SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.03620 · 2023

Recent advances in the Self-Referencing Embedding Strings (SELFIES) library

arXiv · PDF · Open in the Atlas

Code that ran

3 of 7 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 1 has no contract verdict; 1 failure of our instrument; 4 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/2302.03620.json · badge: /api/ran/2302.03620.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
aspuru-guzik-group/selfies canonical (classifier label)
classifier basis not recorded on the link
3 ran · 4 no recorded run
FunctionStatusWhere it lives
get_alphabet_from_selfies Ran
ran on a synthesized input
aspuru-guzik-group/selfies/selfies/utils/selfies_utils.py
code served (permissive licence) · get_code("fb596900403bbe31")
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 torch

def split_selfies(selfies: str):
    """Tokenizes a SELFIES string into its individual symbols."""
    left_idx = selfies.find('[')
    while 0 <= left_idx < len(selfies):
        right_idx = selfies.find(']', left_idx + 1)
        if right_idx == -1:
            raise ValueError("malformed SELFIES string, hanging '[' bracket")
        next_symbol = selfies[left_idx:right_idx + 1]
        yield next_symbol
        left_idx = right_idx + 1
        if selfies[left_idx:left_idx + 1] == '.':
            yield '.'
            left_idx += 1

def get_alphabet_from_selfies(selfies_iter):
    """Constructs an alphabet from an iterable of SELFIES strings."""
    alphabet = set()
    for s in selfies_iter:
        for symbol in split_selfies(s):
            alphabet.add(symbol)
    alphabet.discard('.')
    return alphabet

# Construct valid SELFIES strings
selfies_list = [
    "[C][F][O]",
    "[C].[O]",
    "[F][F]",
    "[C][=C][N]"
]

ARGS = {
    "selfies_iter": selfies_list
}
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 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
get_bonding_capacity Ran
ran, honoured the contract we drafted
aspuru-guzik-group/selfies/selfies/bond_constraints.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from wentao228/SmiSelf, is pointer only (licence: NONE) · get_code("32fb62b6dcc59a99")
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 wentao228/SmiSelf, 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.

smiles_to_bond Ran
ran; our contract draft was wrong, not the code
aspuru-guzik-group/selfies/selfies/utils/smiles_utils.py
code served (permissive licence) · get_code("c494674705c86e66")
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 1, 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.

# Setup code for smiles_to_bond function

# Analyze the function:
# - It takes one parameter: bond_char (Optional[str])
# - It uses .get() on SMILES_BOND_ORDERS dict with bond_char as key
# - It checks if bond_char is in SMILES_STEREO_BONDS set
# - Returns a tuple of (order, stereo)

# The function is straightforward - it just needs string inputs (or None)

ARGS = {
    'bond_char': '-'
}
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, ndim 1, 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
encoding_to_selfies Not yet run
unverified (harvested, no recorded run)
aspuru-guzik-group/selfies/selfies/utils/encoding_utils.py
code served (permissive licence) · get_code("65829db484ea6c2a")
How it ran

no invocation recorded.

find_perfect_matching Not yet run
unverified (harvested, no recorded run)
aspuru-guzik-group/selfies/selfies/utils/matching_utils.py
code served (permissive licence) · get_code("e8341af6c9fe271b")
How it ran

no invocation recorded.

get_preset_constraints Not yet run
unverified (harvested, no recorded run)
aspuru-guzik-group/selfies/selfies/bond_constraints.py
code served (permissive licence) · get_code("d00a9f08948eb9c8")
How it ran

no invocation recorded.

len_selfies Not yet run
unverified (harvested, no recorded run)
aspuru-guzik-group/selfies/selfies/utils/selfies_utils.py
code served (permissive licence) · get_code("5abbee63fffd1547")
How it ran

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, 5 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 2 later) and 2 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
get_bonding_capacity 2 other papers
1 dated earlier, 1 later
2211.13322 (2022-11)
Group SELFIES: A Robust Fragment-Based Molecular String Representation
2509.23099 (2025-09)
How to Make Large Language Models Generate 100% Valid Molecules?
get_alphabet_from_selfies 1 other paper
1 dated earlier
2211.13322 (2022-11)
Group SELFIES: A Robust Fragment-Based Molecular String Representation
get_preset_constraints 1 other paper
1 dated earlier
2211.13322 (2022-11)
Group SELFIES: A Robust Fragment-Based Molecular String Representation
len_selfies 1 other paper
1 dated earlier
2211.13322 (2022-11)
Group SELFIES: A Robust Fragment-Based Molecular String Representation
smiles_to_bond 1 other paper
1 later
2509.23099 (2025-09)
How to Make Large Language Models Generate 100% Valid Molecules?

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

String-based molecular representations play a crucial role in cheminformatics applications, and with the growing success of deep learning in chemistry, have been readily adopted into machine learning pipelines. However, traditional string-based representations such as SMILES are often prone to syntactic and semantic errors when produced by generative models. To address these problems, a novel representation, SELF-referencIng Embedded Strings (SELFIES), was proposed that is inherently 100% robust, alongside an accompanying open-source implementation. Since then, we have generalized SELFIES to support a wider range of molecules and semantic constraints and streamlined its underlying grammar. We have implemented this updated representation in subsequent versions of \selfieslib, where we have also made major advances with respect to design, efficiency, and supported features. Hence, we present the current status of \selfieslib (version 2.1.1) in this manuscript.

For agents

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

get_harvested_code_for_paper("2302.03620")
get_code_for_paper("2302.03620")
have("2302.03620")

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

curl https://syntology.ai/api/ran/2302.03620.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.03620.svg)](https://syntology.ai/paper/2302.03620)

Connect an agent — have() is free.