SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2308.16632 · 2023

3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation

arXiv · PDF · Open in the Atlas

Code that ran

7 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, 2 violated it and 0 have no contract verdict; 5 failures of our instrument; 3 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/2308.16632.json · badge: /api/ran/2308.16632.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
sosppxo/3d-stmn canonical (classifier label)
classifier basis: census
7 ran · 3 no recorded run
FunctionStatusWhere it lives
batch_dice_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
sosppxo/3d-stmn/stmn/model/loss.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from sosppxo/RG-SAN, is pointer only (licence: NONE) · get_code("89f8d423e0baf041")
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 sosppxo/RG-SAN, 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.

createResolutionCallbackFromEnv Ran
ran; our contract draft was wrong, not the code
sosppxo/3d-stmn/stmn/torch/_jit_internal.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from sosppxo/MDIN, is pointer only (licence: NONE) · get_code("381979e9afe9d569")
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 sosppxo/MDIN, 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.

createResolutionCallbackFromFrame Ran
ran; our contract draft was wrong, not the code
sosppxo/3d-stmn/stmn/torch/_jit_internal.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from sosppxo/MDIN, is pointer only (licence: NONE) · get_code("b126ffa42a0734fe")
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 sosppxo/MDIN, 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.

get_closure Ran
ran; our contract draft was wrong, not the code
sosppxo/3d-stmn/stmn/torch/_jit_internal.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from sosppxo/MDIN, is pointer only (licence: NONE) · get_code("c351f1920c45765d")
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 sosppxo/MDIN, 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.

is_integral Ran
ran, violated the contract we drafted
sosppxo/3d-stmn/stmn/torch/testing/_core.py
code served (permissive licence) · get_code("3da3f1e07779dcb8")
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

torch.manual_seed(0)

# The function is_integral takes a single parameter: dtype (a torch.dtype)
# It checks if the dtype is in a tuple of integral types
# We need to provide a valid torch.dtype value

ARGS = {
    "dtype": torch.int64
}
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 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
is_quantized Ran
ran, violated the contract we drafted
sosppxo/3d-stmn/stmn/torch/testing/_core.py
code served (permissive licence) · get_code("f6e2f8ff46abe726")
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

torch.manual_seed(0)

# The function is_quantized takes a torch.dtype and checks if it's in a tuple of quantized dtypes
# We'll test with one of the quantized dtypes

ARGS = {
    "dtype": torch.quint8
}
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 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
make_non_contiguous Ran
ran; our contract draft was wrong, not the code
sosppxo/3d-stmn/stmn/torch/testing/_core.py
code served (permissive licence) · get_code("42478ed654ad3707")
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 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 torch
import random

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

# Create a simple tensor to pass as argument
# Keep it tiny: batch size 2, some features
tensor = torch.randn(2, 4)

ARGS = {
    "tensor": 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 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
batch_sigmoid_bce_loss Not yet run
unverified (harvested, no recorded run)
sosppxo/3d-stmn/stmn/model/loss.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from sosppxo/RG-SAN, is pointer only (licence: NONE) · get_code("2815d6704af5fb9c")
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 sosppxo/RG-SAN, 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. No invocation recorded.

batch_sigmoid_focal_loss Not yet run
unverified (harvested, no recorded run)
sosppxo/3d-stmn/stmn/model/loss.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from sosppxo/RG-SAN, is pointer only (licence: NONE) · get_code("5ce41ce149ac0278")
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 sosppxo/RG-SAN, 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. No invocation recorded.

handle_torch_function Not yet run
unverified (harvested, no recorded run)
sosppxo/3d-stmn/stmn/torch/overrides.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from sosppxo/MDIN, is pointer only (licence: NONE) · get_code("a6f16e0be190712d")
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 sosppxo/MDIN, 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. No invocation 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, 10 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 10 later) and 0 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
batch_dice_loss 5 other papers
4 later, 1 same year, order not determinable
aaai_25335 (2023 (year only))
Superpoint Transformer for 3D Scene Instance Segmentation
2309.01692 (2023-09)
Mask-Attention-Free Transformer for 3D Instance Segmentation
aaai_28408 (2024 (year only))
3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation
and 2 more not named here
batch_sigmoid_bce_loss 5 other papers
4 later, 1 same year, order not determinable
aaai_25335 (2023 (year only))
Superpoint Transformer for 3D Scene Instance Segmentation
2309.01692 (2023-09)
Mask-Attention-Free Transformer for 3D Instance Segmentation
aaai_28408 (2024 (year only))
3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation
and 2 more not named here
batch_sigmoid_focal_loss 5 other papers
4 later, 1 same year, order not determinable
aaai_25335 (2023 (year only))
Superpoint Transformer for 3D Scene Instance Segmentation
2309.01692 (2023-09)
Mask-Attention-Free Transformer for 3D Instance Segmentation
aaai_28408 (2024 (year only))
3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation
and 2 more not named here
createResolutionCallbackFromEnv 2 other papers
2 later
aaai_28408 (2024 (year only))
3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation
2407.20664 (2024-07)
3D-GRES: Generalized 3D Referring Expression Segmentation
createResolutionCallbackFromFrame 2 other papers
2 later
aaai_28408 (2024 (year only))
3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation
2407.20664 (2024-07)
3D-GRES: Generalized 3D Referring Expression Segmentation
get_closure 2 other papers
2 later
aaai_28408 (2024 (year only))
3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation
2407.20664 (2024-07)
3D-GRES: Generalized 3D Referring Expression Segmentation
handle_torch_function 2 other papers
2 later
aaai_28408 (2024 (year only))
3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation
2407.20664 (2024-07)
3D-GRES: Generalized 3D Referring Expression Segmentation
is_integral 1 other paper
1 later
aaai_28408 (2024 (year only))
3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation
is_quantized 1 other paper
1 later
aaai_28408 (2024 (year only))
3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation
make_non_contiguous 1 other paper
1 later
aaai_28408 (2024 (year only))
3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation

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

In 3D Referring Expression Segmentation (3D-RES), the earlier approach adopts a two-stage paradigm, extracting segmentation proposals and then matching them with referring expressions. However, this conventional paradigm encounters significant challenges, most notably in terms of the generation of lackluster initial proposals and a pronounced deceleration in inference speed. Recognizing these limitations, we introduce an innovative end-to-end Superpoint-Text Matching Network (3D-STMN) that is enriched by dependency-driven insights. One of the keystones of our model is the Superpoint-Text Matching (STM) mechanism. Unlike traditional methods that navigate through instance proposals, STM directly correlates linguistic indications with their respective superpoints, clusters of semantically related points. This architectural decision empowers our model to efficiently harness cross-modal semantic relationships, primarily leveraging densely annotated superpoint-text pairs, as opposed to the more sparse instance-text pairs. In pursuit of enhancing the role of text in guiding the segmentation process, we further incorporate the Dependency-Driven Interaction (DDI) module to deepen the network's semantic comprehension of referring expressions. Using the dependency trees as a beacon, this module discerns the intricate relationships between primary terms and their associated descriptors in expressions, thereby elevating both the localization and segmentation capacities of our model. Comprehensive experiments on the ScanRefer benchmark reveal that our model not only set new performance standards, registering an mIoU gain of 11.7 points but also achieve a staggering enhancement in inference speed, surpassing traditional methods by 95.7 times. The code and models are available at https://github.com/sosppxo/3D-STMN.

For agents

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

get_harvested_code_for_paper("2308.16632")
get_code_for_paper("2308.16632")
have("2308.16632")

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

curl https://syntology.ai/api/ran/2308.16632.json

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

[![Syntology run record](https://syntology.ai/api/ran/2308.16632.svg)](https://syntology.ai/paper/2308.16632)

Connect an agent — have() is free.