{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:U3D4Z42HG3NPT3GW6AXKJGNAD7","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":"eb18e9f5b428bc642c9cc43c4014047300d7f7ac02261114da48d0805f933b54","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-30T09:36:18Z","title_canon_sha256":"3958e71f7e1fe1490eefee2345ed58f378068f8efc25f4790160bdfb60702cdd"},"schema_version":"1.0","source":{"id":"2507.22514","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.22514","created_at":"2026-07-05T11:45:43Z"},{"alias_kind":"arxiv_version","alias_value":"2507.22514v1","created_at":"2026-07-05T11:45:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22514","created_at":"2026-07-05T11:45:43Z"},{"alias_kind":"pith_short_12","alias_value":"U3D4Z42HG3NP","created_at":"2026-07-05T11:45:43Z"},{"alias_kind":"pith_short_16","alias_value":"U3D4Z42HG3NPT3GW","created_at":"2026-07-05T11:45:43Z"},{"alias_kind":"pith_short_8","alias_value":"U3D4Z42H","created_at":"2026-07-05T11:45:43Z"}],"graph_snapshots":[{"event_id":"sha256:dd3df61a666f5c6de3c59795b9e92c71a016b1b9888d2d11d63b83690d9910ac","target":"graph","created_at":"2026-07-05T11:45:43Z","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/2507.22514/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Molecular property prediction is an increasingly critical task within drug discovery and development. Typically, neural networks can learn molecular properties using graph-based, language-based or feature-based methods. Recent advances in natural language processing have highlighted the capabilities of neural networks to learn complex human language using masked language modelling. These approaches to training large transformer-based deep learning models have also been used to learn the language of molecules, as represented by simplified molecular-input line-entry system (SMILES) strings. Here","authors_text":"Anne Osbourn, Brooks Paige, Philip Spence","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-30T09:36:18Z","title":"SmilesT5: Domain-specific pretraining for molecular language models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22514","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":"sha256:739ad1d43c3ba7d9f240562314f4933b2a8da27d233eed449e146b3f4b89948d","target":"record","created_at":"2026-07-05T11:45:43Z","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":"eb18e9f5b428bc642c9cc43c4014047300d7f7ac02261114da48d0805f933b54","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-30T09:36:18Z","title_canon_sha256":"3958e71f7e1fe1490eefee2345ed58f378068f8efc25f4790160bdfb60702cdd"},"schema_version":"1.0","source":{"id":"2507.22514","kind":"arxiv","version":1}},"canonical_sha256":"a6c7ccf34736daf9ecd6f02ea499a01fc8f2a7d0804c540ea75addea9e3f13ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6c7ccf34736daf9ecd6f02ea499a01fc8f2a7d0804c540ea75addea9e3f13ad","first_computed_at":"2026-07-05T11:45:43.677070Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:45:43.677070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"94y6JIf3xd3G4X8wmlqunnUdJjrRjThhkTlasbBcBaz3Yvs8dvxJqPWObQgtAOXzSIpPyQ/bERq4pVoO2PeZAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:45:43.677598Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.22514","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:739ad1d43c3ba7d9f240562314f4933b2a8da27d233eed449e146b3f4b89948d","sha256:dd3df61a666f5c6de3c59795b9e92c71a016b1b9888d2d11d63b83690d9910ac"],"state_sha256":"b09963b7398ce8b59885781c33617dc0e0c1d0fb42a9c58d21bb7fe2d7dc26a0"}