{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:U3D4Z42HG3NPT3GW6AXKJGNAD7","short_pith_number":"pith:U3D4Z42H","schema_version":"1.0","canonical_sha256":"a6c7ccf34736daf9ecd6f02ea499a01fc8f2a7d0804c540ea75addea9e3f13ad","source":{"kind":"arxiv","id":"2507.22514","version":1},"attestation_state":"computed","paper":{"title":"SmilesT5: Domain-specific pretraining for molecular language models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anne Osbourn, Brooks Paige, Philip Spence","submitted_at":"2025-07-30T09:36:18Z","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"},"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":"2507.22514","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-30T09:36:18Z","cross_cats_sorted":[],"title_canon_sha256":"3958e71f7e1fe1490eefee2345ed58f378068f8efc25f4790160bdfb60702cdd","abstract_canon_sha256":"eb18e9f5b428bc642c9cc43c4014047300d7f7ac02261114da48d0805f933b54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:43.677598Z","signature_b64":"94y6JIf3xd3G4X8wmlqunnUdJjrRjThhkTlasbBcBaz3Yvs8dvxJqPWObQgtAOXzSIpPyQ/bERq4pVoO2PeZAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6c7ccf34736daf9ecd6f02ea499a01fc8f2a7d0804c540ea75addea9e3f13ad","last_reissued_at":"2026-07-05T11:45:43.677070Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:43.677070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SmilesT5: Domain-specific pretraining for molecular language models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anne Osbourn, Brooks Paige, Philip Spence","submitted_at":"2025-07-30T09:36:18Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22514","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/2507.22514/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":"2507.22514","created_at":"2026-07-05T11:45:43.677128+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.22514v1","created_at":"2026-07-05T11:45:43.677128+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22514","created_at":"2026-07-05T11:45:43.677128+00:00"},{"alias_kind":"pith_short_12","alias_value":"U3D4Z42HG3NP","created_at":"2026-07-05T11:45:43.677128+00:00"},{"alias_kind":"pith_short_16","alias_value":"U3D4Z42HG3NPT3GW","created_at":"2026-07-05T11:45:43.677128+00:00"},{"alias_kind":"pith_short_8","alias_value":"U3D4Z42H","created_at":"2026-07-05T11:45:43.677128+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U3D4Z42HG3NPT3GW6AXKJGNAD7","json":"https://pith.science/pith/U3D4Z42HG3NPT3GW6AXKJGNAD7.json","graph_json":"https://pith.science/api/pith-number/U3D4Z42HG3NPT3GW6AXKJGNAD7/graph.json","events_json":"https://pith.science/api/pith-number/U3D4Z42HG3NPT3GW6AXKJGNAD7/events.json","paper":"https://pith.science/paper/U3D4Z42H"},"agent_actions":{"view_html":"https://pith.science/pith/U3D4Z42HG3NPT3GW6AXKJGNAD7","download_json":"https://pith.science/pith/U3D4Z42HG3NPT3GW6AXKJGNAD7.json","view_paper":"https://pith.science/paper/U3D4Z42H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.22514&json=true","fetch_graph":"https://pith.science/api/pith-number/U3D4Z42HG3NPT3GW6AXKJGNAD7/graph.json","fetch_events":"https://pith.science/api/pith-number/U3D4Z42HG3NPT3GW6AXKJGNAD7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U3D4Z42HG3NPT3GW6AXKJGNAD7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U3D4Z42HG3NPT3GW6AXKJGNAD7/action/storage_attestation","attest_author":"https://pith.science/pith/U3D4Z42HG3NPT3GW6AXKJGNAD7/action/author_attestation","sign_citation":"https://pith.science/pith/U3D4Z42HG3NPT3GW6AXKJGNAD7/action/citation_signature","submit_replication":"https://pith.science/pith/U3D4Z42HG3NPT3GW6AXKJGNAD7/action/replication_record"}},"created_at":"2026-07-05T11:45:43.677128+00:00","updated_at":"2026-07-05T11:45:43.677128+00:00"}