SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.11927 · 2020

Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 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 4 have no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-21; 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/2002.11927.json · badge: /api/ran/2002.11927.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
abduallahmohamed/Social-STGCNN canonical (classifier label)
classifier basis: census
4 ran · 2 no recorded run
FunctionStatusWhere it lives
ade Ran
ran on a synthesized input
abduallahmohamed/Social-STGCNN/metrics.py
code served (permissive licence) · get_code("8fa690d6645c903e")
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 numpy as np
import math

# Construct the arguments for the ade function
# The function expects:
# - predAll: list of prediction arrays
# - targetAll: list of target arrays
# - count_: list of counts for each batch

# Create small sample data
# Each element should be shape (num_agents, max_time, 2) where 2 is x,y coordinates
# We'll create 2 sequences with different shapes to test the function

# Sequence 1: 3 agents, 4 time steps
pred1 = np.random.randn(3, 4, 2).astype(np.float32)
target1 = np.random.randn(3, 4, 2).astype(np.float32)

# Sequence 2: 2 agents, 5 time steps
pred2 = np.random.randn(2, 5, 2).astype(np.float32)
target2 = np.random.randn(2, 5, 2).astype(np.float32)

# Create lists of predictions and targets
predAll = [pred1, pred2]
targetAll = [target1, target2]

# count_ specifies how many agents to use from each sequence
# For seq1 we use 3 agents, for seq2 we use 2 agents
count_ = [3, 2]

ARGS = {
    "predAll": predAll,
    "targetAll": targetAll,
    "count_": count_
}
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 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
anorm Ran
ran on a synthesized input
abduallahmohamed/Social-STGCNN/utils.py
code served (permissive licence) · get_code("56c3d21e5a44de5d")
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 math

def anorm(p1, p2):
    NORM = math.sqrt((p1[0] - p2[0]) ** 2 + (p1[1] - p2[1]) ** 2)
    if NORM == 0:
        return 0
    return 1 / NORM

# p1 and p2 should be indexable sequences with at least 2 numeric elements
# The function accesses p1[0], p1[1], p2[0], p2[1]
p1 = [1.0, 2.0]
p2 = [4.0, 6.0]

ARGS = {
    "p1": p1,
    "p2": p2,
}
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
fde Ran
ran on a synthesized input
abduallahmohamed/Social-STGCNN/metrics.py
code served (permissive licence) · get_code("008d22e2efe19b01")
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 numpy as np
import math

# Analyze the function:
# - predAll: list of arrays, each accessed as predAll[s]
# - targetAll: list of arrays, each accessed as targetAll[s]
# - count_: list/array of integers, accessed as count_[s]
# - Each predAll[s] and targetAll[s] is indexed as [timestep, agent_id, coordinates]
# - After swapaxes(0,1), shape becomes [agent_id, timestep, coordinates]
# - The function loops over agents and timesteps, accessing [:, :, 0] and [:, :, 1] (x, y coords)

# Build small test data
# Let's create 2 samples (All=2)
np.random.seed(0)

# Sample 1: 3 timesteps, 2 agents, 2 coordinates (x, y)
pred1 = np.random.randn(3, 2, 2).astype(np.float32)
target1 = np.random.randn(3, 2, 2).astype(np.float32)

# Sample 2: 4 timesteps, 2 agents, 2 coordinates (x, y)
pred2 = np.random.randn(4, 2, 2).astype(np.float32)
target2 = np.random.randn(4, 2, 2).astype(np.float32)

predAll = [pred1, pred2]
targetAll = [target1, target2]

# count_ specifies how many agents to use from each sample
# count_[0] applies to predAll[0] and targetAll[0], etc.
count_ = [2, 2]  # Use all 2 agents from each sample

ARGS = {
    'predAll': predAll,
    'targetAll': targetAll,
    'count_': count_
}
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 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
poly_fit Ran
ran on a synthesized input
abduallahmohamed/Social-STGCNN/utils.py
code served (permissive licence) · get_code("48470836236aa9df")
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 numpy as np

# Construct a valid trajectory: shape (2, traj_len)
# The function uses traj[0, -traj_len:] and traj[1, -traj_len:] to extract the last traj_len elements
traj = np.array([
    [1.0, 2.0, 3.0, 4.0, 5.0],
    [2.0, 4.0, 6.0, 8.0, 10.0]
])

traj_len = 5

# threshold: a numeric value that determines if trajectory is non-linear
# Setting a low threshold so the function can return either 0 or 1
threshold = 0.5

ARGS = {
    "traj": traj,
    "traj_len": traj_len,
    "threshold": threshold
}
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 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
seq_to_graph Not yet run
unverified (harvested, no recorded run)
abduallahmohamed/Social-STGCNN/utils.py
code served (permissive licence) · get_code("c1feb649ed5942a7")
How it ran

no invocation recorded.

seq_to_nodes Not yet run
unverified (harvested, no recorded run)
abduallahmohamed/Social-STGCNN/metrics.py
code served (permissive licence) · get_code("c35f811b4fcb5e26")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 5 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 5 later) and 1 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
ade 1 other paper
1 later
2203.03057 (2022-03)
Social-Implicit: Rethinking Trajectory Prediction Evaluation and The Effectiveness of Implicit Maximum Likelihood Estimation
anorm 1 other paper
1 later
2203.03057 (2022-03)
Social-Implicit: Rethinking Trajectory Prediction Evaluation and The Effectiveness of Implicit Maximum Likelihood Estimation
fde 1 other paper
1 later
2203.03057 (2022-03)
Social-Implicit: Rethinking Trajectory Prediction Evaluation and The Effectiveness of Implicit Maximum Likelihood Estimation
poly_fit 1 other paper
1 later
2203.03057 (2022-03)
Social-Implicit: Rethinking Trajectory Prediction Evaluation and The Effectiveness of Implicit Maximum Likelihood Estimation
seq_to_nodes 1 other paper
1 later
2203.03057 (2022-03)
Social-Implicit: Rethinking Trajectory Prediction Evaluation and The Effectiveness of Implicit Maximum Likelihood Estimation

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Better machine understanding of pedestrian behaviors enables faster progress in modeling interactions between agents such as autonomous vehicles and humans. Pedestrian trajectories are not only influenced by the pedestrian itself but also by interaction with surrounding objects. Previous methods modeled these interactions by using a variety of aggregation methods that integrate different learned pedestrians states. We propose the Social Spatio-Temporal Graph Convolutional Neural Network (Social-STGCNN), which substitutes the need of aggregation methods by modeling the interactions as a graph. Our results show an improvement over the state of art by 20% on the Final Displacement Error (FDE) and an improvement on the Average Displacement Error (ADE) with 8.5 times less parameters and up to 48 times faster inference speed than previously reported methods. In addition, our model is data efficient, and exceeds previous state of the art on the ADE metric with only 20% of the training data. We propose a kernel function to embed the social interactions between pedestrians within the adjacency matrix. Through qualitative analysis, we show that our model inherited social behaviors that can be expected between pedestrians trajectories. Code is available at https://github.com/abduallahmohamed/Social-STGCNN.

For agents

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

get_harvested_code_for_paper("2002.11927")
get_code_for_paper("2002.11927")
have("2002.11927")

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

curl https://syntology.ai/api/ran/2002.11927.json

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

[![Syntology run record](https://syntology.ai/api/ran/2002.11927.svg)](https://syntology.ai/paper/2002.11927)

Connect an agent — have() is free.