SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.07474 · ICLR · 2023

SQA3D: Situated Question Answering in 3D Scenes

Song-Chun Zhu, Qing Li, Siyuan Huang, Xiaojian Ma, Yitao Liang, Silong Yong, Zilong Zheng

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (6 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 7 have no contract verdict; 0 failures of our instrument; 1 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/2210.07474.json · badge: /api/ran/2210.07474.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
SilongYong/SQA3D canonical (classifier label)
classifier basis: classifier_2025
7 ran · 1 no recorded run
FunctionStatusWhere it lives
FC Ran
ran on a synthesized input · constructed an object; no result was computed
SilongYong/SQA3D/ScanQA/models/mcan_sqa_module.py
code served (permissive licence) · get_code("d04a2cdda13f2c28")
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 an instance of its own class, FC: the run constructed the object and did not call it, so no result was computed. 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)

ARGS = {
    'in_size': 4,
    'out_size': 3,
    'pdrop': 0.1,
    'use_gelu': 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 FC — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a FC 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
FFN Ran
ran on a synthesized input · constructed an object; no result was computed
SilongYong/SQA3D/ScanQA/models/mcan_sqa_module.py
code served (permissive licence) · get_code("5bdf1b882f558a79")
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 an instance of its own class, FFN: the run constructed the object and did not call it, so no result was computed. 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)

ARGS = {
    "hidden_size": 8,
    "pdrop": 0.1,
}
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 FFN — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a FFN 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
LayerNorm Ran
ran on a synthesized input · constructed an object; no result was computed
SilongYong/SQA3D/ScanQA/models/mcan_sqa_module.py
code served (permissive licence) · get_code("82506e21f7dfa931")
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 an instance of its own class, LayerNorm: the run constructed the object and did not call it, so no result was computed. 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)

# The LayerNorm.__init__ takes:
# - size: int (dimension of the parameter tensors)
# - eps: float (default 1e-06)

# The forward method takes:
# - x: tensor of shape (..., size) where last dimension matches size

# Build minimal valid arguments
size = 4
eps = 1e-06

# Create a sample input tensor for testing
# Shape: (batch=2, features=4) to match the size parameter
x = torch.randn(2, 4)

ARGS = {
    "size": size,
    "eps": eps,
}
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 LayerNorm — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a LayerNorm 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
MCAN_ED Ran
ran on a synthesized input · constructed an object; no result was computed
SilongYong/SQA3D/ScanQA/models/mcan_sqa_module.py
code served (permissive licence) · get_code("b2942b89f2d00162")
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 an instance of its own class, MCAN_ED: the run constructed the object and did not call it, so no result was computed. 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
import math

torch.manual_seed(0)

# Parameters for MCAN_ED
hidden_size = 8
num_heads = 2
num_layers = 2
pdrop = 0.1

ARGS = {
    "hidden_size": hidden_size,
    "num_heads": num_heads,
    "num_layers": num_layers,
    "pdrop": pdrop,
}
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 MCAN_ED — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a MCAN_ED 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
MHAtt Ran
ran on a synthesized input
SilongYong/SQA3D/ScanQA/models/mcan_sqa_module.py
code served (permissive licence) · get_code("6a3f3f634cf6de1f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 3, 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
import numpy as np
from scipy import linalg

# INIT_ARGS for MHAtt
INIT_ARGS = {
    'hidden_size': 4,
    'num_heads': 2,
    'pdrop': 0.1
}

# ARGS for forward method
batch_size = 2
seq_len = 3
hidden_size = INIT_ARGS['hidden_size']

v = torch.randn(batch_size, seq_len, hidden_size)
k = torch.randn(batch_size, seq_len, hidden_size)
q = torch.randn(batch_size, seq_len, hidden_size)
mask = torch.zeros(batch_size, 1, 1, seq_len).bool()  # (batch_size, 1, 1, seq_len)

ARGS = {
    'v': v,
    'k': k,
    'q': q,
    'mask': mask
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
numpy, scipy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
MLP Ran
ran on a synthesized input · constructed an object; no result was computed
SilongYong/SQA3D/ScanQA/models/mcan_sqa_module.py
code served (permissive licence) · get_code("a121cbb952a15dfc")
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 an instance of its own class, MLP: the run constructed the object and did not call it, so no result was computed. 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)

ARGS = {
    "in_size": 4,
    "mid_size": 8,
    "out_size": 3,
    "pdrop": 0.1,
    "use_gelu": 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 MLP — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a MLP 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
SA Ran
ran on a synthesized input · constructed an object; no result was computed
SilongYong/SQA3D/ScanQA/models/mcan_sqa_module.py
code served (permissive licence) · get_code("b17249e7a46ba6dc")
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 an instance of its own class, SA: the run constructed the object and did not call it, so no result was computed. 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
import math

torch.manual_seed(0)

# SA.__init__ expects:
# - hidden_size: int
# - num_heads: int (default 8)
# - pdrop: float (default 0.1)

# SA.forward expects:
# - x: tensor of shape (batch, seq_len, hidden_size)
# - x_mask: tensor or None for masking in attention

hidden_size = 4
num_heads = 2
pdrop = 0.1

# Create input tensors
batch_size = 2
seq_len = 3
x = torch.randn(batch_size, seq_len, hidden_size)
x_mask = torch.zeros(batch_size, num_heads, seq_len, seq_len, dtype=torch.bool)

ARGS = {
    'hidden_size': hidden_size,
    'num_heads': num_heads,
    'pdrop': pdrop,
}
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 SA — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a SA 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
SGA Not yet run
unverified (harvested, no recorded run)
SilongYong/SQA3D/ScanQA/models/mcan_sqa_module.py
code served (permissive licence) · get_code("02a7e6b69100fcd5")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 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, 1 later) and 7 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
LayerNorm
brick of this paper's assembly: model
3 other papers
2 dated earlier, 1 later · 2 only as an assembly brick
2105.14517 (2021-05)
GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning
2106.10446 (2021-06)
Attend What You Need: Motion-Appearance Synergistic Networks for Video Question Answering
2508.01984 (2025-08)
IMoRe: Implicit Program-Guided Reasoning for Human Motion Q&A

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

Sitting at the edge of the bed and facing the couch. Question q : Can I go straight to the coffee table in front of me? Scene context : 3D scan, egocentric video, birdeye view (BEV) picture, etc.

For agents

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

get_harvested_code_for_paper("2210.07474")
get_code_for_paper("2210.07474")
have("2210.07474")

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

curl https://syntology.ai/api/ran/2210.07474.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.07474.svg)](https://syntology.ai/paper/2210.07474)

Connect an agent — have() is free.