{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DYLOAVRYWQ2UEUXWYXPDFTNQJI","short_pith_number":"pith:DYLOAVRY","schema_version":"1.0","canonical_sha256":"1e16e05638b4354252f6c5de32cdb04a2946048a80d04c8a3c8e240d98f69cb3","source":{"kind":"arxiv","id":"2411.01401","version":1},"attestation_state":"computed","paper":{"title":"Pre-trained Molecular Language Models with Random Functional Group Masking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","physics.chem-ph"],"primary_cat":"q-bio.BM","authors_text":"Haoyi Xiong, Jiang Bian, Linghe Kong, Ning Sui, Shahid Mumtaz, Tianhao Peng, Xuhong Li, Yanwu Xu, Yuchen Li, Zeke Xie","submitted_at":"2024-11-03T01:56:15Z","abstract_excerpt":"Recent advancements in computational chemistry have leveraged the power of trans-former-based language models, such as MoLFormer, pre-trained using a vast amount of simplified molecular-input line-entry system (SMILES) sequences, to understand and predict molecular properties and activities, a critical step in fields like drug discovery and materials science. To further improve performance, researchers have introduced graph neural networks with graph-based molecular representations, such as GEM, incorporating the topology, geometry, 2D or even 3D structures of molecules into pre-training. Whil"},"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":"2411.01401","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2024-11-03T01:56:15Z","cross_cats_sorted":["cs.AI","cs.LG","physics.chem-ph"],"title_canon_sha256":"acdd48e915ff946f2f8e9086082c4bcf6b64fdbbcdfbcfc7e94ba969d64cd662","abstract_canon_sha256":"7fcd301153b6ccfc87c0cc3daf22213b8a152717641db90224eb2b70c48bd11e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:29.779304Z","signature_b64":"qkI58QUqXp6JJews1m5vsFr6yx3zfpPImXlNfDtHWovBi3bqh0zRg5nJ43XtFjqhRwOk8AujWZy4fEzeyR2QCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e16e05638b4354252f6c5de32cdb04a2946048a80d04c8a3c8e240d98f69cb3","last_reissued_at":"2026-07-05T09:30:29.778853Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:29.778853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pre-trained Molecular Language Models with Random Functional Group Masking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","physics.chem-ph"],"primary_cat":"q-bio.BM","authors_text":"Haoyi Xiong, Jiang Bian, Linghe Kong, Ning Sui, Shahid Mumtaz, Tianhao Peng, Xuhong Li, Yanwu Xu, Yuchen Li, Zeke Xie","submitted_at":"2024-11-03T01:56:15Z","abstract_excerpt":"Recent advancements in computational chemistry have leveraged the power of trans-former-based language models, such as MoLFormer, pre-trained using a vast amount of simplified molecular-input line-entry system (SMILES) sequences, to understand and predict molecular properties and activities, a critical step in fields like drug discovery and materials science. To further improve performance, researchers have introduced graph neural networks with graph-based molecular representations, such as GEM, incorporating the topology, geometry, 2D or even 3D structures of molecules into pre-training. Whil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01401","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/2411.01401/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":"2411.01401","created_at":"2026-07-05T09:30:29.778911+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.01401v1","created_at":"2026-07-05T09:30:29.778911+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01401","created_at":"2026-07-05T09:30:29.778911+00:00"},{"alias_kind":"pith_short_12","alias_value":"DYLOAVRYWQ2U","created_at":"2026-07-05T09:30:29.778911+00:00"},{"alias_kind":"pith_short_16","alias_value":"DYLOAVRYWQ2UEUXW","created_at":"2026-07-05T09:30:29.778911+00:00"},{"alias_kind":"pith_short_8","alias_value":"DYLOAVRY","created_at":"2026-07-05T09:30:29.778911+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/DYLOAVRYWQ2UEUXWYXPDFTNQJI","json":"https://pith.science/pith/DYLOAVRYWQ2UEUXWYXPDFTNQJI.json","graph_json":"https://pith.science/api/pith-number/DYLOAVRYWQ2UEUXWYXPDFTNQJI/graph.json","events_json":"https://pith.science/api/pith-number/DYLOAVRYWQ2UEUXWYXPDFTNQJI/events.json","paper":"https://pith.science/paper/DYLOAVRY"},"agent_actions":{"view_html":"https://pith.science/pith/DYLOAVRYWQ2UEUXWYXPDFTNQJI","download_json":"https://pith.science/pith/DYLOAVRYWQ2UEUXWYXPDFTNQJI.json","view_paper":"https://pith.science/paper/DYLOAVRY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.01401&json=true","fetch_graph":"https://pith.science/api/pith-number/DYLOAVRYWQ2UEUXWYXPDFTNQJI/graph.json","fetch_events":"https://pith.science/api/pith-number/DYLOAVRYWQ2UEUXWYXPDFTNQJI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DYLOAVRYWQ2UEUXWYXPDFTNQJI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DYLOAVRYWQ2UEUXWYXPDFTNQJI/action/storage_attestation","attest_author":"https://pith.science/pith/DYLOAVRYWQ2UEUXWYXPDFTNQJI/action/author_attestation","sign_citation":"https://pith.science/pith/DYLOAVRYWQ2UEUXWYXPDFTNQJI/action/citation_signature","submit_replication":"https://pith.science/pith/DYLOAVRYWQ2UEUXWYXPDFTNQJI/action/replication_record"}},"created_at":"2026-07-05T09:30:29.778911+00:00","updated_at":"2026-07-05T09:30:29.778911+00:00"}