SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.13802 · NeurIPS · 2023

Improving Molecular Properties Prediction Through Latent Space Fusion

Hiroshi Kajino, Emilio Brazil, Renato Cerqueira, Eduardo Soares, Akihiro Kishimoto, Seiji Takeda

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; 1 honoured the contract we drafted, 0 violated it and 0 have 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/2310.13802.json · badge: /api/ran/2310.13802.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
IBM/molformer canonical (classifier label)
classifier basis: census
5 ran · 1 no recorded run
FunctionStatusWhere it lives
RMSELoss Ran
ran, honoured the contract we drafted
IBM/molformer/finetune/finetune_pubchem_light.py
code served (permissive licence) · get_code("586e66fcc2f1243d")
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 Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# Create small tensors for yhat and y
# yhat: predicted values, shape (2, 4)
# y: actual values, shape (2, 4)
yhat = torch.randn(2, 4)
y = torch.randn(2, 4)

ARGS = {
    "yhat": yhat,
    "y": y,
}
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 Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
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
apply_rotary_pos_emb Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
IBM/molformer/finetune/rotate_attention/rotary.py
code served (permissive licence) · get_code("80d40f9800211e41")
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, ndim 4, 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

torch.manual_seed(0)

# Create small tensors for q, k, cos, sin
# q and k are query and key tensors with shape (batch, seq_len, hidden_dim)
# cos and sin are positional embedding tensors with the same shape
batch_size = 2
seq_len = 3
hidden_dim = 4

q = torch.randn(batch_size, seq_len, hidden_dim)
k = torch.randn(batch_size, seq_len, hidden_dim)
cos = torch.randn(batch_size, seq_len, hidden_dim)
sin = torch.randn(batch_size, seq_len, hidden_dim)

ARGS = {
    "q": q,
    "k": k,
    "cos": cos,
    "sin": sin,
}
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 tuple, ndim 4, dtype family float — a tuple 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_all_proteins Ran
ran; our contract draft was wrong, not the code
IBM/molformer/finetune/utils.py
code served (permissive licence) · get_code("a82c749dc3fda0e4")
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 set. 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 os
import pandas as pd

# Create a temporary directory with CSV files
temp_dir = tempfile.mkdtemp()

# Create sample CSV files with protein data
df1 = pd.DataFrame({
    'protein': ['ProteinA', 'ProteinB', 'ProteinC'],
    'affinity': [1.0, 2.0, 3.0]
})
df1.to_csv(os.path.join(temp_dir, 'file1.csv'), index=False)

df2 = pd.DataFrame({
    'protein': ['ProteinB', 'ProteinD', 'ProteinE'],
    'affinity': [4.0, 5.0, 6.0]
})
df2.to_csv(os.path.join(temp_dir, 'file2.csv'), index=False)

df3 = pd.DataFrame({
    'protein': ['ProteinA', 'ProteinF'],
    'affinity': [7.0, 8.0]
})
df3.to_csv(os.path.join(temp_dir, 'file3.csv'), index=False)

ARGS = {
    'affinity_dir': temp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type set — a set output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a set 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
rotate_half Ran
ran; our contract draft was wrong, not the code
IBM/molformer/finetune/rotate_attention/rotary.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from dmgcsilva/vigia, is pointer only (licence: NONE) · get_code("766ad0e51b7a8f09")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from dmgcsilva/vigia, 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.

transform_single_embedding_to_multiple Ran
ran; our contract draft was wrong, not the code
IBM/molformer/finetune/utils.py
code served (permissive licence) · get_code("66af878036f6eae3")
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)

# The function takes a smiles_z_map dictionary where:
# - keys are SMILES strings
# - values are embeddings (likely tensors or arrays)
# The function iterates over keys and wraps each embedding in a dict with 'canonical_embeddings' key

# Create sample embeddings
embedding_1 = torch.randn(4)
embedding_2 = torch.randn(4)

# Create the smiles_z_map with SMILES strings as keys and embeddings as values
smiles_z_map = {
    'CCO': embedding_1,
    'CC(C)O': embedding_2,
}

ARGS = {
    'smiles_z_map': smiles_z_map,
}
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_parser Not yet run
unverified (harvested, no recorded run)
IBM/molformer/finetune/args.py
code served (permissive licence) · get_code("1d370a2640ad13f9")
How it ran

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, 3 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 later) and 3 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
rotate_half 9 other papers
1 dated earlier, 8 later
2305.11072 (2023-05)
Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clustering
2311.04219 (2023-11)
OtterHD: A High-Resolution Multi-modality Model
2311.12570 (2023-11)
BEND: Benchmarking DNA Language Models on biologically meaningful tasks
and 6 more not named here
apply_rotary_pos_emb 2 other papers
2 later
2403.00043 (2024-03)
RiNALMo: General-Purpose RNA Language Models Can Generalize Well on Structure Prediction Tasks
2410.08417 (2024-10)
Bilinear MLPs enable weight-based mechanistic interpretability
RMSELoss 1 other paper
1 dated earlier
2106.09553 (2021-06)
Large-Scale Chemical Language Representations Capture Molecular Structure and Properties

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

Pre-trained Language Models have emerged as promising tools for predicting molecular properties, yet their development is in its early stages, necessitating further research to enhance their efficacy and address challenges such as generalization and sample efficiency. In this paper, we present a multi-view approach that combines latent spaces derived from state-of-the-art chemical models. Our approach relies on two pivotal elements: the embeddings derived from MHG-GNN, which represent molecular structures as graphs, and MoLFormer embeddings rooted in chemical language. The attention mechanism of MoLFormer is able to identify relations between two atoms even when their distance is far apart, while the GNN of MHG-GNN can more precisely capture relations among multiple atoms closely located. In this work, we demonstrate the superior performance of our proposed multi-view approach compared to existing state-of-the-art methods, including MoLFormer-XL, which was trained on 1.1 billion molecules, particularly in intricate tasks such as predicting clinical trial drug toxicity and inhibiting HIV replication. We assessed our approach using six benchmark datasets from Molecu-leNet, where it outperformed competitors in five of them. Our study highlights the potential of latent space fusion and feature integration for advancing molecular property prediction. In this work, we use small versions of MHG-GNN and MoLFormer, which opens up an opportunity for further improvement when our approach uses a larger-scale dataset. Preprint. Under review.

For agents

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

get_harvested_code_for_paper("2310.13802")
get_code_for_paper("2310.13802")
have("2310.13802")

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

curl https://syntology.ai/api/ran/2310.13802.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.13802.svg)](https://syntology.ai/paper/2310.13802)

Connect an agent — have() is free.