SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.14480 · 2020

One Thousand and One Hours: Self-driving Motion Prediction Dataset

arXiv · PDF · Open in the Atlas

Code that ran

9 of 12 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 9 have no contract verdict; 0 failures of our instrument; 3 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/2006.14480.json · badge: /api/ran/2006.14480.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
kazuki-shin/l5kit community (classifier label)
classifier basis not recorded on the link
8 ran · 2 no recorded run
wenkaip-1836890/pyromid_l5prediction community (classifier label)
classifier basis not recorded on the link
1 ran · 1 no recorded run
FunctionStatusWhere it lives
angle_between_vectors Ran
ran on a synthesized input
kazuki-shin/l5kit/l5kit/l5kit/geometry/angle.py
code served (permissive licence) · get_code("a50e4dbbbd238392")
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 float64, 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 numpy as np

# Create two vectors for testing
v1 = np.array([1.0, 0.0, 0.0])
v2 = np.array([0.0, 1.0, 0.0])

ARGS = {
    "v1": v1,
    "v2": v2,
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
compute_mse_error_csv Ran
ran on a synthesized input
kazuki-shin/l5kit/l5kit/l5kit/evaluation/extract_losses.py
code served (permissive licence) · get_code("d1f37740b489c259")
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 (2,) 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 csv
import numpy as np
import tempfile
import os

# Create temporary directory for CSV files
temp_dir = tempfile.mkdtemp()

# Create ground truth CSV file
ground_truth_path = os.path.join(temp_dir, 'ground_truth.csv')
with open(ground_truth_path, 'w', newline='') as f:
    writer = csv.writer(f)
    writer.writerow(['id', 'name', 'val1', 'val2', 'val3', 'val4'])
    writer.writerow(['1', 'obs_a', '1.0', '2.0', '3.0', '4.0'])
    writer.writerow(['2', 'obs_b', '5.0', '6.0', '7.0', '8.0'])

# Create inference output CSV file
inference_output_path = os.path.join(temp_dir, 'inference.csv')
with open(inference_output_path, 'w', newline='') as f:
    writer = csv.writer(f)
    writer.writerow(['id', 'name', 'val1', 'val2', 'val3', 'val4'])
    writer.writerow(['1', 'obs_a', '1.1', '2.1', '3.1', '4.1'])
    writer.writerow(['2', 'obs_b', '5.1', '6.1', '7.1', '8.1'])

ARGS = {
    'ground_truth_path': ground_truth_path,
    'inference_output_path': inference_output_path,
}
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 (2,) — shape (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
compute_yaw_around_north_from_direction Ran
ran on a synthesized input
kazuki-shin/l5kit/l5kit/l5kit/geometry/angle.py
code served (permissive licence) · get_code("11d84a4585550ba9")
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 float64, 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 numpy as np

# Create a direction vector in 2D space
# This vector points roughly northeast
direction_vector = np.array([1.0, 1.0])

ARGS = {
    "direction_vector": direction_vector
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
fit_ackerman_model_exact Ran
ran on a synthesized input
kazuki-shin/l5kit/l5kit/l5kit/kinematic/ackerman_steering_model.py
code served (permissive licence) · get_code("1bf44bcbbd74c8b0")
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 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 numpy as np
from scipy import optimize

# Create small valid numpy arrays for the trajectory waypoints
N = 5  # Number of waypoints

# Initial state
x0 = np.array([0.0])
y0 = np.array([0.0])
r0 = np.array([0.0])  # Initial rotation
v0 = np.array([1.0])  # Initial velocity

# Ground truth (target) waypoints
gx = np.array([0.0, 1.0, 2.0, 2.5, 3.0])
gy = np.array([0.0, 0.5, 1.0, 2.0, 2.5])
gr = np.array([0.0, 0.1, 0.2, 0.3, 0.4])
gv = np.array([1.0, 1.1, 1.2, 1.1, 1.0])

# Weights for each dimension
wgx = np.ones(N)
wgy = np.ones(N)
wgr = np.zeros(N)
wgv = np.zeros(N)

# Parameters
ws = 5.0  # Weight for steering
wa = 5.0  # Weight for acceleration
min_acc = -0.1
max_acc = 0.1
min_steer = -0.2
max_steer = 0.2

ARGS = {
    'x0': x0,
    'y0': y0,
    'r0': r0,
    'v0': v0,
    'gx': gx,
    'gy': gy,
    'gr': gr,
    'gv': gv,
    'wgx': wgx,
    'wgy': wgy,
    'wgr': wgr,
    'wgv': wgv,
    'ws': ws,
    'wa': wa,
    'min_acc': min_acc,
    'max_acc': max_acc,
    'min_steer': min_steer,
    'max_steer': max_steer,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, 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
forward_resnet50 Ran
ran on a synthesized input
wenkaip-1836890/pyromid_l5prediction/agent_motion_prediction.py
code served (permissive licence) · get_code("08332f03eefbeebe")
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 torch.nn as nn

torch.manual_seed(0)

# Build a minimal ResNet50-like model
class MinimalResNet50(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(3, 16, kernel_size=3, padding=1)
        self.fc = nn.Linear(16 * 4 * 4, 8)
    
    def forward(self, x):
        x = self.conv1(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)
        return x

# Build a minimal criterion that supports reduction
class MinimalCriterion(nn.Module):
    def __init__(self):
        super().__init__()
        self.mse = nn.MSELoss(reduction='none')
    
    def forward(self, outputs, targets):
        return self.mse(outputs, targets)

# Create model and criterion
model = MinimalResNet50()
criterion = MinimalCriterion()
device = 'cpu'

# Create data dict with correct structure
data = {
    'image': torch.randn(2, 3, 4, 4),
    'target_positions': torch.randn(2, 8)
}

ARGS = {
    'data': data,
    'model': model,
    'device': device,
    'criterion': criterion
}
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 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
in_angular_distance Ran
ran on a synthesized input
kazuki-shin/l5kit/l5kit/l5kit/dataset/select_agents.py
code served (permissive licence) · get_code("e0ae661ca3c6d2b9")
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 numpy as np

# Create valid arguments for in_angular_distance
yaw1 = np.array(0.5236)  # ~30 degrees in radians
yaw2 = np.array(0.7854)  # ~45 degrees in radians
th = 20.0  # threshold in degrees

ARGS = {
    "yaw1": yaw1,
    "yaw2": yaw2,
    "th": th
}
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 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
in_av_distance Ran
ran on a synthesized input
kazuki-shin/l5kit/l5kit/l5kit/dataset/select_agents.py
code served (permissive licence) · get_code("39730a93a95dfc59")
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 numpy as np

# Create arguments for in_av_distance function
av_translation = np.array([1.5, 2.3, 0.8])  # 3D translation vector, first 2 elements used
agent_centroid = np.array([1.2, 2.1])  # 2D centroid position
th = 0.5  # threshold distance

ARGS = {
    "av_translation": av_translation,
    "agent_centroid": agent_centroid,
    "th": th
}
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 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
in_consecutive_frame Ran
ran on a synthesized input
kazuki-shin/l5kit/l5kit/l5kit/dataset/select_agents.py
code served (permissive licence) · get_code("f520542801f4bbc1")
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 torch

torch.manual_seed(0)

ARGS = {
    "frame_idx": 5,
    "past_frame_idx": 4,
}
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 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
load_config_data Ran
ran on a synthesized input
kazuki-shin/l5kit/l5kit/l5kit/configs/config.py
code served (permissive licence) · get_code("557e35ed5eacf6ab")
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 yaml
import tempfile
import os

# Create a temporary YAML file with valid config data
temp_dir = tempfile.mkdtemp()
config_path = os.path.join(temp_dir, "config.yaml")

config_content = """
model:
  name: test_model
  layers: 3
  hidden_dim: 128
training:
  batch_size: 32
  learning_rate: 0.001
  epochs: 10
data:
  source: dataset_path
  split: 0.8
"""

with open(config_path, 'w') as f:
    f.write(config_content)

ARGS = {
    "path": config_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yaml — 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
build_model_resnet50 Not yet run
unverified (harvested, no recorded run)
wenkaip-1836890/pyromid_l5prediction/agent_motion_prediction.py
code served (permissive licence) · get_code("27cde99d4fbcd6fa")
How it ran

no invocation recorded.

crop_rectangle_from_image Not yet run
unverified (harvested, no recorded run)
kazuki-shin/l5kit/l5kit/l5kit/geometry/image.py
code served (permissive licence) · get_code("d57b6311bb1a8031")
How it ran

no invocation recorded.

fit_ackerman_model_approximate Not yet run
unverified (harvested, no recorded run)
kazuki-shin/l5kit/l5kit/l5kit/kinematic/ackerman_steering_model.py
code served (permissive licence) · get_code("3d42c5f091c331f2")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 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 12 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

Motivated by the impact of large-scale datasets on ML systems we present the largest self-driving dataset for motion prediction to date, containing over 1,000 hours of data. This was collected by a fleet of 20 autonomous vehicles along a fixed route in Palo Alto, California, over a four-month period. It consists of 170,000 scenes, where each scene is 25 seconds long and captures the perception output of the self-driving system, which encodes the precise positions and motions of nearby vehicles, cyclists, and pedestrians over time. On top of this, the dataset contains a high-definition semantic map with 15,242 labelled elements and a high-definition aerial view over the area. We show that using a dataset of this size dramatically improves performance for key self-driving problems. Combined with the provided software kit, this collection forms the largest and most detailed dataset to date for the development of self-driving machine learning tasks, such as motion forecasting, motion planning and simulation. The full dataset is available at http://level5.lyft.com/.

For agents

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

get_harvested_code_for_paper("2006.14480")
get_code_for_paper("2006.14480")
have("2006.14480")

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

curl https://syntology.ai/api/ran/2006.14480.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.14480.svg)](https://syntology.ai/paper/2006.14480)

Connect an agent — have() is free.