SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.05481 · 2022

A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language

arXiv · PDF · Open in the Atlas

Code that ran

5 of 8 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 3 have no contract verdict; 1 failure of our instrument; 3 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/2209.05481.json · badge: /api/ran/2209.05481.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
ai-hpc-research-team/slm4mol community (classifier label)
classifier basis not recorded on the link
4 ran · 2 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 1 no recorded run
FunctionStatusWhere it lives
ToDevice Ran
ran on a synthesized input
ai-hpc-research-team/slm4mol/src/utils/xutils.py
code served (permissive licence) · get_code("7091cac2247e9821")
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 2, dtype family float, shape (2, 4) 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
import torch.nn as nn

torch.manual_seed(0)

# Create test objects that will be moved to device
test_tensor = torch.randn(2, 4)
test_dict = {
    "a": torch.randn(2, 3),
    "b": 42,
    "c": "string"
}
test_tuple = (torch.randn(2, 4), "text", 10)
test_list = [torch.randn(2, 5), torch.randn(3, 4), "item"]

# Simple class with .to() method (like nn.Module)
class SimpleModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.param = nn.Parameter(torch.randn(2, 4))

simple_module = SimpleModule()

device = "cpu"

ARGS = {
    "obj": test_tensor,
    "device": device
}
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 2, dtype family float, shape (2, 4) — shape (2, 4) 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
custom_collate_fn Ran
ran on a synthesized input
ai-hpc-research-team/slm4mol/src/utils/xutils.py
code served (permissive licence) · get_code("b55b14ce1d8befcc")
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
from torch_geometric.data import Data
from torch.nn.utils.rnn import pad_sequence

torch.manual_seed(0)

class TokenizerOutput:
    def __init__(self, input_ids, attention_mask):
        self.input_ids = input_ids
        self.attention_mask = attention_mask

def create_batch_item():
    """Create a single item that matches the expected structure"""
    item = {}
    
    # Text-like fields that have input_ids and attention_mask
    for key in ['SMILES_labels', 'caption_labels', 'IUPAC_labels', 'InChI_labels', 
                'SELFIES_labels', 'SMILES', 'caption', 'IUPAC', 'InChI', 'SELFIES', 'text', 'scaffold']:
        input_ids = torch.randint(0, 100, (1, 8))
        attention_mask = torch.ones(1, 8)
        item[key] = TokenizerOutput(input_ids, attention_mask)
    
    # Truth fields that are just strings
    for key in ['SMILES_truth', 'caption_truth', 'IUPAC_truth', 'InChI_truth', 'SELFIES_truth']:
        item[key] = "example_string"
    
    # Graph field
    graph_data = Data(
        x=torch.randn(5, 4),
        edge_index=torch.tensor([[0, 1, 2], [1, 2, 3]], dtype=torch.long)
    )
    item['graph'] = graph_data
    
    # Property and ID fields
    item['org_property'] = torch.tensor([[1.5]])
    item['target_property'] = torch.tensor([[2.3]])
    item['cid'] = torch.tensor([[42]])
    item['id'] = torch.tensor([[99]])
    
    # Other numeric fields (will use the last else branch)
    item['other_field'] = torch.randn(1, 3, 4)
    
    return item

batch = [create_batch_item(), create_batch_item()]

ARGS = {
    'batch': batch
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torch_geometric — 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_latest_checkpoint Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from ai-hpc-research-team/git-mol
pointer only · get_code("138b87fa967c256f")
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.

safe_index Ran
ran, honoured the contract we drafted
ai-hpc-research-team/slm4mol/src/feature/graph_featurizer.py
pointer only (licence: MIT); the stored copy get_code serves, from lvkd84/graphfp, is pointer only (licence: NONE) · get_code("556ccfd77bd3c202")
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 lvkd84/graphfp, 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.

text_evaluate Ran
ran on a synthesized input
ai-hpc-research-team/slm4mol/src/evaluations/text_translation_metrics.py
code served (permissive licence) · get_code("8ca70db968a79f18")
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.

import numpy as np
import pandas as pd

class MockTokenizer:
    def tokenize(self, text):
        # Simple tokenization: split by spaces and add special tokens
        tokens = text.split()
        return ['[CLS]'] + tokens + ['[SEP]']

# Create mock tokenizer
tk = MockTokenizer()

# Create small test data
targets = [
    "the quick brown fox",
    "jumps over the lazy dog"
]

preds = [
    "the quick brown fox",
    "jumps over the lazy dog"
]

molecules = [
    "CCO",
    "CC(C)O"
]

text_trunc_length = 128

ARGS = {
    "tk": tk,
    "targets": targets,
    "preds": preds,
    "molecules": molecules,
    "text_trunc_length": text_trunc_length
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
nltk, numpy, pandas, rouge_score — 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
generate_mols Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from calvin-zcx/moflow
pointer only · get_code("54e7398c07a02f5c")
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. No invocation recorded.

generate_scaffold Not yet run
unverified (harvested, no recorded run)
ai-hpc-research-team/slm4mol/src/evaluations/mol_translation_metrics.py
code served (permissive licence) · get_code("0365b968d90ed84e")
How it ran

no invocation recorded.

pad_tensors_to_max_length Not yet run
unverified (harvested, no recorded run)
ai-hpc-research-team/slm4mol/src/models/model_manager.py
code served (permissive licence) · get_code("96dcc6542582fbce")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 3 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 2 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.

FunctionAlso present inEarliest-datedOthers named
safe_index 3 other papers
3 later
2306.07812 (2023-06)
Automated 3D Pre-Training for Molecular Property Prediction
2306.16819 (2023-06)
Graph Denoising Diffusion for Inverse Protein Folding
2310.03274 (2023-10)
Fragment-based Pretraining and Finetuning on Molecular Graphs
generate_mols 1 other paper
1 dated earlier
2006.10137 (2020-06)
MoFlow: An Invertible Flow Model for Generating Molecular Graphs
get_latest_checkpoint 1 other paper
1 later
2308.06911 (2023-08)
GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text

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

Although artificial intelligence (AI) has made significant progress in understanding molecules in a wide range of fields, existing models generally acquire the single cognitive ability from the single molecular modality. Since the hierarchy of molecular knowledge is profound, even humans learn from different modalities including both intuitive diagrams and professional texts to assist their understanding. Inspired by this, we propose a molecular multimodal foundation model which is pretrained from molecular graphs and their semantically related textual data (crawled from published Scientific Citation Index papers) via contrastive learning. This AI model represents a critical attempt that directly bridges molecular graphs and natural language. Importantly, through capturing the specific and complementary information of the two modalities, our proposed model can better grasp molecular expertise. Experimental results show that our model not only exhibits promising performance in cross-modal tasks such as cross-modal retrieval and molecule caption, but also enhances molecular property prediction and possesses capability to generate meaningful molecular graphs from natural language descriptions. We believe that our model would have a broad impact on AI-empowered fields across disciplines such as biology, chemistry, materials, environment, and medicine, among others.

For agents

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

get_harvested_code_for_paper("2209.05481")
get_code_for_paper("2209.05481")
have("2209.05481")

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

curl https://syntology.ai/api/ran/2209.05481.json

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

[![Syntology run record](https://syntology.ai/api/ran/2209.05481.svg)](https://syntology.ai/paper/2209.05481)

Connect an agent — have() is free.