SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.00796 · 2023

Unsupervised Entity Alignment for Temporal Knowledge Graphs

arXiv · PDF · Open in the Atlas

Code that ran

10 of 12 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 10 have no contract verdict; 0 failures of our instrument; 2 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/2302.00796.json · badge: /api/ran/2302.00796.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
zju-daily/dualmatch canonical (classifier label)
classifier basis not recorded on the link
10 ran · 2 no recorded run
FunctionStatusWhere it lives
cal_sims Ran
ran on a synthesized input
zju-daily/dualmatch/seu_tkg.py
code served (permissive licence) · get_code("7f5dae800e82ca67")
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 EagerTensor, ndim 2, dtype family float, shape (2, 2) 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 tensorflow as tf
import numpy as np

# Set seeds for reproducibility
tf.random.set_seed(0)
np.random.seed(0)

# Create small test data
batch_size = 2
feature_dim = 4
num_features = 5

# Create feature matrix (num_features x feature_dim)
feature = tf.constant(np.random.randn(num_features, feature_dim), dtype=tf.float32)

# Create test_pair with indices into the feature matrix
test_pair = tf.constant([[0, 1], [2, 3]], dtype=tf.int32)

# right parameter - can be None or an integer for splitting the feature matrix
right = None

ARGS = {
    "test_pair": test_pair,
    "feature": feature,
    "right": right,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 2, dtype family float, shape (2, 2) — shape (2, 2) 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_feature_matrix Ran
ran on a synthesized input
zju-daily/dualmatch/utils2.py
code served (permissive licence) · get_code("30b6c3e4661be6f6")
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. 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 math
from collections import defaultdict
import tempfile
import os

torch.manual_seed(0)

# Create a temporary directory and files for testing
temp_dir = tempfile.mkdtemp()
filename_base = os.path.join(temp_dir, "test_")

# Create a mock triples file
triples_file = filename_base + "triples_0"
with open(triples_file, 'w') as f:
    f.write("1 0 2 100\n")
    f.write("2 1 3 101\n")
    f.write("3 0 1 102\n")

# Create a mock ent_ids file
ent_ids_file = filename_base + "ent_ids_0"
with open(ent_ids_file, 'w') as f:
    f.write("10\n")  # num_ent = 10

# Create a mock getLast function in a module
import sys
from types import ModuleType

wl_test = ModuleType('wl_test')

def getLast(filename):
    with open(filename, 'r') as f:
        return int(f.read().strip())

wl_test.getLast = getLast
sys.modules['wl_test'] = wl_test

# Create time_id mapping
time_id = {100: 0, 101: 1, 102: 2}

ARGS = {
    'filename': filename_base,
    'i': 0,
    'shift_id': 0,
    'tf_idf': False,
    'time_id': time_id
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow, torch, wl_test — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, shape (10, 6) — shape (10, 6) as a later run recorded it
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_link Ran
ran on a synthesized input
zju-daily/dualmatch/utils2.py
code served (permissive licence) · get_code("32267b06a34760c1")
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 2, 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 tempfile
import os

# Create temporary files with the expected format
temp_dir = tempfile.mkdtemp()
filename = os.path.join(temp_dir, 'test_')

# Create sup_pairs file
sup_pairs_content = """1 10
2 20
3 30"""

with open(filename + 'sup_pairs', 'w') as f:
    f.write(sup_pairs_content)

# Create ref_pairs file
ref_pairs_content = """4 40
5 50"""

with open(filename + 'ref_pairs', 'w') as f:
    f.write(ref_pairs_content)

ARGS = {
    'filename': filename,
    'shift_id': 0
}
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 list, ndim 2, dtype family int — 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
get_time Ran
ran on a synthesized input
zju-daily/dualmatch/utils2.py
code served (permissive licence) · get_code("44ea70c31791249e")
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 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 tempfile
import os

# Create temporary directory and files
temp_dir = tempfile.mkdtemp()
base_filename = os.path.join(temp_dir, "data")

# Create triples_1 file
with open(base_filename + "triples_1", 'w') as f:
    f.write("0 1 2 10 5\n")
    f.write("1 2 3 20 7\n")
    f.write("2 3 4 10 5\n")

# Create triples_2 file
with open(base_filename + "triples_2", 'w') as f:
    f.write("3 4 5 30 2\n")
    f.write("4 5 6 20 7\n")

ARGS = {
    "filename": base_filename
}
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 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
readobj Ran
ran on a synthesized input
zju-daily/dualmatch/dto.py
code served (permissive licence) · get_code("84598856fa1287c7")
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 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 pickle
import tempfile
import os

# Create a temporary file and write a pickled object to it
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test_object.pkl")

# Create a simple test object and pickle it
test_data = {"key": "value", "number": 42, "list": [1, 2, 3]}
with open(temp_file, 'wb') as f:
    pickle.dump(test_data, f)

# Define arguments for readobj function
ARGS = {
    "fname": temp_file
}
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 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
sinkhorn Ran
ran on a synthesized input
zju-daily/dualmatch/seu_tkg.py
code served (permissive licence) · get_code("ff5e3f83e9e31d8d")
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 EagerTensor, 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 tensorflow as tf
import numpy as np

# Create a small similarity matrix
# sims will be used with tf.exp, tf.reduce_sum, and division operations
# Shape: (2, 4) - batch size 2, 4 dimensions
sims = tf.constant([
    [0.1, 0.2, 0.3, 0.4],
    [0.5, 0.6, 0.7, 0.8]
], dtype=tf.float32)

ARGS = {
    "sims": sims,
    "eps": 1e-06
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, 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
to_json Ran
ran on a synthesized input
zju-daily/dualmatch/dto.py
code served (permissive licence) · get_code("c7588b10b2803a0f")
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 str. 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
from dataclasses import dataclass

@dataclass
class CustomObject:
    name: str
    value: int
    nested: dict

ARGS = {
    "obj": CustomObject(
        name="test_object",
        value=42,
        nested={"key": "value", "number": 123}
    )
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
view2 Ran
ran on a synthesized input
zju-daily/dualmatch/utils.py
code served (permissive licence) · get_code("c2134ade863a5542")
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 (6, 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

torch.manual_seed(0)

# view2 takes a tensor x and either returns it as-is if it's 2D,
# or reshapes it to 2D by flattening all but the last dimension.
# We'll test both cases.

# Case 1: 2D tensor (should be returned as-is)
x_2d = torch.randn(2, 4)

# Case 2: 3D tensor (should be reshaped to 2D)
x_3d = torch.randn(2, 3, 4)

# We'll use the 3D case as it exercises the view operation
ARGS = {
    "x": x_3d
}
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 (6, 4) — shape (6, 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
view3 Ran
ran on a synthesized input
zju-daily/dualmatch/utils.py
code served (permissive licence) · get_code("dfa7dc642bf2a74a")
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 (1, 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

torch.manual_seed(0)

# The function expects a Tensor and performs operations:
# - Checks if x.dim() == 3
# - If not, calls x.view(1, x.size(0), -1)
# We need to test both cases

# Test case: 2D tensor that will be reshaped to 3D
x = torch.randn(2, 4)

ARGS = {
    "x": x
}
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 (1, 2, 4) — shape (1, 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
view_back Ran
ran on a synthesized input
zju-daily/dualmatch/utils.py
code served (permissive licence) · get_code("86b4c5eb684f9131")
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 (1, 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
from torch import Tensor

torch.manual_seed(0)

# Create test tensors with distinct sizes
# 2D tensor: (batch=2, features=4)
tensor_2d = torch.randn(2, 4)

# 3D tensor: (batch=2, seq=3, features=4)
tensor_3d = torch.randn(2, 3, 4)

ARGS = {
    "M": tensor_2d
}
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 (1, 2, 4) — shape (1, 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
construct_sparse_rel_matrix Not yet run
unverified (harvested, no recorded run)
zju-daily/dualmatch/seu_tkg.py
code served (permissive licence) · get_code("42f155574fc2f921")
How it ran

no invocation recorded.

get_score Not yet run
unverified (harvested, no recorded run)
zju-daily/dualmatch/processing.py
code served (permissive licence) · get_code("68824ba6e717496e")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 0 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
readobj 1 other paper
1 dated earlier
2205.10312 (2022-05)
ClusterEA: Scalable Entity Alignment with Stochastic Training and Normalized Mini-batch Similarities
to_json 1 other paper
1 dated earlier
2205.10312 (2022-05)
ClusterEA: Scalable Entity Alignment with Stochastic Training and Normalized Mini-batch Similarities
view2 1 other paper
1 dated earlier
2205.10312 (2022-05)
ClusterEA: Scalable Entity Alignment with Stochastic Training and Normalized Mini-batch Similarities
view3 1 other paper
1 dated earlier
2205.10312 (2022-05)
ClusterEA: Scalable Entity Alignment with Stochastic Training and Normalized Mini-batch Similarities
view_back 1 other paper
1 dated earlier
2205.10312 (2022-05)
ClusterEA: Scalable Entity Alignment with Stochastic Training and Normalized Mini-batch Similarities

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

Entity alignment (EA) is a fundamental data integration task that identifies equivalent entities between different knowledge graphs (KGs). Temporal Knowledge graphs (TKGs) extend traditional knowledge graphs by introducing timestamps, which have received increasing attention. State-of-the-art time-aware EA studies have suggested that the temporal information of TKGs facilitates the performance of EA. However, existing studies have not thoroughly exploited the advantages of temporal information in TKGs. Also, they perform EA by pre-aligning entity pairs, which can be labor-intensive and thus inefficient. In this paper, we present DualMatch which effectively fuses the relational and temporal information for EA. DualMatch transfers EA on TKGs into a weighted graph matching problem. More specifically, DualMatch is equipped with an unsupervised method, which achieves EA without necessitating seed alignment. DualMatch has two steps: (i) encoding temporal and relational information into embeddings separately using a novel label-free encoder, Dual-Encoder; and (ii) fusing both information and transforming it into alignment using a novel graph-matching-based decoder, GM-Decoder. DualMatch is able to perform EA on TKGs with or without supervision, due to its capability of effectively capturing temporal information. Extensive experiments on three real-world TKG datasets offer the insight that DualMatch outperforms the state-of-the-art methods in terms of H@1 by 2.4% - 10.7% and MRR by 1.7% - 7.6%, respectively.

For agents

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

get_harvested_code_for_paper("2302.00796")
get_code_for_paper("2302.00796")
have("2302.00796")

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

curl https://syntology.ai/api/ran/2302.00796.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.00796.svg)](https://syntology.ai/paper/2302.00796)

Connect an agent — have() is free.