SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1702.01105 · 2017

Joint 2D-3D-Semantic Data for Indoor Scene Understanding

arXiv · PDF · Open in the Atlas

Code that ran

13 of 14 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; 4 honoured the contract we drafted, 3 violated it and 4 have no contract verdict; 2 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/1702.01105.json · badge: /api/ran/1702.01105.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
alexsax/2D-3D-Semantics canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
jamycheung/trans4pass community (classifier label)
classifier basis not recorded on the link
9 ran · 1 no recorded run
jamycheung/360BEV community (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
FunctionStatusWhere it lives
cluster Ran
ran on a synthesized input
jamycheung/trans4pass/adaptations/model/memory.py
code served (permissive licence) · get_code("525fc4fc5ea60036")
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 ndarray, 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 numpy as np
from scipy.sparse import csr_matrix

# Create small sparse data for clustering
# Using a 2D sparse matrix with 5 samples and 4 features
data = np.array([1, 2, 3, 4, 5, 6])
row = np.array([0, 0, 1, 2, 3, 4])
col = np.array([0, 1, 2, 1, 3, 0])
sparse_data = csr_matrix((data, (row, col)), shape=(5, 4))

ARGS = {
    'sparse_data': sparse_data,
    'nclust': 2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, 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
colorize_mask Ran
ran, honoured the contract we drafted
jamycheung/trans4pass/adaptations/evaluate.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from lym29/DASeg, is pointer only (licence: NONE) · get_code("21ac171a17099011")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from lym29/DASeg, and GitHub detected no licence in that repository 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.

colorize_mask Ran
ran, honoured the contract we drafted
jamycheung/trans4pass/adaptations/evaluate_out13.py
code served (permissive licence) · get_code("e27caf70d841dc1a")
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 Image. 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
from PIL import Image

palette = [128, 64, 128, 244, 35, 232, 70, 70, 70, 102, 102, 156, 190, 153, 153, 153, 153, 153, 250, 170, 30, 220, 220, 0, 107, 142, 35, 152, 251, 152, 70, 130, 180, 220, 20, 60, 0, 0, 142]

def colorize_mask(mask):
    new_mask = Image.fromarray(mask.astype(np.uint8)).convert('P')
    new_mask.putpalette(palette)
    return new_mask

# Create a small test mask with uint8 values (0-255 range)
# Using a 4x3 array to have distinct dimensions
test_mask = np.array([
    [0, 1, 2],
    [10, 20, 30],
    [100, 150, 200],
    [255, 128, 64]
], dtype=np.uint8)

ARGS = {
    "mask": test_mask
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 2 and dtype family int 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
fast_hist Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jamycheung/trans4pass/adaptations/compute_iou.py
code served (permissive licence) · get_code("d86fb168246b16a4")
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) and returned ndarray, ndim 2, dtype family int, shape (4, 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 numpy as np

# Analyze the function:
# - a: array-like, used with >= 0, < n comparisons, and .astype(int)
# - b: array-like, same shape as a, used in indexing
# - n: int, used as upper bound and for bincount minlength

# Create small numpy arrays for a and b
a = np.array([0, 1, 2, 3, 1, 2], dtype=np.int32)
b = np.array([0, 1, 2, 0, 1, 2], dtype=np.int32)
n = 4

ARGS = {
    "a": a,
    "b": b,
    "n": n
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family int, shape (4, 4) — shape (4, 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_color Ran
ran, violated the contract we drafted
alexsax/2D-3D-Semantics/assets/utils.py
code served (permissive licence) · get_code("d01e418562a2f61b")
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) 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

ARGS = {
    "i": 16711680
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 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
get_index Ran
ran, violated the contract we drafted
alexsax/2D-3D-Semantics/assets/utils.py
code served (permissive licence) · get_code("7b7786158a580007")
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) and returned int, ndim 0, dtype family int, 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)

# The function get_index takes a color parameter which should be a 3-tuple
# in RGB order where each element is in [0, 255]
color = (128, 64, 32)

ARGS = {
    "color": color
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, 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_logger Ran
ran on a synthesized input
jamycheung/360BEV/model/utils.py
code served (permissive licence) · get_code("02d6e3bce0c2ff87")
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 Logger. 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 os
import tempfile
import logging

# Create a temporary directory for logging
logdir = tempfile.mkdtemp()

# Define arguments for get_logger
ARGS = {
    'logdir': logdir
}
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 Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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
load_labels Ran
ran; our contract draft was wrong, not the code
alexsax/2D-3D-Semantics/assets/utils.py
code served (permissive licence) · get_code("40ff9df70f20a948")
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) 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 json
import tempfile
import os

# Create a temporary JSON file with sample labels
temp_dir = tempfile.mkdtemp()
label_file = os.path.join(temp_dir, "labels.json")

sample_labels = {
    "image_1": {"class": "cat", "confidence": 0.95},
    "image_2": {"class": "dog", "confidence": 0.87},
    "image_3": {"class": "bird", "confidence": 0.72}
}

with open(label_file, 'w') as f:
    json.dump(sample_labels, f)

ARGS = {
    "label_file": label_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 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
load_my_state_dict Ran
ran on a synthesized input
jamycheung/trans4pass/adaptations/train_mpa.py
code served (permissive licence) · get_code("3a271e09c872b5dc")
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 SimpleModel. 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)

# Create a simple model with state_dict
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):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

# Instantiate the model
model = SimpleModel()

# Create a state_dict with some parameter values
state_dict = {}
for name, param in model.state_dict().items():
    state_dict[name] = param.clone() + 0.1

# Also add a key with 'module.' prefix to test that code path
state_dict['module.linear1.weight'] = model.state_dict()['linear1.weight'].clone() + 0.2

ARGS = {
    'model': model,
    'state_dict': state_dict
}
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 SimpleModel — a SimpleModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModel 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
lr_poly Ran
ran, honoured the contract we drafted
jamycheung/trans4pass/adaptations/train_mpa.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from lym29/DASeg, is pointer only (licence: NONE) · get_code("b3b7c1c716f4ca66")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from lym29/DASeg, and GitHub detected no licence in that repository 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.

make_divisible Ran
ran, honoured the contract we drafted
jamycheung/trans4pass/adaptations/model/trans4passplus.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from changlin31/DS-Net, is pointer only (licence: NONE) · get_code("5b2c72c30130d62a")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from changlin31/DS-Net, and GitHub detected no licence in that repository 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.

per_class_acc Ran
ran on a synthesized input
jamycheung/trans4pass/adaptations/compute_iou.py
code served (permissive licence) · get_code("7b4aac1e5c4c0b33")
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 float32, 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

# per_class_acc expects a confusion matrix (histogram)
# The function uses:
# - np.diag(hist) to get diagonal elements
# - hist.sum(1) to get row sums
# - division operations
# - np.nanmean() on the result

# Create a small confusion matrix: 4 classes x 4 classes
# This represents predictions vs ground truth
hist = np.array([
    [10, 2, 1, 0],      # class 0: 10 correct, 2 confused with class 1, etc.
    [1, 8, 1, 0],       # class 1: 8 correct
    [0, 1, 12, 2],      # class 2: 12 correct
    [0, 0, 1, 7]        # class 3: 7 correct
], dtype=np.float32)

ARGS = {
    "hist": hist
}
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 float32, 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
per_class_iu Ran
ran, violated the contract we drafted
jamycheung/trans4pass/adaptations/compute_iou.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from YanchaoYang/FDA, is pointer only (licence: NONE) · get_code("b1c59751f8968e99")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from YanchaoYang/FDA, and GitHub detected no licence in that repository 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.

init_memory Not yet run
unverified (harvested, no recorded run)
jamycheung/trans4pass/adaptations/model/memory.py
code served (permissive licence) · get_code("0cb59986142ffbcc")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 6 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 6 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
lr_poly 21 other papers
1 dated earlier, 20 later
1612.02646 (2016-12)
Learning Video Object Segmentation from Static Images
1703.01780 (2017-03)
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
1704.08509 (2017-04)
No More Discrimination: Cross City Adaptation of Road Scene Segmenters
and 18 more not named here
colorize_mask 15 other papers
15 later
1704.08509 (2017-04)
No More Discrimination: Cross City Adaptation of Road Scene Segmenters
1802.10349 (2018-02)
Learning to Adapt Structured Output Space for Semantic Segmentation
1809.09478 (2018-09)
Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation
and 12 more not named here
fast_hist 12 other papers
1 dated earlier, 11 later
1511.00561 (2015-11)
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
1806.07373 (2018-06)
Few-Shot Segmentation Propagation with Guided Networks
1808.00661 (2018-08)
Adaptive Temporal Encoding Network for Video Instance-level Human Parsing
and 9 more not named here
per_class_iu 6 other papers
6 later
1809.09478 (2018-09)
Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation
2003.14032 (2020-03)
PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation
2004.05498 (2020-04)
FDA: Fourier Domain Adaptation for Semantic Segmentation
and 3 more not named here
make_divisible 5 other papers
5 later
2103.13258 (2021-03)
Dynamic Slimmable Network
2107.00644 (2021-07)
Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation
Guo_Improving_Robustness_of_Vision_Transformers_by_Reducing_Sensitivity_To_Patch_CVPR_2023_paper (2023 (year only))
Improving Robustness of Vision Transformers by Reducing Sensitivity to Patch Corruptions
and 2 more not named here
get_color 1 other paper
1 later
2203.09440 (2022-03)
TO-Scene: A Large-scale Dataset for Understanding 3D Tabletop Scenes

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

We present a dataset of large-scale indoor spaces that provides a variety of mutually registered modalities from 2D, 2.5D and 3D domains, with instance-level semantic and geometric annotations. The dataset covers over 6,000m2 and contains over 70,000 RGB images, along with the corresponding depths, surface normals, semantic annotations, global XYZ images (all in forms of both regular and 360° equirectangular images) as well as camera information. It also includes registered raw and semantically annotated 3D meshes and point clouds. The dataset enables development of joint and cross-modal learning models and potentially unsupervised approaches utilizing the regularities present in large-scale indoor spaces. The dataset is available here: http://3Dsemantics.stanford.edu/

For agents

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

get_harvested_code_for_paper("1702.01105")
get_code_for_paper("1702.01105")
have("1702.01105")

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

curl https://syntology.ai/api/ran/1702.01105.json

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

[![Syntology run record](https://syntology.ai/api/ran/1702.01105.svg)](https://syntology.ai/paper/1702.01105)

Connect an agent — have() is free.