SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2211.11979 · 2022

Learnable Spectral Wavelets on Dynamic Graphs to Capture Global Interactions

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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 3 have no contract verdict; 2 failures of our instrument; 0 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/2211.11979.json · badge: /api/ran/2211.11979.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
ansonb/deft community (classifier label)
classifier basis not recorded on the link
5 ran · 0 no recorded run
FunctionStatusWhere it lives
feature_reader Ran
ran on a synthesized input
ansonb/deft/models.py
code served (permissive licence) · get_code("2eb9d39c82188679")
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 coo_matrix. 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 feature data
# The function expects a JSON file where keys are node IDs (as strings)
# and values are lists of feature indices
temp_dir = tempfile.mkdtemp()
feature_data = {
    "0": [0, 2, 4],
    "1": [1, 3, 5],
    "2": [0, 1, 4],
    "3": [2, 3]
}
temp_file = os.path.join(temp_dir, "features.json")
with open(temp_file, 'w') as f:
    json.dump(feature_data, f)

ARGS = {
    "path": temp_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type coo_matrix — a coo_matrix output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a coo_matrix 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
graph_reader Ran
ran on a synthesized input
ansonb/deft/models.py
code served (permissive licence) · get_code("672c2bffc50d20fd")
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 Graph. 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 pandas as pd
import networkx as nx
import os

# Create a temporary CSV file with edge list data
temp_dir = tempfile.mkdtemp()
csv_path = os.path.join(temp_dir, "edges.csv")

# Create a simple edge list CSV file
edge_data = pd.DataFrame({
    'source': [0, 1, 2, 3, 4],
    'target': [1, 2, 3, 4, 0]
})
edge_data.to_csv(csv_path, index=False)

ARGS = {
    'path': csv_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
networkx, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Graph — a Graph output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Graph output the recorded ndim 1 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
scaled_exp Ran
ran; our contract draft was wrong, not the code
ansonb/deft/model_deft.py
code served (permissive licence) · get_code("654acacaf00954fb")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) 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 torch

torch.manual_seed(0)

# The function returns a callable that expects edges with a .data attribute
# edges.data[field] should be a tensor that can be divided by scale_constant
# We need to create a mock edges object

class MockEdges:
    def __init__(self, field_name, tensor_data):
        self.data = {field_name: tensor_data}

# Create a small tensor for the field
field_name = "attention_scores"
tensor_data = torch.randn(2, 4)

# The function will be called with edges, so we need to set up the arguments
# that scaled_exp expects
scale_constant = 2.0

ARGS = {
    "field": field_name,
    "scale_constant": scale_constant
}
Setup block drafted by
a language model, Claude Sonnet 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 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
src_dot_dst Ran
ran; our contract draft was wrong, not the code
ansonb/deft/model_deft.py
code served (permissive licence) · get_code("23fba400cff6fafa")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) 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 torch

torch.manual_seed(0)

# The function src_dot_dst returns a function that operates on edges
# It expects edges to have .src and .dst attributes with dictionaries
# containing src_field and dst_field keys respectively
# The returned function computes dot product and stores in out_field

# We need to provide field names as strings
src_field = "h"
dst_field = "h" 
out_field = "score"

ARGS = {
    "src_field": src_field,
    "dst_field": dst_field,
    "out_field": out_field
}
Setup block drafted by
a language model, Claude Sonnet 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 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
target_reader Ran
ran on a synthesized input
ansonb/deft/models.py
code served (permissive licence) · get_code("275c19411fe5d6c0")
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 1, dtype family float, shape (5,) 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
import pandas as pd
import tempfile
import os

# Create a temporary CSV file with target data
temp_dir = tempfile.mkdtemp()
csv_path = os.path.join(temp_dir, 'targets.csv')

# Write a simple CSV with a 'target' column
target_data = pd.DataFrame({'target': [1.5, 2.3, 3.1, 4.2, 5.0]})
target_data.to_csv(csv_path, index=False)

ARGS = {
    'path': csv_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (5,) — shape (5,) 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

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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, 2 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
scaled_exp 4 other papers
2 dated earlier, 2 later
1902.10191 (2019-02)
EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs
2012.09699 (2020-12)
A Generalization of Transformer Networks to Graphs
2302.07253 (2023-02)
Energy Transformer
and 1 more not named here
src_dot_dst 4 other papers
2 dated earlier, 2 later
1902.10191 (2019-02)
EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs
2012.09699 (2020-12)
A Generalization of Transformer Networks to Graphs
2302.07253 (2023-02)
Energy Transformer
and 1 more not named here
feature_reader 1 other paper
1 dated earlier
1902.10191 (2019-02)
EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs
graph_reader 1 other paper
1 dated earlier
1902.10191 (2019-02)
EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs
target_reader 1 other paper
1 dated earlier
1902.10191 (2019-02)
EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs

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

Learning on evolving(dynamic) graphs has caught the attention of researchers as static methods exhibit limited performance in this setting. The existing methods for dynamic graphs learn spatial features by local neighborhood aggregation, which essentially only captures the low pass signals and local interactions. In this work, we go beyond current approaches to incorporate global features for effectively learning representations of a dynamically evolving graph. We propose to do so by capturing the spectrum of the dynamic graph. Since static methods to learn the graph spectrum would not consider the history of the evolution of the spectrum as the graph evolves with time, we propose a novel approach to learn the graph wavelets to capture this evolving spectra. Further, we propose a framework that integrates the dynamically captured spectra in the form of these learnable wavelets into spatial features for incorporating local and global interactions. Experiments on eight standard datasets show that our method significantly outperforms related methods on various tasks for dynamic graphs.

For agents

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

get_harvested_code_for_paper("2211.11979")
get_code_for_paper("2211.11979")
have("2211.11979")

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

curl https://syntology.ai/api/ran/2211.11979.json

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

[![Syntology run record](https://syntology.ai/api/ran/2211.11979.svg)](https://syntology.ai/paper/2211.11979)

Connect an agent — have() is free.