SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.06312 · ACL · 2020

Reasoning with Latent Structure Refinement for Document-Level Relation Extraction

Zhijiang Guo, Guoshun Nan, Wei Lu, Ivan Sekulić

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-21; 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/2005.06312.json · badge: /api/ran/2005.06312.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
nanguoshun/LSR marked official in Papers with Code
Papers with Code archive
4 ran · 2 no recorded run
scofield7419/DiaRE-D2G community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
Encoder Ran
ran on a synthesized input
nanguoshun/LSR/code/models/lsr.py
pointer only (licence: NONE) · get_code("595e166a8ca90874")
How it ran

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

GraphConvLayer Ran
ran on a synthesized input
nanguoshun/LSR/code/models/lsr.py
pointer only (licence: NONE) · get_code("ba46f3df56f000df")
How it ran

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

SelfAttention Ran
ran on a synthesized input
nanguoshun/LSR/code/models/lsr.py
pointer only (licence: NONE) · get_code("9002f9968c2d49b3")
How it ran

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

SpGraphAttentionLayer Ran
ran on a synthesized input · constructed an object; no result was computed
scofield7419/DiaRE-D2G/models/layers.py
code served (permissive licence) · get_code("7712f8727696bca0")
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 an instance of its own class, SpGraphAttentionLayer: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch.nn as nn

torch.manual_seed(0)

# Create small test tensors for the layer
in_features = 4
out_features = 3
num_nodes = 2

# Create a sparse adjacency matrix (2x2 with some edges)
# We need at least one edge for the layer to work
adj = torch.tensor([[1.0, 1.0],
                    [1.0, 0.0]])

# Create input features (num_nodes x in_features)
input_features = torch.randn(num_nodes, in_features)

ARGS = {
    'in_features': in_features,
    'out_features': out_features,
    'dropout': 0.2,
    'alpha': 0.2,
    'concat': True
}
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 SpGraphAttentionLayer — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a SpGraphAttentionLayer 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
StructInduction Ran
ran on a synthesized input
nanguoshun/LSR/code/models/lsr.py
pointer only (licence: NONE) · get_code("51320645411607c4")
How it ran

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

DynamicReasoner Not yet run
unverified (harvested, no recorded run)
nanguoshun/LSR/code/models/lsr.py
pointer only (licence: NONE) · get_code("9ef4d206c1c24798")
How it ran

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

LSR Not yet run
unverified (harvested, no recorded run)
nanguoshun/LSR/code/models/lsr.py
pointer only (licence: NONE) · get_code("1f2a2663db3d1f09")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nanguoshun/LSR 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 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 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.

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Document-level relation extraction requires integrating information within and across multiple sentences of a document and capturing complex interactions between inter-sentence entities. However, effective aggregation of relevant information in the document remains a challenging research question. Existing approaches construct static document-level graphs based on syntactic trees, co-references or heuristics from the unstructured text to model the dependencies. Unlike previous methods that may not be able to capture rich non-local interactions for inference, we propose a novel model that empowers the relational reasoning across sentences by automatically inducing the latent document-level graph. We further develop a refinement strategy, which enables the model to incrementally aggregate relevant information for multi-hop reasoning. Specifically, our model achieves an F 1 score of 59.05 on a large-scale documentlevel dataset (DocRED), significantly improving over the previous results, and also yields new state-of-the-art results on the CDR and GDA dataset. Furthermore, extensive analyses show that the model is able to discover more accurate inter-sentence relations.

For agents

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

get_harvested_code_for_paper("2005.06312")
get_code_for_paper("2005.06312")
have("2005.06312")

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

curl https://syntology.ai/api/ran/2005.06312.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.06312.svg)](https://syntology.ai/paper/2005.06312)

Connect an agent — have() is free.