{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/recent-advances-in-the-self-referencing","title":"Recent advances in the Self-Referencing Embedding Strings (SELFIES) library","arxiv_id":"2302.03620","date":"2023-02-07","proceeding":null,"authors":["Alston Lo","Robert Pollice","AkshatKumar Nigam","Andrew D. White","Mario Krenn","Alán Aspuru-Guzik"],"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.","url_abs":"https://arxiv.org/abs/2302.03620v1","url_pdf":"https://arxiv.org/pdf/2302.03620v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"recent-advances-in-the-self-referencing","repo_url":"https://github.com/aspuru-guzik-group/selfies","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2302.03620","atlas_url":"https://app.syntology.ai/?focus=2302.03620","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.03620"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aspuru-guzik-group/selfies","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2,"ran_honours":1,"unverified":4},"by_repo_kind":{"official":{"samples":7,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"fb596900403bbe31","entry":"get_alphabet_from_selfies","repo":"aspuru-guzik-group/selfies","repo_kind":"official","path":"selfies/utils/selfies_utils.py","file_url":"https://github.com/aspuru-guzik-group/selfies/blob/HEAD/selfies/utils/selfies_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fb596900403bbe31"}},{"code_sha256_prefix":"32fb62b6dcc59a99","entry":"get_bonding_capacity","repo":"aspuru-guzik-group/selfies","repo_kind":"official","path":"selfies/bond_constraints.py","file_url":"https://github.com/aspuru-guzik-group/selfies/blob/HEAD/selfies/bond_constraints.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"32fb62b6dcc59a99"}},{"code_sha256_prefix":"c494674705c86e66","entry":"smiles_to_bond","repo":"aspuru-guzik-group/selfies","repo_kind":"official","path":"selfies/utils/smiles_utils.py","file_url":"https://github.com/aspuru-guzik-group/selfies/blob/HEAD/selfies/utils/smiles_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c494674705c86e66"}},{"code_sha256_prefix":"65829db484ea6c2a","entry":"encoding_to_selfies","repo":"aspuru-guzik-group/selfies","repo_kind":"official","path":"selfies/utils/encoding_utils.py","file_url":"https://github.com/aspuru-guzik-group/selfies/blob/HEAD/selfies/utils/encoding_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"65829db484ea6c2a"}},{"code_sha256_prefix":"e8341af6c9fe271b","entry":"find_perfect_matching","repo":"aspuru-guzik-group/selfies","repo_kind":"official","path":"selfies/utils/matching_utils.py","file_url":"https://github.com/aspuru-guzik-group/selfies/blob/HEAD/selfies/utils/matching_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e8341af6c9fe271b"}},{"code_sha256_prefix":"d00a9f08948eb9c8","entry":"get_preset_constraints","repo":"aspuru-guzik-group/selfies","repo_kind":"official","path":"selfies/bond_constraints.py","file_url":"https://github.com/aspuru-guzik-group/selfies/blob/HEAD/selfies/bond_constraints.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d00a9f08948eb9c8"}},{"code_sha256_prefix":"5abbee63fffd1547","entry":"len_selfies","repo":"aspuru-guzik-group/selfies","repo_kind":"official","path":"selfies/utils/selfies_utils.py","file_url":"https://github.com/aspuru-guzik-group/selfies/blob/HEAD/selfies/utils/selfies_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5abbee63fffd1547"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}