SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.15484 · NeurIPS · 2023

NuTrea: Neural Tree Search for Context-guided Multi-hop KGQA

Hyunwoo Kim, Kyu Hyeong, Choi, Seunghun Lee, Jaewon Chu

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 0 have no contract verdict; 5 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/2310.15484.json · badge: /api/ran/2310.15484.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
mlvlab/NuTrea canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
FunctionStatusWhere it lives
cal_accuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
mlvlab/NuTrea/src/evaluate.py
pointer only (licence: MIT); the stored copy get_code serves, from cmavro/gnn-rag, is pointer only (licence: NONE) · get_code("e2b0054974cf0526")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from cmavro/gnn-rag, and GitHub detected no licence in that repository 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.

create_logger Ran
ran; our contract draft was wrong, not the code
mlvlab/NuTrea/src/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from cmavro/gnn-rag, is pointer only (licence: NONE) · get_code("a315b40cce5ae385")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from cmavro/gnn-rag, and GitHub detected no licence in that repository 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.

f1_and_hits Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
mlvlab/NuTrea/src/evaluate.py
code served (permissive licence) · get_code("6b47f14c88f967d2")
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 tuple. 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.

# Analyze the function to understand what it needs:
# - answers: list of answer IDs (integers)
# - candidate2prob: list of tuples (candidate_id, probability)
# - id2entity: dict mapping IDs to entity names (strings)
# - eps: float threshold (default 0.5)

# The function uses:
# - id2entity[a] to look up entity names by ID
# - candidate2prob as a list that can be sorted
# - answers as a list to check membership with 'in'

# Create valid arguments:
id2entity = {
    0: "entity_0",
    1: "entity_1",
    2: "entity_2",
    3: "entity_3",
    4: "entity_4",
}

answers = [1, 3]

candidate2prob = [
    (1, 0.6),
    (2, 0.3),
    (0, 0.15),
]

eps = 0.5

ARGS = {
    "answers": answers,
    "candidate2prob": candidate2prob,
    "id2entity": id2entity,
    "eps": eps,
}
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 tuple — a tuple output has no array shape of its own; none is 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_dict Ran
ran; our contract draft was wrong, not the code
mlvlab/NuTrea/src/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from cmavro/gnn-rag, is pointer only (licence: NONE) · get_code("89b3368210f04f55")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from cmavro/gnn-rag, and GitHub detected no licence in that repository 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.

load_dict Ran
ran; our contract draft was wrong, not the code
mlvlab/NuTrea/src/dataset_load.py
pointer only (licence: MIT); the stored copy get_code serves, from cmavro/gnn-rag, is pointer only (licence: NONE) · get_code("df9be8b9ddd85c0a")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from cmavro/gnn-rag, and GitHub detected no licence in that repository 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.

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, 4 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
load_dict 3 other papers
1 dated earlier, 2 later
2022.findings-emnlp.181 (2022 (year only))
ReaRev: Adaptive Reasoning for Question Answering over Knowledge Graphs
2402.02175 (2024-02)
Enhancing Complex Question Answering over Knowledge Graphs through Evidence Pattern Retrieval
2405.20139 (2024-05)
GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning
cal_accuracy 2 other papers
1 dated earlier, 1 later
2022.findings-emnlp.181 (2022 (year only))
ReaRev: Adaptive Reasoning for Question Answering over Knowledge Graphs
2405.20139 (2024-05)
GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning
create_logger 2 other papers
1 dated earlier, 1 later
2022.findings-emnlp.181 (2022 (year only))
ReaRev: Adaptive Reasoning for Question Answering over Knowledge Graphs
2405.20139 (2024-05)
GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning
get_dict 2 other papers
1 dated earlier, 1 later
2022.findings-emnlp.181 (2022 (year only))
ReaRev: Adaptive Reasoning for Question Answering over Knowledge Graphs
2405.20139 (2024-05)
GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning
f1_and_hits 1 other paper
1 dated earlier
2022.findings-emnlp.181 (2022 (year only))
ReaRev: Adaptive Reasoning for Question Answering over Knowledge 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

Multi-hop Knowledge Graph Question Answering (KGQA) is a task that involves retrieving nodes from a knowledge graph (KG) to answer natural language questions. Recent GNN-based approaches formulate this task as a KG path searching problem, where messages are sequentially propagated from the seed node towards the answer nodes. However, these messages are past-oriented, and they do not consider the full KG context. To make matters worse, KG nodes often represent proper noun entities and are sometimes encrypted, being uninformative in selecting between paths. To address these problems, we propose Neural Tree Search (Nu-Trea), a tree search-based GNN model that incorporates the broader KG context. Our model adopts a message-passing scheme that probes the unreached subtree regions to boost the past-oriented embeddings. In addition, we introduce the Relation Frequency-Inverse Entity Frequency (RF-IEF) node embedding that considers the global KG context to better characterize ambiguous KG nodes. The general effectiveness of our approach is demonstrated through experiments on three major multi-hop KGQA benchmark datasets, and our extensive analyses further validate its expressiveness and robustness. Overall, NuTrea provides a powerful means to query the KG with complex natural language questions. Code is available at https://github.com/mlvlab/NuTrea.

For agents

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

get_harvested_code_for_paper("2310.15484")
get_code_for_paper("2310.15484")
have("2310.15484")

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

curl https://syntology.ai/api/ran/2310.15484.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.15484.svg)](https://syntology.ai/paper/2310.15484)

Connect an agent — have() is free.