{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:SXDSYR7PFLE67OY4XHRPVM5QB4","short_pith_number":"pith:SXDSYR7P","canonical_record":{"source":{"id":"2204.00056","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.chem-ph","submitted_at":"2022-03-31T19:39:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ecf4437790c987725e02f403157af2624d1299f486483137b3edbac43e7935aa","abstract_canon_sha256":"864b35aeb1165e83fe2c3a82431af4e562fd6e244844e72c9814b5bd88eb60d5"},"schema_version":"1.0"},"canonical_sha256":"95c72c47ef2ac9efbb1cb9e2fab3b00f3402802095fc7cac75e94d6be74aa1eb","source":{"kind":"arxiv","id":"2204.00056","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.00056","created_at":"2026-07-05T05:12:11Z"},{"alias_kind":"arxiv_version","alias_value":"2204.00056v1","created_at":"2026-07-05T05:12:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.00056","created_at":"2026-07-05T05:12:11Z"},{"alias_kind":"pith_short_12","alias_value":"SXDSYR7PFLE6","created_at":"2026-07-05T05:12:11Z"},{"alias_kind":"pith_short_16","alias_value":"SXDSYR7PFLE67OY4","created_at":"2026-07-05T05:12:11Z"},{"alias_kind":"pith_short_8","alias_value":"SXDSYR7P","created_at":"2026-07-05T05:12:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:SXDSYR7PFLE67OY4XHRPVM5QB4","target":"record","payload":{"canonical_record":{"source":{"id":"2204.00056","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.chem-ph","submitted_at":"2022-03-31T19:39:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ecf4437790c987725e02f403157af2624d1299f486483137b3edbac43e7935aa","abstract_canon_sha256":"864b35aeb1165e83fe2c3a82431af4e562fd6e244844e72c9814b5bd88eb60d5"},"schema_version":"1.0"},"canonical_sha256":"95c72c47ef2ac9efbb1cb9e2fab3b00f3402802095fc7cac75e94d6be74aa1eb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:12:11.184437Z","signature_b64":"iwdDMecokpYhiLCiZXr+gu02VIgb6/D9zKK9i1xf5ckONyoZMod8zb9l0S7lh6uXAshCN7ODaPVZafIDgeFSBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95c72c47ef2ac9efbb1cb9e2fab3b00f3402802095fc7cac75e94d6be74aa1eb","last_reissued_at":"2026-07-05T05:12:11.183958Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:12:11.183958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.00056","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":"2026-07-05T05:12:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9xjvToYDsvrSrEtsqYTfQh5In5aGlDBAIRIpWm5a0L4onhxy3mZi/EfdDOBcUasIs10dCbCTong6G8bPKODqCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:50:31.331833Z"},"content_sha256":"693fde178030af24641f41af2ac72d681c016e4b755c5267cd9886ef9ce1e958","schema_version":"1.0","event_id":"sha256:693fde178030af24641f41af2ac72d681c016e4b755c5267cd9886ef9ce1e958"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:SXDSYR7PFLE67OY4XHRPVM5QB4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SELFIES and the future of molecular string representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.chem-ph","authors_text":"Adamo Young, AkshatKumar Nigam, Al\\'an Aspuru-Guzik, Alberto Alexander Gayle, Alston Lo, Andrew Wang, Andrew White, Angelo Frei, Berend Smit, Chong Sun, Dominik Lemm, Felix Strieth-Kalthoff, Gary Tom, Guido Falk von Rudorff, Jos\\'e Manuel N\\'apoles-Duarte, Kevin Maik Jablonka, Kohulan Rajan, Mario Krenn, Marta Skreta, Nathan C. Frey, Nessa Carson, Pascal Friederich, Philippe Schwaller, Qianxiang Ai, Rafael F. Lameiro, Robert Pollice, Rose Yu, Senja Barthel, Seyed Mohamad Moosavi, Th\\'eophile Gaudin, Ulrich Schatzschneider","submitted_at":"2022-03-31T19:39:20Z","abstract_excerpt":"Artificial intelligence (AI) and machine learning (ML) are expanding in popularity for broad applications to challenging tasks in chemistry and materials science. Examples include the prediction of properties, the discovery of new reaction pathways, or the design of new molecules. The machine needs to read and write fluently in a chemical language for each of these tasks. Strings are a common tool to represent molecular graphs, and the most popular molecular string representation, SMILES, has powered cheminformatics since the late 1980s. However, in the context of AI and ML in chemistry, SMILE"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.00056","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/2204.00056/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":"2026-07-05T05:12:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+anACspOMXk5woiCPDIv4V3hp0XVoBfnC7SflXM+4UDntWVBp7w9EuvYn3kfWWdPTvU5FwONydSfZuQrrGJ9AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:50:31.332402Z"},"content_sha256":"1308a64694f947d9bd08d183d8f882736fad6c31947a3812a8a1e87248a1f3c5","schema_version":"1.0","event_id":"sha256:1308a64694f947d9bd08d183d8f882736fad6c31947a3812a8a1e87248a1f3c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SXDSYR7PFLE67OY4XHRPVM5QB4/bundle.json","state_url":"https://pith.science/pith/SXDSYR7PFLE67OY4XHRPVM5QB4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SXDSYR7PFLE67OY4XHRPVM5QB4/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":"2026-08-03T22:50:31Z","links":{"resolver":"https://pith.science/pith/SXDSYR7PFLE67OY4XHRPVM5QB4","bundle":"https://pith.science/pith/SXDSYR7PFLE67OY4XHRPVM5QB4/bundle.json","state":"https://pith.science/pith/SXDSYR7PFLE67OY4XHRPVM5QB4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SXDSYR7PFLE67OY4XHRPVM5QB4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:SXDSYR7PFLE67OY4XHRPVM5QB4","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":"864b35aeb1165e83fe2c3a82431af4e562fd6e244844e72c9814b5bd88eb60d5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.chem-ph","submitted_at":"2022-03-31T19:39:20Z","title_canon_sha256":"ecf4437790c987725e02f403157af2624d1299f486483137b3edbac43e7935aa"},"schema_version":"1.0","source":{"id":"2204.00056","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.00056","created_at":"2026-07-05T05:12:11Z"},{"alias_kind":"arxiv_version","alias_value":"2204.00056v1","created_at":"2026-07-05T05:12:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.00056","created_at":"2026-07-05T05:12:11Z"},{"alias_kind":"pith_short_12","alias_value":"SXDSYR7PFLE6","created_at":"2026-07-05T05:12:11Z"},{"alias_kind":"pith_short_16","alias_value":"SXDSYR7PFLE67OY4","created_at":"2026-07-05T05:12:11Z"},{"alias_kind":"pith_short_8","alias_value":"SXDSYR7P","created_at":"2026-07-05T05:12:11Z"}],"graph_snapshots":[{"event_id":"sha256:1308a64694f947d9bd08d183d8f882736fad6c31947a3812a8a1e87248a1f3c5","target":"graph","created_at":"2026-07-05T05:12:11Z","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/2204.00056/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Artificial intelligence (AI) and machine learning (ML) are expanding in popularity for broad applications to challenging tasks in chemistry and materials science. Examples include the prediction of properties, the discovery of new reaction pathways, or the design of new molecules. The machine needs to read and write fluently in a chemical language for each of these tasks. Strings are a common tool to represent molecular graphs, and the most popular molecular string representation, SMILES, has powered cheminformatics since the late 1980s. However, in the context of AI and ML in chemistry, SMILE","authors_text":"Adamo Young, AkshatKumar Nigam, Al\\'an Aspuru-Guzik, Alberto Alexander Gayle, Alston Lo, Andrew Wang, Andrew White, Angelo Frei, Berend Smit, Chong Sun, Dominik Lemm, Felix Strieth-Kalthoff, Gary Tom, Guido Falk von Rudorff, Jos\\'e Manuel N\\'apoles-Duarte, Kevin Maik Jablonka, Kohulan Rajan, Mario Krenn, Marta Skreta, Nathan C. Frey, Nessa Carson, Pascal Friederich, Philippe Schwaller, Qianxiang Ai, Rafael F. Lameiro, Robert Pollice, Rose Yu, Senja Barthel, Seyed Mohamad Moosavi, Th\\'eophile Gaudin, Ulrich Schatzschneider","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.chem-ph","submitted_at":"2022-03-31T19:39:20Z","title":"SELFIES and the future of molecular string representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.00056","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":"sha256:693fde178030af24641f41af2ac72d681c016e4b755c5267cd9886ef9ce1e958","target":"record","created_at":"2026-07-05T05:12:11Z","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":"864b35aeb1165e83fe2c3a82431af4e562fd6e244844e72c9814b5bd88eb60d5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.chem-ph","submitted_at":"2022-03-31T19:39:20Z","title_canon_sha256":"ecf4437790c987725e02f403157af2624d1299f486483137b3edbac43e7935aa"},"schema_version":"1.0","source":{"id":"2204.00056","kind":"arxiv","version":1}},"canonical_sha256":"95c72c47ef2ac9efbb1cb9e2fab3b00f3402802095fc7cac75e94d6be74aa1eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95c72c47ef2ac9efbb1cb9e2fab3b00f3402802095fc7cac75e94d6be74aa1eb","first_computed_at":"2026-07-05T05:12:11.183958Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:12:11.183958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iwdDMecokpYhiLCiZXr+gu02VIgb6/D9zKK9i1xf5ckONyoZMod8zb9l0S7lh6uXAshCN7ODaPVZafIDgeFSBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:12:11.184437Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.00056","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:693fde178030af24641f41af2ac72d681c016e4b755c5267cd9886ef9ce1e958","sha256:1308a64694f947d9bd08d183d8f882736fad6c31947a3812a8a1e87248a1f3c5"],"state_sha256":"d781d33d90b07b4b81d1b29e5fd434a3e271946d957167f07591fbd4fafa3d75"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KWr0hjSNjMdtdwZ1XXh3Nl8NDxN9MO7tkXb1PXCZRTJ5M0jM4bp3UTOjp7qqCz8zlgi2L4vf2yZbgO1LOGYUAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T22:50:31.335955Z","bundle_sha256":"9e29424f2908d7de1bf53b6f72f8017f56f795357163ef220f69babe4d29e0ad"}}