SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.02649 · 2023

CCIL: Context-conditioned imitation learning for urban driving

arXiv · PDF · Open in the Atlas

Code that ran

7 of 7 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 6 have no contract verdict; 1 failure 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/2305.02649.json · badge: /api/ran/2305.02649.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
Kguo-cs/ccil community (classifier label)
classifier basis not recorded on the link
7 ran · 0 no recorded run
FunctionStatusWhere it lives
bger Ran
ran; our contract draft was wrong, not the code
Kguo-cs/ccil/model/lqr_solver.py
pointer only (licence: MIT); the stored copy get_code serves, from jiaweihe1996/GMTracker, is pointer only (licence: GPL-3.0) · get_code("612774f5e2ab3ddb")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from jiaweihe1996/GMTracker, and GPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

eclamp Ran
ran on a synthesized input
Kguo-cs/ccil/model/lqr_solver.py
code served (permissive licence) · get_code("24985d610459b138")
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 Tensor, ndim 2, dtype family float, shape (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 torch

torch.manual_seed(0)

# Construct valid arguments for eclamp function
# The function clamps tensor x between lower and upper bounds
# lower and upper can be tensors (same size as x) or floats

x = torch.randn(2, 4)
lower = torch.randn(2, 4)
upper = torch.randn(2, 4)

# Ensure lower < upper for valid clamping
lower = torch.minimum(lower, upper)
upper = torch.maximum(lower, upper + 1.0)

ARGS = {
    "x": x,
    "lower": lower,
    "upper": upper
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (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
get_device Ran
ran on a synthesized input
Kguo-cs/ccil/evaluate/metric_utils.py
code served (permissive licence) · get_code("4617723d7391e6d7")
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 device. 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

torch.manual_seed(0)

# The function get_device(val) extracts the device from tensors or recursively
# searches through dicts, lists, and tuples for tensors.
# We need to provide a value that exercises the function.

# Test with a tensor on CPU
tensor_val = torch.randn(2, 4)

ARGS = {
    "val": tensor_val
}
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 device — a device output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a device 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
get_history Ran
ran on a synthesized input
Kguo-cs/ccil/toy/ccil_dataset.py
code served (permissive licence) · get_code("99dc0150556c98f4")
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 numpy as np

ARGS = {
    "radius": 5.0,
    "cur_theta": np.pi / 4,
    "speed": 2.0
}
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 — 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
make_categorical Ran
ran on a synthesized input
Kguo-cs/ccil/evaluate/metric_utils.py
code served (permissive licence) · get_code("48ddcc59dab8479e")
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 ABCMeta. 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 torchmetrics
from torch import nn

torch.manual_seed(0)

# Create a simple metric class to pass to make_categorical
# We'll use a built-in torchmetric that's simple and well-supported
class SimpleMetric(torchmetrics.Metric):
    def __init__(self):
        super().__init__()
        self.add_state("value", default=torch.tensor(0.0), dist_reduce_fx="sum")
    
    def update(self, x):
        self.value += x
    
    def compute(self):
        return self.value

ARGS = {
    "cls": SimpleMetric
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchmetrics — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ABCMeta — a ABCMeta output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ABCMeta 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
pnqp Ran
ran on a synthesized input
Kguo-cs/ccil/model/lqr_solver.py
code served (permissive licence) · get_code("35abbdd57a673c2b")
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
torch.manual_seed(0)

# The function pnqp solves a batch of quadratic programs
# H: (n_batch, n, n) - Hessian matrices
# q: (n_batch, n) - linear term
# lower: (n_batch, n) or float - lower bounds
# upper: (n_batch, n) or float - upper bounds
# x_init: (n_batch, n) or None - initial point

n_batch = 2
n = 4

# Create positive definite Hessian matrices for stable QP solving
H = torch.randn(n_batch, n, n)
H = H @ H.transpose(-2, -1) + torch.eye(n).unsqueeze(0) * 0.1  # Make PD

# Linear term
q = torch.randn(n_batch, n)

# Lower and upper bounds - use tensors with same shape as x
lower = -torch.ones(n_batch, n)
upper = torch.ones(n_batch, n)

# Initial point (optional)
x_init = torch.zeros(n_batch, n)

ARGS = {
    'H': H,
    'q': q,
    'lower': lower,
    'upper': upper,
    'x_init': x_init,
    'n_iter': 20
}
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
safe_compute Ran
ran on a synthesized input
Kguo-cs/ccil/evaluate/metric_utils.py
code served (permissive licence) · get_code("c3bcfb16fafde775")
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 torch
import torch.nn as nn

torch.manual_seed(0)

class MockMetric:
    """A mock metric object with a compute() method."""
    def compute(self):
        return {"accuracy": 0.95, "loss": 0.05}

class MockMetricException:
    """A mock metric object that raises an exception."""
    def compute(self):
        raise ValueError("Computation failed")

# Test with a valid metric
metric_valid = MockMetric()

# Test with a metric that raises an exception
metric_invalid = MockMetricException()

# Create arguments dictionary
ARGS = {
    "metric": metric_valid,
    "default_val": None
}
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 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

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 6 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
bger 3 other papers
3 dated earlier · 1 only as an assembly brick
2010.13943 (2020-10)
Interior Point Solving for LP-based prediction+optimisation
2103.16178 (2021-03)
Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking
2106.12900 (2021-06)
Long-term Cross Adversarial Training: A Robust Meta-learning Method for Few-shot Classification Tasks

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

Imitation learning holds great promise for addressing the complex task of autonomous urban driving, as experienced human drivers can navigate highly challenging scenarios with ease. While behavior cloning is a widely used imitation learning approach in autonomous driving due to its exemption from risky online interactions, it suffers from the covariate shift issue. To address this limitation, we propose a context-conditioned imitation learning approach that employs a policy to map the context state into the ego vehicle's future trajectory, rather than relying on the traditional formulation of both ego and context states to predict the ego action. Additionally, to reduce the implicit ego information in the coordinate system, we design an ego-perturbed goal-oriented coordinate system. The origin of this coordinate system is the ego vehicle's position plus a zero mean Gaussian perturbation, and the x-axis direction points towards its goal position. Our experiments on the real-world large-scale Lyft and nuPlan datasets show that our method significantly outperforms state-of-the-art approaches.

For agents

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

get_harvested_code_for_paper("2305.02649")
get_code_for_paper("2305.02649")
have("2305.02649")

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

curl https://syntology.ai/api/ran/2305.02649.json

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

[![Syntology run record](https://syntology.ai/api/ran/2305.02649.svg)](https://syntology.ai/paper/2305.02649)

Connect an agent — have() is free.