SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1803.10892 · 2018

Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks

arXiv · PDF · Open in the Atlas

Code that ran

10 of 10 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 5 have no contract verdict; 5 failures 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/1803.10892.json · badge: /api/ran/1803.10892.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
agrimgupta92/sgan canonical (classifier label)
classifier basis: census
6 ran · 0 no recorded run
rohanchandra30/TrackNPred reimplementation (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
mirkozaff/aa-sgan extension (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
bce_loss Ran
ran; our contract draft was wrong, not the code
agrimgupta92/sgan/sgan/losses.py
code served (permissive licence) · get_code("e953c2a70a67444a")
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
import torch.nn as nn

torch.manual_seed(0)

# Create input tensor of shape (N,) with scores
input_tensor = torch.randn(2, requires_grad=True)

# Create target tensor of shape (N,) with binary values (0 and 1)
target_tensor = torch.tensor([0.0, 1.0])

ARGS = {
    "input": input_tensor,
    "target": target_tensor,
}
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
bool_flag Ran
ran on a synthesized input
agrimgupta92/sgan/sgan/utils.py
code served (permissive licence) · get_code("533a2b4e2af6948c")
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
import numpy as np

def bool_flag(s):
    if s == '1':
        return True
    elif s == '0':
        return False
    msg = 'Invalid value "%s" for bool flag (should be 0 or 1)'
    raise ValueError(msg % s)

ARGS = {
    's': '1'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, 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
evaluate_helper Ran
ran; our contract draft was wrong, not the code
mirkozaff/aa-sgan/src/evaluate_model.py
pointer only (licence: NONE) · get_code("55df9dc702dcf13c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mirkozaff/aa-sgan when it was checked. 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.

gan_d_loss Ran
ran on a synthesized input
agrimgupta92/sgan/sgan/losses.py
code served (permissive licence) · get_code("a896ec1008736cfb")
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
import random

torch.manual_seed(0)

# Create tiny tensors for scores
batch_size = 2
scores_real = torch.randn(batch_size)
scores_fake = torch.randn(batch_size)

ARGS = {
    "scores_real": scores_real,
    "scores_fake": scores_fake,
}
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
gan_g_loss Ran
ran on a synthesized input
agrimgupta92/sgan/sgan/losses.py
code served (permissive licence) · get_code("9895ef20982713d2")
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
import random

torch.manual_seed(0)
random.seed(0)

# Create a small batch of fake scores
# The function expects a tensor of shape (N,) containing scores
batch_size = 2
scores_fake = torch.randn(batch_size)

ARGS = {
    "scores_fake": scores_fake
}
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
get_dtypes Ran
ran; our contract draft was wrong, not the code
rohanchandra30/TrackNPred/model/Prediction/sganTrain.py
pointer only (licence: NONE) · get_code("396bc31e5aa3e580")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rohanchandra30/TrackNPred when it was checked. 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.

get_noise Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
rohanchandra30/TrackNPred/model/Prediction/sgan/models.py
pointer only (licence: NONE) · get_code("cc7ee43eadf25dac")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rohanchandra30/TrackNPred when it was checked. 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.

get_total_norm Ran
ran on a synthesized input
agrimgupta92/sgan/sgan/utils.py
code served (permissive licence) · get_code("86ef0f4c4c0c2702")
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
import torch.nn as nn

torch.manual_seed(0)

# Create a simple model with parameters that have gradients
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        return self.linear2(self.linear1(x))

model = SimpleModel()

# Create some dummy input and output to compute gradients
x = torch.randn(2, 4)
y = torch.randn(2, 2)

# Forward pass and compute loss
output = model(x)
loss = nn.MSELoss()(output, y)

# Backward pass to populate gradients
loss.backward()

# Get model parameters (they now have .grad attributes)
parameters = list(model.parameters())

ARGS = {
    "parameters": parameters,
    "norm_type": 2
}
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
int_tuple Ran
ran on a synthesized input
agrimgupta92/sgan/sgan/utils.py
code served (permissive licence) · get_code("c7a0b110ef7c5e03")
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 int; 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
import numpy as np

def int_tuple(s):
    return tuple((int(i) for i in s.split(',')))

ARGS = {
    's': '1,2,3,4,5'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — 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 int — 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
make_mlp Ran
ran; our contract draft was wrong, not the code
rohanchandra30/TrackNPred/model/Prediction/sgan/models.py
pointer only (licence: NONE) · get_code("367e08507e69216f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rohanchandra30/TrackNPred when it was checked. 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.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 5 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 4 later) and 5 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
bce_loss 3 other papers
3 later
1804.01622 (2018-04)
Image Generation from Scene Graphs
1909.05379 (2019-09)
Specifying Object Attributes and Relations in Interactive Scene Generation
1912.07414 (2019-12)
Learning Canonical Representations for Scene Graph to Image Generation
int_tuple 3 other papers
3 later
1804.01622 (2018-04)
Image Generation from Scene Graphs
1909.05379 (2019-09)
Specifying Object Attributes and Relations in Interactive Scene Generation
2111.14820 (2021-11)
Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective
get_noise 2 other papers
2 later
2111.14820 (2021-11)
Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective
2207.10398 (2022-07)
D2-TPred: Discontinuous Dependency for Trajectory Prediction under Traffic Lights
evaluate_helper 1 other paper
1 dated earlier
1710.04689 (2017-10)
Social Attention: Modeling Attention in Human Crowds
get_total_norm 1 other paper
1 later
1804.01622 (2018-04)
Image Generation from Scene Graphs

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

Understanding human motion behavior is critical for autonomous moving platforms (like self-driving cars and social robots) if they are to navigate human-centric environments. This is challenging because human motion is inherently multimodal: given a history of human motion paths, there are many socially plausible ways that people could move in the future. We tackle this problem by combining tools from sequence prediction and generative adversarial networks: a recurrent sequence-to-sequence model observes motion histories and predicts future behavior, using a novel pooling mechanism to aggregate information across people. We predict socially plausible futures by training adversarially against a recurrent discriminator, and encourage diverse predictions with a novel variety loss. Through experiments on several datasets we demonstrate that our approach outperforms prior work in terms of accuracy, variety, collision avoidance, and computational complexity.

For agents

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

get_harvested_code_for_paper("1803.10892")
get_code_for_paper("1803.10892")
have("1803.10892")

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

curl https://syntology.ai/api/ran/1803.10892.json

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

[![Syntology run record](https://syntology.ai/api/ran/1803.10892.svg)](https://syntology.ai/paper/1803.10892)

Connect an agent — have() is free.