{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4I3E5SDDUCJ75XPTDLKFJ4QQG6","short_pith_number":"pith:4I3E5SDD","canonical_record":{"source":{"id":"2302.03620","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.chem-ph","submitted_at":"2023-02-07T17:24:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d433f64c965feca02168de1e2c7430dc8d1e982a044172379c412d0671a6df7c","abstract_canon_sha256":"2a706127a1561ef0bec890095baaeff864024aa55340f504848647bc0ff0e9ff"},"schema_version":"1.0"},"canonical_sha256":"e2364ec863a093feddf31ad454f21037b5d6035c6d827605d3f59e44f3911bf0","source":{"kind":"arxiv","id":"2302.03620","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.03620","created_at":"2026-07-05T06:50:38Z"},{"alias_kind":"arxiv_version","alias_value":"2302.03620v1","created_at":"2026-07-05T06:50:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03620","created_at":"2026-07-05T06:50:38Z"},{"alias_kind":"pith_short_12","alias_value":"4I3E5SDDUCJ7","created_at":"2026-07-05T06:50:38Z"},{"alias_kind":"pith_short_16","alias_value":"4I3E5SDDUCJ75XPT","created_at":"2026-07-05T06:50:38Z"},{"alias_kind":"pith_short_8","alias_value":"4I3E5SDD","created_at":"2026-07-05T06:50:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4I3E5SDDUCJ75XPTDLKFJ4QQG6","target":"record","payload":{"canonical_record":{"source":{"id":"2302.03620","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.chem-ph","submitted_at":"2023-02-07T17:24:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d433f64c965feca02168de1e2c7430dc8d1e982a044172379c412d0671a6df7c","abstract_canon_sha256":"2a706127a1561ef0bec890095baaeff864024aa55340f504848647bc0ff0e9ff"},"schema_version":"1.0"},"canonical_sha256":"e2364ec863a093feddf31ad454f21037b5d6035c6d827605d3f59e44f3911bf0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:38.893921Z","signature_b64":"MaeGGUfoWl5fsiWwfrD37P0f0mG0AiXhQmT6z8RrGmvnmMiB8S9eK4MQSk/OEHow9eq9SY2M89c4+X5MhpfhBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2364ec863a093feddf31ad454f21037b5d6035c6d827605d3f59e44f3911bf0","last_reissued_at":"2026-07-05T06:50:38.893455Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:38.893455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.03620","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:50:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ba7uhZWkwoloWyn6QS0S6dVyXz3ayXpQPqJE7NVdtKNPGzHYykVyu7O4ji/Kf+y2BmnivPwcPBtLcdEgj6SBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:07:19.369177Z"},"content_sha256":"422f0c641215bca4bb473214a072af3df61026c3c87d6d47161c1193ae9803dd","schema_version":"1.0","event_id":"sha256:422f0c641215bca4bb473214a072af3df61026c3c87d6d47161c1193ae9803dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4I3E5SDDUCJ75XPTDLKFJ4QQG6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recent advances in the Self-Referencing Embedding Strings (SELFIES) library","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.chem-ph","authors_text":"AkshatKumar Nigam, Al\\'an Aspuru-Guzik, Alston Lo, Andrew D. White, Mario Krenn, Robert Pollice","submitted_at":"2023-02-07T17:24:08Z","abstract_excerpt":"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 s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03620","kind":"arxiv","version":1},"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/2302.03620/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:50:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yYWj9rhG2UHQ2Ccd7/69rUBD49gS0bZSAwS5YlfALl8Zd0QI6Kj44cL4Z2F/Nus6MX1cUgn3URT7u+dfE191CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:07:19.369739Z"},"content_sha256":"df63ba469d682f2990ac7d4e555e468797e5889abecdbb0444c67f4d01225cc5","schema_version":"1.0","event_id":"sha256:df63ba469d682f2990ac7d4e555e468797e5889abecdbb0444c67f4d01225cc5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4I3E5SDDUCJ75XPTDLKFJ4QQG6/bundle.json","state_url":"https://pith.science/pith/4I3E5SDDUCJ75XPTDLKFJ4QQG6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4I3E5SDDUCJ75XPTDLKFJ4QQG6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T20:07:19Z","links":{"resolver":"https://pith.science/pith/4I3E5SDDUCJ75XPTDLKFJ4QQG6","bundle":"https://pith.science/pith/4I3E5SDDUCJ75XPTDLKFJ4QQG6/bundle.json","state":"https://pith.science/pith/4I3E5SDDUCJ75XPTDLKFJ4QQG6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4I3E5SDDUCJ75XPTDLKFJ4QQG6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4I3E5SDDUCJ75XPTDLKFJ4QQG6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2a706127a1561ef0bec890095baaeff864024aa55340f504848647bc0ff0e9ff","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.chem-ph","submitted_at":"2023-02-07T17:24:08Z","title_canon_sha256":"d433f64c965feca02168de1e2c7430dc8d1e982a044172379c412d0671a6df7c"},"schema_version":"1.0","source":{"id":"2302.03620","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.03620","created_at":"2026-07-05T06:50:38Z"},{"alias_kind":"arxiv_version","alias_value":"2302.03620v1","created_at":"2026-07-05T06:50:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03620","created_at":"2026-07-05T06:50:38Z"},{"alias_kind":"pith_short_12","alias_value":"4I3E5SDDUCJ7","created_at":"2026-07-05T06:50:38Z"},{"alias_kind":"pith_short_16","alias_value":"4I3E5SDDUCJ75XPT","created_at":"2026-07-05T06:50:38Z"},{"alias_kind":"pith_short_8","alias_value":"4I3E5SDD","created_at":"2026-07-05T06:50:38Z"}],"graph_snapshots":[{"event_id":"sha256:df63ba469d682f2990ac7d4e555e468797e5889abecdbb0444c67f4d01225cc5","target":"graph","created_at":"2026-07-05T06:50:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2302.03620/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"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 s","authors_text":"AkshatKumar Nigam, Al\\'an Aspuru-Guzik, Alston Lo, Andrew D. White, Mario Krenn, Robert Pollice","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.chem-ph","submitted_at":"2023-02-07T17:24:08Z","title":"Recent advances in the Self-Referencing Embedding Strings (SELFIES) library"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03620","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:422f0c641215bca4bb473214a072af3df61026c3c87d6d47161c1193ae9803dd","target":"record","created_at":"2026-07-05T06:50:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2a706127a1561ef0bec890095baaeff864024aa55340f504848647bc0ff0e9ff","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.chem-ph","submitted_at":"2023-02-07T17:24:08Z","title_canon_sha256":"d433f64c965feca02168de1e2c7430dc8d1e982a044172379c412d0671a6df7c"},"schema_version":"1.0","source":{"id":"2302.03620","kind":"arxiv","version":1}},"canonical_sha256":"e2364ec863a093feddf31ad454f21037b5d6035c6d827605d3f59e44f3911bf0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2364ec863a093feddf31ad454f21037b5d6035c6d827605d3f59e44f3911bf0","first_computed_at":"2026-07-05T06:50:38.893455Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:50:38.893455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MaeGGUfoWl5fsiWwfrD37P0f0mG0AiXhQmT6z8RrGmvnmMiB8S9eK4MQSk/OEHow9eq9SY2M89c4+X5MhpfhBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:50:38.893921Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.03620","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:422f0c641215bca4bb473214a072af3df61026c3c87d6d47161c1193ae9803dd","sha256:df63ba469d682f2990ac7d4e555e468797e5889abecdbb0444c67f4d01225cc5"],"state_sha256":"308c65061090e71a76c904bf17f65908097dcc6c387b8f913e6de04d34399991"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4gSnEAczD3tFxNvPL2Cp2ezFd42Pxi2vH651FIRlgmMDiv7MTiu9g1YTLjX1Py8GkdEEuwtD3Fb7t5DH17HLBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T20:07:19.375946Z","bundle_sha256":"c4fc971bf77afee182cce1bd58925f66f95758f4f8f1d8a7acad855f8fba943d"}}