SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.05906 · ACL · 2024

TTM-RE: Memory-Augmented Document-Level Relation Extraction

Jimeng Sun, Xuan Wang, Chufan Gao

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 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; 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/2406.05906.json · badge: /api/ran/2406.05906.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
chufangao/TTM-RE community
Papers with Code archive
3 ran · 2 no recorded run
FunctionStatusWhere it lives
MLPBlock Ran
ran on a synthesized input · constructed an object; no result was computed
chufangao/TTM-RE/ttm.py
code served (permissive licence) · get_code("f96a7b8bf3905e35")
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, MLPBlock: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "in_dim": 64,
    "mlp_dim": 128,
    "dropout": 0.1,
    "out_dim": None,
}
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 MLPBlock — 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 MLPBlock output the recorded ndim 1 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
TokenAddEraseWrite Ran
ran on a synthesized input · constructed an object; no result was computed
chufangao/TTM-RE/ttm.py
code served (permissive licence) · get_code("049beb3aa9b0d892")
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, TokenAddEraseWrite: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn

torch.manual_seed(0)

# Create the TokenAddEraseWrite module instance
model = nn.Module()

# Define parameters for TokenAddEraseWrite
num_tokens = 8
bottleneck_dim = 64
dropout_rate = 0.1
input_dim = 768
memory_size = 64

# Create small tensors for testing
# memory: [bs, memory_size, c] where bs=2, memory_size=64, c=768
memory = torch.randn(2, memory_size, input_dim)

# control_inputs: [bs, memory_size + input_size, c]
# Let's use a small input_size for testing, say 4
input_size = 4
control_inputs = torch.randn(2, memory_size + input_size, input_dim)

ARGS = {
    "num_tokens": num_tokens,
    "bottleneck_dim": bottleneck_dim,
    "dropout_rate": dropout_rate,
    "input_dim": input_dim,
    "memory_size": memory_size,
}
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 TokenAddEraseWrite — 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 TokenAddEraseWrite 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
TokenLearnerModuleV11 Ran
ran on a synthesized input · constructed an object; no result was computed
chufangao/TTM-RE/ttm.py
code served (permissive licence) · get_code("9582b55e30030192")
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, TokenLearnerModuleV11: the run constructed the object and did not call it, so no result was computed. 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
from torch import nn

torch.manual_seed(0)

# ARGS for TokenLearnerModuleV11.__init__
ARGS = {
    "num_tokens": 8,
    "input_shape": 4,
    "bottleneck_dim": 64,
    "dropout_rate": 0.1,
}
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 TokenLearnerModuleV11 — 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 TokenLearnerModuleV11 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
TokenTuringMachineEncoder Not yet run
unverified (harvested, no recorded run)
chufangao/TTM-RE/ttm.py
code served (permissive licence) · get_code("ea89835398ff603b")
How it ran

no invocation recorded.

TokenTuringMachineUnit Not yet run
unverified (harvested, no recorded run)
chufangao/TTM-RE/ttm.py
code served (permissive licence) · get_code("ea9991c8f3758ba2")
How it ran

no invocation 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, 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 5 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 aims to categorize the association between any two entities within a document. We find that previous methods for document-level relation extraction are ineffective in exploiting the full potential of large amounts of training data with varied noise levels. For example, in the ReDo-cRED benchmark dataset, state-of-the-art methods trained on the large-scale, lower-quality, distantly supervised training data generally do not perform better than those trained solely on the smaller, high-quality, human-annotated training data. To unlock the full potential of large-scale noisy training data for documentlevel relation extraction, we propose TTM-RE, a novel approach that integrates a trainable memory module, known as the Token Turing Machine, with a noisy-robust loss function that accounts for the positive-unlabeled setting. Extensive experiments on ReDocRED, a benchmark dataset for document-level relation extraction, reveal that TTM-RE achieves state-ofthe-art performance (with an absolute F1 score improvement of over 3%). Ablation studies further illustrate the superiority of TTM-RE in other domains (the ChemDisGene dataset in the biomedical domain) and under highly unlabeled settings.

For agents

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

get_harvested_code_for_paper("2406.05906")
get_code_for_paper("2406.05906")
have("2406.05906")

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

curl https://syntology.ai/api/ran/2406.05906.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.05906.svg)](https://syntology.ai/paper/2406.05906)

Connect an agent — have() is free.