{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:NSEHBMCTBDM7PY3SIJ4V7G4DS4","short_pith_number":"pith:NSEHBMCT","schema_version":"1.0","canonical_sha256":"6c8870b05308d9f7e37242795f9b839735ee4d77cbfab06a8d4a42e4e2e1564e","source":{"kind":"arxiv","id":"1905.13741","version":2},"attestation_state":"computed","paper":{"title":"Self-Referencing Embedded Strings (SELFIES): A 100% robust molecular string representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.chem-ph","quant-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"AkshatKumar Nigam, Al\\'an Aspuru-Guzik, Florian H\\\"ase, Mario Krenn, Pascal Friederich","submitted_at":"2019-05-31T17:51:07Z","abstract_excerpt":"The discovery of novel materials and functional molecules can help to solve some of society's most urgent challenges, ranging from efficient energy harvesting and storage to uncovering novel pharmaceutical drug candidates. Traditionally matter engineering -- generally denoted as inverse design -- was based massively on human intuition and high-throughput virtual screening. The last few years have seen the emergence of significant interest in computer-inspired designs based on evolutionary or deep learning methods. The major challenge here is that the standard strings molecular representation S"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1905.13741","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-31T17:51:07Z","cross_cats_sorted":["physics.chem-ph","quant-ph","stat.ML"],"title_canon_sha256":"81710496dae543aacbf56a9a52a11c293b5f41707a9c9ffca701342eada3900d","abstract_canon_sha256":"8fab8e80ab54492c73cecbd1a798ccf5fda8dd8c35ea6f13f70423dbddfed60f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:13.766172Z","signature_b64":"jIg4LOqpC1UHtvrMAp+YBl9jTqEtmABEC25wItg3nynUk+/ZvBZeS/aSpyBWrxWhgYzv0DWZw30GYIXvshw4Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c8870b05308d9f7e37242795f9b839735ee4d77cbfab06a8d4a42e4e2e1564e","last_reissued_at":"2026-07-05T01:49:13.765677Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:13.765677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Referencing Embedded Strings (SELFIES): A 100% robust molecular string representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.chem-ph","quant-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"AkshatKumar Nigam, Al\\'an Aspuru-Guzik, Florian H\\\"ase, Mario Krenn, Pascal Friederich","submitted_at":"2019-05-31T17:51:07Z","abstract_excerpt":"The discovery of novel materials and functional molecules can help to solve some of society's most urgent challenges, ranging from efficient energy harvesting and storage to uncovering novel pharmaceutical drug candidates. Traditionally matter engineering -- generally denoted as inverse design -- was based massively on human intuition and high-throughput virtual screening. The last few years have seen the emergence of significant interest in computer-inspired designs based on evolutionary or deep learning methods. The major challenge here is that the standard strings molecular representation S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13741","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1905.13741/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1905.13741","created_at":"2026-07-05T01:49:13.765734+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.13741v2","created_at":"2026-07-05T01:49:13.765734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13741","created_at":"2026-07-05T01:49:13.765734+00:00"},{"alias_kind":"pith_short_12","alias_value":"NSEHBMCTBDM7","created_at":"2026-07-05T01:49:13.765734+00:00"},{"alias_kind":"pith_short_16","alias_value":"NSEHBMCTBDM7PY3S","created_at":"2026-07-05T01:49:13.765734+00:00"},{"alias_kind":"pith_short_8","alias_value":"NSEHBMCT","created_at":"2026-07-05T01:49:13.765734+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21395","citing_title":"Atomistic Language Models Understand and Generate Materials","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2412.14642","citing_title":"Speak-to-Structure: Evaluating LLMs in Open-domain Natural Language-Driven Molecule Generation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12980","citing_title":"CoRe-Gen: Robust Spectrum-to-Structure Generation under Imperfect Fingerprint Conditions","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NSEHBMCTBDM7PY3SIJ4V7G4DS4","json":"https://pith.science/pith/NSEHBMCTBDM7PY3SIJ4V7G4DS4.json","graph_json":"https://pith.science/api/pith-number/NSEHBMCTBDM7PY3SIJ4V7G4DS4/graph.json","events_json":"https://pith.science/api/pith-number/NSEHBMCTBDM7PY3SIJ4V7G4DS4/events.json","paper":"https://pith.science/paper/NSEHBMCT"},"agent_actions":{"view_html":"https://pith.science/pith/NSEHBMCTBDM7PY3SIJ4V7G4DS4","download_json":"https://pith.science/pith/NSEHBMCTBDM7PY3SIJ4V7G4DS4.json","view_paper":"https://pith.science/paper/NSEHBMCT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.13741&json=true","fetch_graph":"https://pith.science/api/pith-number/NSEHBMCTBDM7PY3SIJ4V7G4DS4/graph.json","fetch_events":"https://pith.science/api/pith-number/NSEHBMCTBDM7PY3SIJ4V7G4DS4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NSEHBMCTBDM7PY3SIJ4V7G4DS4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NSEHBMCTBDM7PY3SIJ4V7G4DS4/action/storage_attestation","attest_author":"https://pith.science/pith/NSEHBMCTBDM7PY3SIJ4V7G4DS4/action/author_attestation","sign_citation":"https://pith.science/pith/NSEHBMCTBDM7PY3SIJ4V7G4DS4/action/citation_signature","submit_replication":"https://pith.science/pith/NSEHBMCTBDM7PY3SIJ4V7G4DS4/action/replication_record"}},"created_at":"2026-07-05T01:49:13.765734+00:00","updated_at":"2026-07-05T01:49:13.765734+00:00"}