{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EQLAKPS6RM2HJ5M3IEMEVNHPGD","short_pith_number":"pith:EQLAKPS6","canonical_record":{"source":{"id":"2304.04662","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2023-04-10T15:38:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bb73a15d33ecc02a893047afe2a57f2a7be5debeeb653789acdeb43980089d70","abstract_canon_sha256":"196b4b9a82ae88782e051c846a8be8faf9740042d467bac714c98573a99a7fd6"},"schema_version":"1.0"},"canonical_sha256":"2416053e5e8b3474f59b41184ab4ef30fc60e193cb229db5e3107447355ed8c0","source":{"kind":"arxiv","id":"2304.04662","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.04662","created_at":"2026-07-05T06:13:56Z"},{"alias_kind":"arxiv_version","alias_value":"2304.04662v2","created_at":"2026-07-05T06:13:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04662","created_at":"2026-07-05T06:13:56Z"},{"alias_kind":"pith_short_12","alias_value":"EQLAKPS6RM2H","created_at":"2026-07-05T06:13:56Z"},{"alias_kind":"pith_short_16","alias_value":"EQLAKPS6RM2HJ5M3","created_at":"2026-07-05T06:13:56Z"},{"alias_kind":"pith_short_8","alias_value":"EQLAKPS6","created_at":"2026-07-05T06:13:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EQLAKPS6RM2HJ5M3IEMEVNHPGD","target":"record","payload":{"canonical_record":{"source":{"id":"2304.04662","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2023-04-10T15:38:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bb73a15d33ecc02a893047afe2a57f2a7be5debeeb653789acdeb43980089d70","abstract_canon_sha256":"196b4b9a82ae88782e051c846a8be8faf9740042d467bac714c98573a99a7fd6"},"schema_version":"1.0"},"canonical_sha256":"2416053e5e8b3474f59b41184ab4ef30fc60e193cb229db5e3107447355ed8c0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:56.118715Z","signature_b64":"hMoZdz+BY87ijZqpujz5+9ir7+0ImU/Bvv7vhEBqUFJHByA6kmfxvjIyF3ZXYwDgnsCBb4BHIqEeM9d1qK8EDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2416053e5e8b3474f59b41184ab4ef30fc60e193cb229db5e3107447355ed8c0","last_reissued_at":"2026-07-05T06:13:56.118210Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:56.118210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.04662","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:13:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZrFpA0ivyp5l7c0FQHyMHw/cKHrJGZ+FRzyZeA+OYr++rYLfrdtX1JBGY18TV5Z/+vfBPaxe+pCLaotInB6PAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T11:54:41.689569Z"},"content_sha256":"823680f913fe2d4fa5a839841b711cc9866bb8076979ec6ee9424a1b8be65e4a","schema_version":"1.0","event_id":"sha256:823680f913fe2d4fa5a839841b711cc9866bb8076979ec6ee9424a1b8be65e4a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EQLAKPS6RM2HJ5M3IEMEVNHPGD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SELFormer: Molecular Representation Learning via SELFIES Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Atabey \\\"Unl\\\"u, Atakan Y\\\"uksel, Erva Ulusoy, Tunca Do\\u{g}an","submitted_at":"2023-04-10T15:38:25Z","abstract_excerpt":"Automated computational analysis of the vast chemical space is critical for numerous fields of research such as drug discovery and material science. Representation learning techniques have recently been employed with the primary objective of generating compact and informative numerical expressions of complex data. One approach to efficiently learn molecular representations is processing string-based notations of chemicals via natural language processing (NLP) algorithms. Majority of the methods proposed so far utilize SMILES notations for this purpose; however, SMILES is associated with numero"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04662","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/2304.04662/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":"2026-07-05T06:13:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aAuJtd89nXa2pUhRP+rApb0kxs1LsyDD/pCIbMIwwoALVyqvlt1kgnp3rNVXA2/DkPpecWdLxZrPpBxXNT7hCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T11:54:41.690686Z"},"content_sha256":"057c2f67748ffaeeef6edfa0922dde32d86d14381eae278d382e667d2a0e501d","schema_version":"1.0","event_id":"sha256:057c2f67748ffaeeef6edfa0922dde32d86d14381eae278d382e667d2a0e501d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EQLAKPS6RM2HJ5M3IEMEVNHPGD/bundle.json","state_url":"https://pith.science/pith/EQLAKPS6RM2HJ5M3IEMEVNHPGD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EQLAKPS6RM2HJ5M3IEMEVNHPGD/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":"2026-08-01T11:54:41Z","links":{"resolver":"https://pith.science/pith/EQLAKPS6RM2HJ5M3IEMEVNHPGD","bundle":"https://pith.science/pith/EQLAKPS6RM2HJ5M3IEMEVNHPGD/bundle.json","state":"https://pith.science/pith/EQLAKPS6RM2HJ5M3IEMEVNHPGD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EQLAKPS6RM2HJ5M3IEMEVNHPGD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EQLAKPS6RM2HJ5M3IEMEVNHPGD","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":"196b4b9a82ae88782e051c846a8be8faf9740042d467bac714c98573a99a7fd6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2023-04-10T15:38:25Z","title_canon_sha256":"bb73a15d33ecc02a893047afe2a57f2a7be5debeeb653789acdeb43980089d70"},"schema_version":"1.0","source":{"id":"2304.04662","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.04662","created_at":"2026-07-05T06:13:56Z"},{"alias_kind":"arxiv_version","alias_value":"2304.04662v2","created_at":"2026-07-05T06:13:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04662","created_at":"2026-07-05T06:13:56Z"},{"alias_kind":"pith_short_12","alias_value":"EQLAKPS6RM2H","created_at":"2026-07-05T06:13:56Z"},{"alias_kind":"pith_short_16","alias_value":"EQLAKPS6RM2HJ5M3","created_at":"2026-07-05T06:13:56Z"},{"alias_kind":"pith_short_8","alias_value":"EQLAKPS6","created_at":"2026-07-05T06:13:56Z"}],"graph_snapshots":[{"event_id":"sha256:057c2f67748ffaeeef6edfa0922dde32d86d14381eae278d382e667d2a0e501d","target":"graph","created_at":"2026-07-05T06:13:56Z","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/2304.04662/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated computational analysis of the vast chemical space is critical for numerous fields of research such as drug discovery and material science. Representation learning techniques have recently been employed with the primary objective of generating compact and informative numerical expressions of complex data. One approach to efficiently learn molecular representations is processing string-based notations of chemicals via natural language processing (NLP) algorithms. Majority of the methods proposed so far utilize SMILES notations for this purpose; however, SMILES is associated with numero","authors_text":"Atabey \\\"Unl\\\"u, Atakan Y\\\"uksel, Erva Ulusoy, Tunca Do\\u{g}an","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2023-04-10T15:38:25Z","title":"SELFormer: Molecular Representation Learning via SELFIES Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04662","kind":"arxiv","version":2},"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":"sha256:823680f913fe2d4fa5a839841b711cc9866bb8076979ec6ee9424a1b8be65e4a","target":"record","created_at":"2026-07-05T06:13:56Z","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":"196b4b9a82ae88782e051c846a8be8faf9740042d467bac714c98573a99a7fd6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2023-04-10T15:38:25Z","title_canon_sha256":"bb73a15d33ecc02a893047afe2a57f2a7be5debeeb653789acdeb43980089d70"},"schema_version":"1.0","source":{"id":"2304.04662","kind":"arxiv","version":2}},"canonical_sha256":"2416053e5e8b3474f59b41184ab4ef30fc60e193cb229db5e3107447355ed8c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2416053e5e8b3474f59b41184ab4ef30fc60e193cb229db5e3107447355ed8c0","first_computed_at":"2026-07-05T06:13:56.118210Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:13:56.118210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hMoZdz+BY87ijZqpujz5+9ir7+0ImU/Bvv7vhEBqUFJHByA6kmfxvjIyF3ZXYwDgnsCBb4BHIqEeM9d1qK8EDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:13:56.118715Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.04662","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:823680f913fe2d4fa5a839841b711cc9866bb8076979ec6ee9424a1b8be65e4a","sha256:057c2f67748ffaeeef6edfa0922dde32d86d14381eae278d382e667d2a0e501d"],"state_sha256":"feba1cd82ec72781fcde6b451b439e520265eea8de542ccfa7e29ef11acb5288"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"09PY2ci7/GPISstyAldRu4BRDh16mxKNrZDiBbbtGlej6W+6vCmQqnyjDUjORfeoWHCYyti1UX54P9Y83WCBAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T11:54:41.694405Z","bundle_sha256":"1b23c554352ca7910b54a4b2de7d19e479dae87277f4e992b7b652d4f9b32218"}}