SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.11121 · ICML · 2020

PackIt: A Virtual Environment for Geometric Planning

Akit Goyal, Jia Deng

arXiv · PDF · Open in the Atlas

Code that ran

5 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 5 have no contract verdict; 0 failures of our instrument; 3 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/2007.11121.json · badge: /api/ran/2007.11121.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
princeton-vl/PackIt canonical (classifier label)
classifier basis: census
5 ran · 3 no recorded run
FunctionStatusWhere it lives
cmp_to_key Ran
ran on a synthesized input
princeton-vl/PackIt/packing/packing_heuristic.py
code served (permissive licence) · get_code("a7c2af84c4a1a5d5")
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 type. 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
from functools import cmp_to_key as builtin_cmp_to_key

# Define a simple comparison function
def reverse_numeric(a, b):
    """Compare two numbers in reverse order"""
    if a < b:
        return 1
    elif a > b:
        return -1
    else:
        return 0

# Test with a custom comparison function that compares tuples
def compare_by_second(a, b):
    """Compare tuples by their second element"""
    if a[1] < b[1]:
        return -1
    elif a[1] > b[1]:
        return 1
    else:
        return 0

ARGS = {
    "mycmp": reverse_numeric
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type type — a type output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a type 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
extract_coarse_fea Ran
ran on a synthesized input
princeton-vl/PackIt/packing/packing_fea.py
code served (permissive licence) · get_code("7e06e75d5778a590")
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 ndarray, ndim 1, dtype family float, shape (8,) as a later run recorded it. The image it ran in was 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 numpy as np

# Create a small 3D voxel array (4x5x6)
voxel = np.random.rand(4, 5, 6)

# Feature extraction parameters: extract 2x2x2 coarse features
fea_per_dim = [2, 2, 2]

# Whether to normalize features
norm_fea = True

ARGS = {
    "voxel": voxel,
    "fea_per_dim": fea_per_dim,
    "norm_fea": norm_fea,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (8,) — shape (8,) 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
get_file_id_lst Ran
ran on a synthesized input
princeton-vl/PackIt/packing/packing_evalute.py
code served (permissive licence) · get_code("7b821311df4239de")
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 list, ndim 2, dtype family float; 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 json
import os
import tempfile
import shutil

# Create a temporary directory structure to simulate the environment
temp_dir = tempfile.mkdtemp()
env_name = "TestEnv"
env_data_dir = os.path.join(temp_dir, f"{env_name}_Data/StreamingAssets")
os.makedirs(env_data_dir, exist_ok=True)

# Create a sample pack file with valid JSON data
pack_file_1 = "pack1.json"
pack_file_1_path = os.path.join(env_data_dir, pack_file_1)
pack_data_1 = {
    "data": [
        {"id": 0, "name": "item0"},
        {"id": 1, "name": "item1"},
        {"id": 2, "name": "item2"}
    ]
}
with open(pack_file_1_path, 'w') as f:
    json.dump(pack_data_1, f)

# Create another sample pack file
pack_file_2 = "pack2.json"
pack_file_2_path = os.path.join(env_data_dir, pack_file_2)
pack_data_2 = {
    "data": [
        {"id": 0, "name": "item0"},
        {"id": 1, "name": "item1"}
    ]
}
with open(pack_file_2_path, 'w') as f:
    json.dump(pack_data_2, f)

# Change to the temp directory so relative paths work
original_cwd = os.getcwd()
os.chdir(temp_dir)

try:
    # Define ARGS with valid parameter values
    ARGS = {
        "env_name": env_name,
        "pack_file_name": [pack_file_1, pack_file_2]
    }
finally:
    # Cleanup will happen after function execution
    pass
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, dtype family float — a list 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
indexed_convolution Ran
ran on a synthesized input
princeton-vl/PackIt/packing/packing_fea.py
code served (permissive licence) · get_code("c67469dc3f4e187a")
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 ndarray, ndim 3, dtype family float, shape (3, 2, 4) as a later run recorded it. The image it ran in was 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 numpy as np

# Create a small 3D voxel volume
voxel = np.random.randn(10, 10, 10)

# Create a small 3D filter/kernel
_filter = np.random.randn(3, 3, 3)

# Create index arrays for specific locations to perform convolution
x_indices = np.array([0, 2, 4])
y_indices = np.array([1, 3])
z_indices = np.array([0, 2, 4, 5])

# Boolean flag for filter values optimization
filter_values_same = False

ARGS = {
    "voxel": voxel,
    "_filter": _filter,
    "x_indices": x_indices,
    "y_indices": y_indices,
    "z_indices": z_indices,
    "filter_values_same": filter_values_same,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float, shape (3, 2, 4) — shape (3, 2, 4) 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
success_at Ran
ran on a synthesized input
princeton-vl/PackIt/results.py
code served (permissive licence) · get_code("70624fc4a149ad0c")
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 float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was 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
import numpy as np

torch.manual_seed(0)

# Construct the reward list
reward = [0.5, -0.3, 0.2, -0.8, 0.1]

# Apply the efficiency transformation
efficiency = [x + 1 if x < 0 else x for x in reward]

# Define parameters for success_at function
threshold = 0.5

# Create ARGS dictionary
ARGS = {
    'efficiency': efficiency,
    'threshold': threshold
}
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 float, ndim 0, dtype family float, shape () — shape () 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
batch_norm Not yet run
unverified (harvested, no recorded run)
princeton-vl/PackIt/packing/packing_policy.py
code served (permissive licence) · get_code("7e285ec51db733b2")
How it ran

no invocation recorded.

proj_residual3d Not yet run
unverified (harvested, no recorded run)
princeton-vl/PackIt/packing/packing_policy.py
code served (permissive licence) · get_code("2f3c68de0f252383")
How it ran

no invocation recorded.

residual3d Not yet run
unverified (harvested, no recorded run)
princeton-vl/PackIt/packing/packing_policy.py
code served (permissive licence) · get_code("f35e860ccb5c2998")
How it ran

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 ability to jointly understand the geometry of objects and plan actions for manipulating them is crucial for intelligent agents. We refer to this ability as geometric planning. Recently, many interactive environments have been proposed to evaluate intelligent agents on various skills, however, none of them cater to the needs of geometric planning. We present PackIt, a virtual environment to evaluate and potentially learn the ability to do geometric planning, where an agent needs to take a sequence of actions to pack a set of objects into a box with limited space. We also construct a set of challenging packing tasks using an evolutionary algorithm. Further, we study various baselines for the task that include modelfree learning-based and heuristic-based methods, as well as search-based optimization methods that assume access to the model of the environment. Code and data are available at https: //github.com/princeton-vl/PackIt.

For agents

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

get_harvested_code_for_paper("2007.11121")
get_code_for_paper("2007.11121")
have("2007.11121")

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

curl https://syntology.ai/api/ran/2007.11121.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.11121.svg)](https://syntology.ai/paper/2007.11121)

Connect an agent — have() is free.