SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.01872 · 2021

Parts2Words: Learning Joint Embedding of Point Clouds and Texts by Bidirectional Matching between Parts and Words

arXiv · PDF · Open in the Atlas

Code that ran

4 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 4 have no contract verdict; 0 failures of our instrument; 6 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/2107.01872.json · badge: /api/ran/2107.01872.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
jlutangchuan/parts2words canonical (classifier label)
classifier basis: census
4 ran · 6 no recorded run
FunctionStatusWhere it lives
lambda_softmax_func Ran
ran on a synthesized input
jlutangchuan/parts2words/parts2words/models/model.py
code served (permissive licence) · get_code("756af0f529e8efd8")
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 3, dtype family float, shape (2, 4, 3) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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)

# The function expects:
# - inputs: tensor of shape (batch_size, max_word_len, k_parts)
# - lambda_val: scalar multiplier
# - k_parts: list/tensor of k values for each batch element

batch_size = 2
max_word_len = 4
k_parts_value = 3

# Create inputs tensor with shape (batch_size, max_word_len, k_parts_value)
inputs = torch.randn(batch_size, max_word_len, k_parts_value)

# lambda_val is a scalar multiplier
lambda_val = 0.5

# k_parts should be a list or tensor with k values for each batch element
# Based on the function's usage: k_expand = torch.Tensor(k_parts).view(-1, 1, 1)
# This suggests k_parts is something that can be converted to a tensor with shape (batch_size,)
k_parts = [2, 3]

ARGS = {
    "inputs": inputs,
    "lambda_val": lambda_val,
    "k_parts": k_parts,
}
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 3, dtype family float, shape (2, 4, 3) — shape (2, 4, 3) 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
multi_index_list Ran
ran on a synthesized input
jlutangchuan/parts2words/utils/common_tools.py
code served (permissive licence) · get_code("a3311d58663005ac")
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 list, ndim 1, 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

torch.manual_seed(0)

# The function multi_index_list takes a list and indices, 
# and returns elements from the list at those indices.
# It's a simple indexing operation: [li[i] for i in idx]

# Create a simple list with distinct elements
li = ['a', 'b', 'c', 'd', 'e']

# Create indices to select from the list
idx = [0, 2, 4, 1]

ARGS = {
    'li': li,
    'idx': idx
}
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 list, ndim 1, dtype family float — a list 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
rotate_point Ran
ran on a synthesized input
jlutangchuan/parts2words/parts2words/dataloaders/data.py
code served (permissive licence) · get_code("4bd367b04bee9a29")
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, 3) 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

# The function expects:
# - point: array-like that can be converted to np.array and reshaped to (-1, 3)
# - rotation_angle: scalar angle in radians

# Create a small point array with shape that can be reshaped to (-1, 3)
# Using a 2x3 array (2 points, 3D coordinates each)
point = np.array([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]])

# Rotation angle in radians (e.g., 45 degrees)
rotation_angle = np.pi / 4

ARGS = {
    "point": point,
    "rotation_angle": rotation_angle
}
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 ndarray, ndim 2, dtype family float, shape (2, 3) — shape (2, 3) 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
timer Ran
ran on a synthesized input
jlutangchuan/parts2words/utils/common_tools.py
code served (permissive licence) · get_code("b522db937a918b5a")
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 function. 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 functools
import time

def timer(func):
    @functools.wraps(func)
    def time_wrapper(*args, **kwargs):
        start_time = time.time()
        res = func(*args, **kwargs)
        end_time = time.time()
        print('%s took %f second' % (func.__name__, end_time - start_time))
        return res
    return time_wrapper

def sample_function(x, y):
    """A simple function to be decorated by timer"""
    return x + y

ARGS = {
    'func': sample_function
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
collate_fn Not yet run
unverified (harvested, no recorded run)
jlutangchuan/parts2words/parts2words/dataloaders/data.py
code served (permissive licence) · get_code("cb3d4f8e9e9bd628")
How it ran

no invocation recorded.

emd_inference_opencv Not yet run
unverified (harvested, no recorded run)
jlutangchuan/parts2words/parts2words/models/model_utils/emd_util.py
code served (permissive licence) · get_code("2e059b3e849cc9d3")
How it ran

no invocation recorded.

emd_inference_opencv_test Not yet run
unverified (harvested, no recorded run)
jlutangchuan/parts2words/parts2words/models/model_utils/emd_util.py
code served (permissive licence) · get_code("667b2d862e57062f")
How it ran

no invocation recorded.

get_parser Not yet run
unverified (harvested, no recorded run)
jlutangchuan/parts2words/utils/config.py
code served (permissive licence) · get_code("779b6aa2f5e28418")
How it ran

no invocation recorded.

get_precomp_loader Not yet run
unverified (harvested, no recorded run)
jlutangchuan/parts2words/parts2words/dataloaders/data.py
code served (permissive licence) · get_code("a7c37b3d1620a9b8")
How it ran

no invocation recorded.

lambda_softmax_func_i2t Not yet run
unverified (harvested, no recorded run)
jlutangchuan/parts2words/parts2words/models/model.py
code served (permissive licence) · get_code("85a4f29b6c4a2a26")
How it ran

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, 7 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 7 later) and 3 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
emd_inference_opencv 1 other paper
1 later
2502.19128 (2025-02)
SCA3D: Enhancing Cross-modal 3D Retrieval via 3D Shape and Caption Paired Data Augmentation
emd_inference_opencv_test 1 other paper
1 later
2502.19128 (2025-02)
SCA3D: Enhancing Cross-modal 3D Retrieval via 3D Shape and Caption Paired Data Augmentation
get_precomp_loader 1 other paper
1 later
2502.19128 (2025-02)
SCA3D: Enhancing Cross-modal 3D Retrieval via 3D Shape and Caption Paired Data Augmentation
lambda_softmax_func 1 other paper
1 later
2502.19128 (2025-02)
SCA3D: Enhancing Cross-modal 3D Retrieval via 3D Shape and Caption Paired Data Augmentation
multi_index_list 1 other paper
1 later
2502.19128 (2025-02)
SCA3D: Enhancing Cross-modal 3D Retrieval via 3D Shape and Caption Paired Data Augmentation
rotate_point 1 other paper
1 later
2502.19128 (2025-02)
SCA3D: Enhancing Cross-modal 3D Retrieval via 3D Shape and Caption Paired Data Augmentation
timer 1 other paper
1 later
2502.19128 (2025-02)
SCA3D: Enhancing Cross-modal 3D Retrieval via 3D Shape and Caption Paired Data Augmentation

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

Shape-Text matching is an important task of high-level shape understanding. Current methods mainly represent a 3D shape as multiple 2D rendered views, which obviously can not be understood well due to the structural ambiguity caused by self-occlusion in the limited number of views. To resolve this issue, we directly represent 3D shapes as point clouds, and propose to learn joint embedding of point clouds and texts by bidirectional matching between parts from shapes and words from texts. Specifically, we first segment the point clouds into parts, and then leverage optimal transport method to match parts and words in an optimized feature space, where each part is represented by aggregating features of all points within it and each word is abstracted by its contextual information. We optimize the feature space in order to enlarge the similarities between the paired training samples, while simultaneously maximizing the margin between the unpaired ones. Experiments demonstrate that our method achieves a significant improvement in accuracy over the SOTAs on multi-modal retrieval tasks under the Text2Shape dataset. Codes are available at https://github.com/JLUtangchuan/Parts2Words.

For agents

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

get_harvested_code_for_paper("2107.01872")
get_code_for_paper("2107.01872")
have("2107.01872")

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

curl https://syntology.ai/api/ran/2107.01872.json

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

[![Syntology run record](https://syntology.ai/api/ran/2107.01872.svg)](https://syntology.ai/paper/2107.01872)

Connect an agent — have() is free.