SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1906.01401 · 2019

Unsupervised Emergence of Egocentric Spatial Structure from Sensorimotor Prediction

arXiv · PDF · Open in the Atlas

Code that ran

8 of 16 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 8 have no contract verdict; 0 failures of our instrument; 8 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/1906.01401.json · badge: /api/ran/1906.01401.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
alaflaquiere/learn-spatial-structure canonical (classifier label)
classifier basis: census
8 ran · 8 no recorded run
FunctionStatusWhere it lives
compute_yaw_and_pitch Ran
ran on a synthesized input
alaflaquiere/learn-spatial-structure/gqn_renderer/bullet_tools.py
code served (permissive licence) · get_code("0ac8905b73b4afc7")
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 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 numpy as np

# The function takes a single parameter 'vec' which should be a sequence/array
# with 3 elements (x, y, z) that can be unpacked and used in numpy operations

# Create a test vector
vec = np.array([1.0, 0.5, 2.0])

ARGS = {
    'vec': vec
}
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 tuple, ndim 1, dtype family float — 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
create_directory Ran
ran on a synthesized input
alaflaquiere/learn-spatial-structure/tools.py
code served (permissive licence) · get_code("c548708ccee68214")
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 bool, 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 tempfile
import os

# Create a temporary directory for testing
temp_dir = tempfile.mkdtemp()
test_directory = os.path.join(temp_dir, "test_folder")

ARGS = {
    "directory": test_directory,
    "safe": False
}
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 bool, 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
get_colors Ran
ran on a synthesized input
alaflaquiere/learn-spatial-structure/gqn_renderer/bullet_tools.py
code served (permissive licence) · get_code("f449c1a2566eada5")
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 colorsys

ARGS = {
    "num_colors": 6
}
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
load_compressed_sensorimotor_transitions Ran
ran on a synthesized input
alaflaquiere/learn-spatial-structure/tools.py
code served (permissive licence) · get_code("5edba394179a59f5")
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 dict. 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 os
import sys
import numpy as np
import tempfile

# Create a temporary directory with a valid npz file
temp_dir = tempfile.mkdtemp()

# Create sample sensorimotor data
motor_t = np.random.randn(10, 3).astype(np.float32)
sensor_t = np.random.randn(10, 4).astype(np.float32)
shift_t = np.random.randn(10, 2).astype(np.float32)
motor_tp = np.random.randn(10, 3).astype(np.float32)
sensor_tp = np.random.randn(10, 4).astype(np.float32)
shift_tp = np.random.randn(10, 2).astype(np.float32)

# Save as npz file
npz_path = os.path.join(temp_dir, 'sensorimotor_data.npz')
np.savez(
    npz_path,
    motor_t=motor_t,
    sensor_t=sensor_t,
    shift_t=shift_t,
    motor_tp=motor_tp,
    sensor_tp=sensor_tp,
    shift_tp=shift_tp
)

ARGS = {
    'data_directory': npz_path,
    'n_transitions': 5
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
load_sensorimotor_transitions Ran
ran on a synthesized input
alaflaquiere/learn-spatial-structure/tools.py
code served (permissive licence) · get_code("669e9e80fc63cb41")
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 dict. 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 os
import sys
import numpy as np
import _pickle as cpickle
import tempfile

# Create a temporary directory and pickle file with valid sensorimotor data
temp_dir = tempfile.mkdtemp()
data_file = os.path.join(temp_dir, 'sensorimotor_data.pkl')

# Create sample sensorimotor data
sample_data = {
    'motor_t': np.random.randn(10, 3),
    'sensor_t': np.random.randn(10, 4),
    'shift_t': np.random.randn(10, 2),
    'motor_tp': np.random.randn(10, 3),
    'sensor_tp': np.random.randn(10, 4),
    'shift_tp': np.random.randn(10, 2),
}

# Save the data to a pickle file
with open(data_file, 'wb') as f:
    cpickle.dump(sample_data, f)

ARGS = {
    'data_directory': data_file,
    'n_transitions': 5,
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
opengl_to_bullet_frame Ran
ran on a synthesized input
alaflaquiere/learn-spatial-structure/gqn_renderer/bullet_tools.py
code served (permissive licence) · get_code("a2fa0b636edc229c")
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 1, 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 torch

torch.manual_seed(0)

# The function expects a vector with 3 elements (xyz coordinates)
# It accesses vec[0], vec[1], vec[2] via indexing
# It returns a list of 3 elements

ARGS = {
    "vec": [1.0, 2.0, 3.0]
}
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 list, ndim 1, 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
save_training Ran
ran on a synthesized input
alaflaquiere/learn-spatial-structure/train_network.py
code served (permissive licence) · get_code("38da9e9b4293a600")
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 bool, ndim 0, 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 datetime
import uuid
import tempfile
import os

# Create a temporary directory structure for testing
temp_dir = tempfile.mkdtemp()
data_dir = tempfile.mkdtemp()

# Create the generation_params.txt file that the function expects to read
generation_params = {
    'UUID': uuid.uuid4().hex,
    'param1': 'value1'
}
with open(os.path.join(data_dir, 'generation_params.txt'), 'w') as f:
    json.dump(generation_params, f)

# Create a mock args object with required attributes
class Args:
    def __init__(self):
        self.sigma_noise_motor = 0.05
        self.sigma_noise_sensor = 0.03
        self.n_epochs = 100

# Mock the get_git_hash function that's called in save_training
def get_git_hash():
    return "abc1234def5678"

# Insert the mock function into the global scope so save_training can use it
import sys
current_module = sys.modules[__name__]
setattr(current_module, 'get_git_hash', get_git_hash)

ARGS = {
    'directory': temp_dir,
    'path_data': data_dir,
    'run': 1,
    'type_simu': 'neural_network',
    'args': Args()
}
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 bool, ndim 0, dtype family float — no output shape is stated: observe_signature.py could not observe it (fixture:KeyError)
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
split_filename Ran
ran on a synthesized input
alaflaquiere/learn-spatial-structure/gqn_renderer/urdf/obj_to_urdf_converter.py
code served (permissive licence) · get_code("97ea824910a8f489")
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 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 os

def split_filename(string):
    path_to_file = os.path.dirname(string)
    filename, extension = os.path.splitext(os.path.basename(string))
    return (path_to_file, filename, extension)

ARGS = {
    "string": "/home/user/documents/myfile.txt"
}
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 tuple, ndim 1, dtype family float — 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
check_savability Not yet run
unverified (harvested, no recorded run)
alaflaquiere/learn-spatial-structure/generate_sensorimotor_data.py
code served (permissive licence) · get_code("7b96a764747985bc")
How it ran

no invocation recorded.

display_all_projections_of_a_single_run Not yet run
unverified (harvested, no recorded run)
alaflaquiere/learn-spatial-structure/analyze_network.py
code served (permissive licence) · get_code("0f18608976845162")
How it ran

no invocation recorded.

display_data Not yet run
unverified (harvested, no recorded run)
alaflaquiere/learn-spatial-structure/display_progress.py
code served (permissive licence) · get_code("da992feb99476646")
How it ran

no invocation recorded.

load_subdirectory_data Not yet run
unverified (harvested, no recorded run)
alaflaquiere/learn-spatial-structure/analyze_network.py
code served (permissive licence) · get_code("28c99f6bc48412f5")
How it ran

no invocation recorded.

mlp Not yet run
unverified (harvested, no recorded run)
alaflaquiere/learn-spatial-structure/Networks.py
code served (permissive licence) · get_code("2420edc5273f2b91")
How it ran

no invocation recorded.

read_and_display_results Not yet run
unverified (harvested, no recorded run)
alaflaquiere/learn-spatial-structure/analyze_network.py
code served (permissive licence) · get_code("088bc220d3d50ca0")
How it ran

no invocation recorded.

save_compressed_dictionary Not yet run
unverified (harvested, no recorded run)
alaflaquiere/learn-spatial-structure/generate_sensorimotor_data.py
code served (permissive licence) · get_code("55e4fde63c2fbf8b")
How it ran

no invocation recorded.

save_dictionary Not yet run
unverified (harvested, no recorded run)
alaflaquiere/learn-spatial-structure/generate_sensorimotor_data.py
code served (permissive licence) · get_code("6812386eab351693")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 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 16 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

Despite its omnipresence in robotics application, the nature of spatial knowledge and the mechanisms that underlie its emergence in autonomous agents are still poorly understood. Recent theoretical works suggest that the Euclidean structure of space induces invariants in an agent's raw sensorimotor experience. We hypothesize that capturing these invariants is beneficial for sensorimotor prediction and that, under certain exploratory conditions, a motor representation capturing the structure of the external space should emerge as a byproduct of learning to predict future sensory experiences. We propose a simple sensorimotor predictive scheme, apply it to different agents and types of exploration, and evaluate the pertinence of these hypotheses. We show that a naive agent can capture the topology and metric regularity of its sensor's position in an egocentric spatial frame without any a priori knowledge, nor extraneous supervision.

For agents

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

get_harvested_code_for_paper("1906.01401")
get_code_for_paper("1906.01401")
have("1906.01401")

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

curl https://syntology.ai/api/ran/1906.01401.json

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

[![Syntology run record](https://syntology.ai/api/ran/1906.01401.svg)](https://syntology.ai/paper/1906.01401)

Connect an agent — have() is free.