SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.02072 · 2026

Calibrating Adaptive Smoothing Methods for Freeway Traffic Reconstruction

Junyi Ji, Derek Gloudemans, Gergely Zachár, Matthew Nice, William Barbour, Daniel Work

arXiv · PDF · Open in the Atlas

Code that ran

9 of 11 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; 8 failures of our instrument; 2 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/2602.02072.json · badge: /api/ran/2602.02072.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
trafficwaves/ASMx canonical (classifier label)
classifier basis: census
9 ran · 2 no recorded run
FunctionStatusWhere it lives
fft_four_convs Ran
ran; our contract draft was wrong, not the code
trafficwaves/ASMx/ASM_utils.py
code served (permissive licence) · get_code("2c943e1da501dc4a")
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 5, 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)

# Tiny tensor dimensions: B=2, C=3, H=5, W=4, F=2, Kh=2, Kw=2
B, C, H, W = 2, 3, 5, 4
F, Kh, Kw = 2, 2, 2

# Create input tensors
Dp = torch.randn(B, C, H, W)
Mp = torch.randn(B, C, H, W)

# Create kernel tensors
k_cong = torch.randn(F, C, Kh, Kw)
k_free = torch.randn(F, C, Kh, Kw)

# Create arguments dict
ARGS = {
    'Dp': Dp,
    'Mp': Mp,
    'k_cong': k_cong,
    'k_free': k_free,
    'use_ortho': True,
}
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, ndim 5, 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
fill_space_time_matrix Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
trafficwaves/ASMx/preprocessing/corridor_preprocessing.py
code served (permissive licence) · get_code("9f495880b081606d")
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 DataFrame. 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
import pandas as pd

# Create sample raw data with the required columns
np.random.seed(0)

n_samples = 50
raw_data = pd.DataFrame({
    'milemarker': np.random.uniform(53.3, 70.1, n_samples),
    'time_unix_fix': np.random.uniform(1000000, 1000600, n_samples),
    'lane1_speed': np.random.uniform(30, 80, n_samples),
    'lane1_volume': np.random.uniform(100, 500, n_samples),
})

ARGS = {
    'raw_data': raw_data,
    'dx': 0.1,
    'dt': 10,
    'lane': 1,
    'data_type': 'speed',
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 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
fill_space_time_matrix Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
trafficwaves/ASMx/preprocessing/preprocessing.py
code served (permissive licence) · get_code("c7668c51d6f1583a")
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 DataFrame. 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
import pandas as pd

# Create sample raw data with required columns
np.random.seed(0)

# Generate time data
num_records = 50
base_time = 1000000
time_unix_fix = np.sort(np.random.uniform(base_time, base_time + 5000, num_records))

# Generate milemarker data in the range that will be used
milemarker = np.random.uniform(58.7, 62.7, num_records)

# Generate speed data for lane 1
lane1_speed = np.random.uniform(40, 80, num_records)

raw_data = pd.DataFrame({
    'milemarker': milemarker,
    'time_unix_fix': time_unix_fix,
    'lane1_speed': lane1_speed
})

ARGS = {
    'raw_data': raw_data,
    'dx': 0.1,
    'dt': 10,
    'lane': 1,
    'data_type': 'speed'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 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
fill_space_time_matrix Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
trafficwaves/ASMx/production/ASMxCorridor.py
code served (permissive licence) · get_code("5fc22ff2774f94d4")
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 DataFrame. 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
import pandas as pd

# Create sample raw data with required columns
raw_data = pd.DataFrame({
    'milemarker': [10.2, 10.5, 10.8, 11.1, 11.4, 10.3, 10.6, 10.9, 11.2, 11.5],
    'time_unix_fix': [1609459200, 1609459210, 1609459220, 1609459230, 1609459240, 
                      1609459205, 1609459215, 1609459225, 1609459235, 1609459245],
    'lane1_speed': [65.5, 64.2, 66.1, 63.8, 65.0, 64.5, 65.3, 64.9, 66.2, 63.5]
})

ARGS = {
    'raw_data': raw_data,
    'dx': 0.1,
    'dt': 10,
    'lane': 1,
    'data_type': 'speed'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 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
rmse Ran
ran; our contract draft was wrong, not the code
trafficwaves/ASMx/calibration/train_day_to_day.py
code served (permissive licence) · get_code("3f8af5d6dd4be49b")
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 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)

# Create small tensors for pred and target
# Using shape (2, 4) for batch_size=2, feature_dim=4
pred = torch.randn(2, 4)
target = torch.randn(2, 4)

# Create a mask with the same shape, containing only 0s and 1s
mask = torch.randint(0, 2, (2, 4)).float()

ARGS = {
    "pred": pred,
    "target": target,
    "mask": mask,
}
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 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
round_to_fix Ran
ran, honoured the contract we drafted
trafficwaves/ASMx/preprocessing/FAST.py
code served (permissive licence) · get_code("522cd8b9d94f756b")
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.

from datetime import datetime, timedelta

# Construct a valid datetime object as an argument
# The function expects a datetime object with second and microsecond attributes
test_time = datetime(2023, 10, 15, 12, 30, 45, 500000)

ARGS = {
    "time": test_time
}
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 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
split_date Ran
ran; our contract draft was wrong, not the code
trafficwaves/ASMx/preprocessing/corridor_fast_processing.py
code served (permissive licence) · get_code("0166d15dc642a20c")
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 str. 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)

def split_date(entry):
    return entry.split('.')[0]

ARGS = {
    "entry": "2024.01.15"
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
wasserstein_distance Ran
ran; our contract draft was wrong, not the code
trafficwaves/ASMx/calibration/train_day_to_day.py
code served (permissive licence) · get_code("35413fedd41072d8")
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 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)

# Create small tensors for pred and target
pred = torch.randn(2, 4)
target = torch.randn(2, 4)

# Create a binary mask tensor
mask = torch.ones(2, 4)

ARGS = {
    "pred": pred,
    "target": target,
    "mask": mask,
}
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 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
weighted_rmse Ran
ran; our contract draft was wrong, not the code
trafficwaves/ASMx/calibration/seeds.py
code served (permissive licence) · get_code("b65140a8da4b4c99")
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 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)

# Create small tensors for pred and target
# pred: predicted values, shape (2, 4)
pred = torch.randn(2, 4)

# target: ground truth values, shape (2, 4)
target = torch.randn(2, 4)

# mask: optional binary mask, shape (2, 4)
mask = torch.randint(0, 2, (2, 4)).float()

# threshold and high_weight are scalar floats
threshold = 15.0
high_weight = 10.0

ARGS = {
    'pred': pred,
    'target': target,
    'mask': mask,
    'threshold': threshold,
    'high_weight': high_weight,
}
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 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
fft_four_convs Not yet run
unverified (harvested, no recorded run)
trafficwaves/ASMx/calibration/ASM_utils.py
code served (permissive licence) · get_code("be4ebce8abd125ed")
How it ran

no invocation recorded.

time_to_unix Not yet run
unverified (harvested, no recorded run)
trafficwaves/ASMx/preprocessing/corridor_fast_processing.py
code served (permissive licence) · get_code("22638c880829ccd5")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 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 11 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 adaptive smoothing method (ASM) is a widely used approach for traffic state reconstruction. This article presents a Python implementation of ASM, featuring endto-end calibration using real-world ground truth data. The calibration is formulated as a parameterized kernel optimization problem. The model is calibrated using data from a full-state observation testbed, with input from a sparse radar sensor network. The implementation is developed in PyTorch, enabling integration with various deep learning methods. We evaluate the results in terms of speed distribution, spatiotemporal error distribution, and spatial error to provide benchmark metrics for the traffic reconstruction problem. We further demonstrate the usability of the calibrated method across multiple freeways. Finally, we discuss the challenges of reproducibility in general traffic model calibration and the limitations of ASM. This article is reproducible and can serve as a benchmark for various freeway operation tasks.

For agents

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

get_harvested_code_for_paper("2602.02072")
get_code_for_paper("2602.02072")
have("2602.02072")

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

curl https://syntology.ai/api/ran/2602.02072.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.02072.svg)](https://syntology.ai/paper/2602.02072)

Connect an agent — have() is free.