SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.02389 · 2024

KICGPT: Large Language Model with Knowledge in Context for Knowledge Graph Completion

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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; 1 honoured the contract we drafted, 0 violated it and 0 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/2402.02389.json · badge: /api/ran/2402.02389.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
weiyanbin1999/kicgpt canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
get_entity_neighbors Ran
ran, honoured the contract we drafted
weiyanbin1999/kicgpt/get_demonstrations.py
code served (permissive licence) · get_code("0223642e7418f57a")
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

# Set random seed for reproducibility
torch.manual_seed(0)

# Construct the graph and reverse_graph global variables
# graph[source] is a dict where keys are neighbors and values are edge weights/relations
graph = {
    'entity_0': {
        'entity_1': 'relation_A',
        'entity_2': 'relation_B',
    },
    'entity_1': {
        'entity_3': 'relation_C',
    },
    'entity_2': {
        'entity_0': 'relation_D',
    },
}

# reverse_graph stores edges where target_entity appears as tail
# reverse_graph[target] is a dict where keys are heads and values are edge weights/relations
reverse_graph = {
    'entity_1': {
        'entity_0': 'relation_A',
    },
    'entity_2': {
        'entity_0': 'relation_B',
    },
    'entity_3': {
        'entity_1': 'relation_C',
    },
    'entity_0': {
        'entity_2': 'relation_D',
    },
}

# Define arguments for get_entity_neighbors
ARGS = {
    'traget_entity': 'entity_0',
    'max_triplet': 4,
}
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
get_onestep_neighbors Ran
ran; our contract draft was wrong, not the code
weiyanbin1999/kicgpt/get_demonstrations.py
code served (permissive licence) · get_code("f20e6de64e707e7f")
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 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.

# Analyze the function to understand what it needs
# - graph: a dict where keys are nodes and values are dicts (adjacency lists with weights)
# - source: a node identifier (string or int)
# - num_samples: an integer (not used in function body, but parameter exists)
# - reverse: an integer (0 or 1) that controls tuple ordering

# Build a simple graph structure
graph = {
    'node_a': {
        'node_b': 0.5,
        'node_c': 0.7,
        'node_d': 0.3
    },
    'node_b': {
        'node_a': 0.5,
        'node_e': 0.9
    },
    'node_c': {
        'node_a': 0.7,
        'node_f': 0.2
    }
}

source = 'node_a'
num_samples = 5
reverse = 0

ARGS = {
    'graph': graph,
    'source': source,
    'num_samples': num_samples,
    'reverse': reverse
}
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 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
random_delete Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from zjunlp/relphormer
pointer only · get_code("a3b7d3d832aced8d")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 2 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
random_delete 1 other paper
1 dated earlier
2205.10852 (2022-05)
Relphormer: Relational Graph Transformer for Knowledge Graph Representations

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

Knowledge Graph Completion (KGC) is crucial for addressing knowledge graph incompleteness and supporting downstream applications. Many models have been proposed for KGC. They can be categorized into two main classes: triple-based and text-based approaches. Triple-based methods struggle with long-tail entities due to limited structural information and imbalanced entity distributions. Text-based methods alleviate this issue but require costly training for language models and specific finetuning for knowledge graphs, which limits their efficiency. To alleviate these limitations, in this paper, we propose KICGPT, a framework that integrates a large language model (LLM) and a triple-based KGC retriever. It alleviates the long-tail problem without incurring additional training overhead. KICGPT uses an in-context learning strategy called Knowledge Prompt, which encodes structural knowledge into demonstrations to guide the LLM. Empirical results on benchmark datasets demonstrate the effectiveness of KICGPT with smaller training overhead and no finetuning.

For agents

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

get_harvested_code_for_paper("2402.02389")
get_code_for_paper("2402.02389")
have("2402.02389")

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

curl https://syntology.ai/api/ran/2402.02389.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.02389.svg)](https://syntology.ai/paper/2402.02389)

Connect an agent — have() is free.