SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1911.03082 · 2019

Composition-based Multi-Relational Graph Convolutional Networks

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 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 1 has no contract verdict; 4 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/1911.03082.json · badge: /api/ran/1911.03082.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
malllabiisc/CompGCN canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
anilakash/indkgc extension (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
FunctionStatusWhere it lives
get_combined_results Ran
ran; our contract draft was wrong, not the code
malllabiisc/CompGCN/helper.py
code served (permissive licence) · get_code("1693e0374b56cfbc")
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 torch
import numpy as np

torch.manual_seed(0)

# Construct left_results dict with required keys
left_results = {
    'count': 100,
    'mr': 50.0,
    'mrr': 75.0,
    'hits@1': 80,
    'hits@2': 85,
    'hits@3': 88,
    'hits@4': 90,
    'hits@5': 92,
    'hits@6': 93,
    'hits@7': 94,
    'hits@8': 95,
    'hits@9': 96,
    'hits@10': 97,
}

# Construct right_results dict with required keys
right_results = {
    'count': 100,
    'mr': 60.0,
    'mrr': 70.0,
    'hits@1': 75,
    'hits@2': 80,
    'hits@3': 82,
    'hits@4': 85,
    'hits@5': 87,
    'hits@6': 88,
    'hits@7': 89,
    'hits@8': 90,
    'hits@9': 91,
    'hits@10': 92,
}

ARGS = {
    'left_results': left_results,
    'right_results': right_results,
}
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 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
get_logger Ran
ran; our contract draft was wrong, not the code
malllabiisc/CompGCN/helper.py
code served (permissive licence) · get_code("4ecef8549fab0398")
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 tempfile
import json
import os

# Create temporary directories for testing
temp_dir = tempfile.mkdtemp()
log_dir = temp_dir + '/logs/'
config_dir = temp_dir + '/config/'

# Create directories
os.makedirs(log_dir, exist_ok=True)
os.makedirs(config_dir, exist_ok=True)

# Create a minimal log_config.json that the function expects
log_config = {
    'version': 1,
    'disable_existing_loggers': False,
    'formatters': {
        'standard': {
            'format': '%(asctime)s - [%(levelname)s] - %(message)s'
        }
    },
    'handlers': {
        'file_handler': {
            'class': 'logging.FileHandler',
            'level': 'DEBUG',
            'formatter': 'standard',
            'filename': ''
        },
        'console': {
            'class': 'logging.StreamHandler',
            'level': 'DEBUG',
            'formatter': 'standard',
            'stream': 'ext://sys.stdout'
        }
    },
    'root': {
        'level': 'DEBUG',
        'handlers': ['file_handler', 'console']
    }
}

# Write the config file
with open(config_dir + 'log_config.json', 'w') as f:
    json.dump(log_config, f)

# Define arguments for the function
ARGS = {
    'name': 'test_logger',
    'log_dir': log_dir,
    'config_dir': config_dir
}
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 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
get_param Ran
ran on a synthesized input
malllabiisc/CompGCN/helper.py
code served (permissive licence) · get_code("892c466d12dfb05b")
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 Parameter, ndim 2, 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
from torch.nn.init import xavier_normal_
from torch.nn import Parameter

torch.manual_seed(0)

ARGS = {
    "shape": (4, 3)
}
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 Parameter, ndim 2, dtype family float — no output shape is stated: observe_signature.py recorded Tensor ndim 2, which disagrees with the fixture run
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
process_nbfnet_rank Ran
ran; our contract draft was wrong, not the code
anilakash/indkgc/script/eval_anyburl.py
pointer only (licence: NONE) · get_code("92482118031a5b26")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, anilakash/indkgc 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.

shuffle_batch Ran
ran; our contract draft was wrong, not the code
anilakash/indkgc/script/eval_anyburl.py
pointer only (licence: NONE) · get_code("cf1e4406130d8693")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, anilakash/indkgc 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.

process_nbfnet_score Not yet run
unverified (harvested, no recorded run)
anilakash/indkgc/script/eval_anyburl.py
pointer only (licence: NONE) · get_code("d5f75c3eba2a7d63")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, anilakash/indkgc 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 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 2 the same month, 2 later) and 4 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
get_logger 3 other papers
1 dated earlier, 1 the same month, 1 later
1901.08255 (2019-01)
Confidence-based Graph Convolutional Networks for Semi-Supervised Learning
1911.00219 (2019-11)
InteractE: Improving Convolution-based Knowledge Graph Embeddings by Increasing Feature Interactions
2022.findings-emnlp.341 (2022 (year only))
Joint Multilingual Knowledge Graph Completion and Alignment
get_combined_results 2 other papers
1 the same month, 1 later
1911.00219 (2019-11)
InteractE: Improving Convolution-based Knowledge Graph Embeddings by Increasing Feature Interactions
2022.findings-emnlp.341 (2022 (year only))
Joint Multilingual Knowledge Graph Completion and Alignment

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

Graph Convolutional Networks (GCNs) have recently been shown to be quite successful in modeling graph-structured data. However, the primary focus has been on handling simple undirected graphs. Multi-relational graphs are a more general and prevalent form of graphs where each edge has a label and direction associated with it. Most of the existing approaches to handle such graphs suffer from over-parameterization and are restricted to learning representations of nodes only. In this paper, we propose CompGCN, a novel Graph Convolutional framework which jointly embeds both nodes and relations in a relational graph. CompGCN leverages a variety of entity-relation composition operations from Knowledge Graph Embedding techniques and scales with the number of relations. It also generalizes several of the existing multi-relational GCN methods. We evaluate our proposed method on multiple tasks such as node classification, link prediction, and graph classification, and achieve demonstrably superior results. We make the source code of CompGCN available to foster reproducible research.

For agents

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

get_harvested_code_for_paper("1911.03082")
get_code_for_paper("1911.03082")
have("1911.03082")

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

curl https://syntology.ai/api/ran/1911.03082.json

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

[![Syntology run record](https://syntology.ai/api/ran/1911.03082.svg)](https://syntology.ai/paper/1911.03082)

Connect an agent — have() is free.