satisfies the function's requirements
num_nodes = 2
num_edges = 3
node_dim = 4
edge_dim = 5

graph = {
    'nodes': torch.randn(num_nodes, node_dim),  # shape: (2, 4)
    'edges': torch.randn(num_edges, edge_dim),  # shape: (3, 5)
    'receivers': torch.tensor([0, 1, 0], dtype=torch.long),  # shape: (3,) - receiver indices for each edge
    'n_node': torch.tensor([[num_nodes]], dtype=torch.long),  # shape: (1, 1) - number of nodes per graph
    'globals': torch.randn(1, 6),  # shape: (1, 6) - global features for 1 graph
}

ARGS = {
    'graph': graph
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 — a tuple output has no array shape of its own; none is 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
marshalling_func Ran
ran; our contract draft was wrong, not the code
tomsilver/ploi/gnn/gnn.py
code served (permissive licence) · get_code("9f8543fe8f66bf14")
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. 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 torch
import numpy as np

torch.manual_seed(0)

# Construct a minimal graph dict with all required keys
graph = {
    'nodes': torch.randn(5, 4),  # 5 nodes, 4-dim features
    'receivers': torch.tensor([0, 1, 2], dtype=torch.long),  # 3 edges
    'senders': torch.tensor([1, 2, 3], dtype=torch.long),  # 3 edges
    'edges': torch.randn(3, 6),  # 3 edges, 6-dim features
    'globals': torch.randn(2, 8),  # 2 graphs, 8-dim global features
    'n_edge': torch.tensor([[3], [0]], dtype=torch.long)  # n_edge per graph
}

ARGS = {
    'graph': graph
}
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 — a tuple output has no array shape of its own; none is 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
prepare_receiver_matrix Ran
ran, honoured the contract we drafted
tomsilver/ploi/gnn/gnn.py
code served (permissive licence) · get_code("0b4629864557c835")
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) and returned Tensor, ndim 2, dtype family float, shape (3, 2) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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

torch.manual_seed(0)

# Construct a minimal graph dict that satisfies the function's requirements
# The function accesses: graph['nodes'], graph['edges'], graph['receivers']
# It calls .size()[0] on nodes and edges
# It calls .is_cuda on receivers
# It calls .view(-1) on receivers

graph = {
    'nodes': torch.randn(2, 4),  # 2 nodes, 4 features
    'edges': torch.randn(3, 4),  # 3 edges, 4 features
    'receivers': torch.tensor([0, 1, 0]).long()  # receiver indices for each edge
}

ARGS = {
    'graph': graph
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
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 (3, 2) — shape (3, 2) 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

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

Real-world planning problems often involve hundreds or even thousands of objects, straining the limits of modern planners. In this work, we address this challenge by learning to predict a small set of objects that, taken together, would be sufficient for finding a plan. We propose a graph neural network architecture for predicting object importance in a single inference pass, thus incurring little overhead while greatly reducing the number of objects that must be considered by the planner. Our approach treats the planner and transition model as black boxes, and can be used with any off-the-shelf planner. Empirically, across classical planning, probabilistic planning, and robotic task and motion planning, we find that our method results in planning that is significantly faster than several baselines, including other partial grounding strategies and lifted planners. We conclude that learning to predict a sufficient set of objects for a planning problem is a simple, powerful, and general mechanism for planning in large instances. Video: https://youtu.be/FWsVJc2fvCE Code: https://git.io/JIsqX

For agents

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

get_harvested_code_for_paper("2009.05613")
get_code_for_paper("2009.05613")
have("2009.05613")

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

curl https://syntology.ai/api/ran/2009.05613.json

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

[![Syntology run record](https://syntology.ai/api/ran/2009.05613.svg)](https://syntology.ai/paper/2009.05613)

Connect an agent — have() is free.