{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GV2OKTLOUZGTJXOFB5PVS7HPOR","short_pith_number":"pith:GV2OKTLO","schema_version":"1.0","canonical_sha256":"3574e54d6ea64d34ddc50f5f597cef747a64ead0ee7becae02dec31f647874cc","source":{"kind":"arxiv","id":"2401.16771","version":1},"attestation_state":"computed","paper":{"title":"MolPLA: A Molecular Pretraining Framework for Learning Cores, R-Groups and their Linker Joints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jaewoo Kang, Jueon Park, Junhyun Lee, Mogan Gim, Ngoc-Quang Nguyen, Sanghoon Lee, Seungheun Baek, Soyon Park","submitted_at":"2024-01-30T06:20:08Z","abstract_excerpt":"Molecular core structures and R-groups are essential concepts in drug development. Integration of these concepts with conventional graph pre-training approaches can promote deeper understanding in molecules. We propose MolPLA, a novel pre-training framework that employs masked graph contrastive learning in understanding the underlying decomposable parts inmolecules that implicate their core structure and peripheral R-groups. Furthermore, we formulate an additional framework that grants MolPLA the ability to help chemists find replaceable R-groups in lead optimization scenarios. Experimental re"},"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":"2401.16771","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-30T06:20:08Z","cross_cats_sorted":[],"title_canon_sha256":"0d14eb895c71d2a16ef91acab646531011440612b942468f407135fbd67b661c","abstract_canon_sha256":"e0c73425b046a70898b740a8e668d887f1053634cb2068121f1116716e2c1454"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:59.851624Z","signature_b64":"rX1r6ADxyvfjMtZ5kmISdsGlTdCv2ynAapM2TxOSH1TkR0IY5IQ/X4+OBAcZxtIBvwuB85avbVhSodwY+/7YDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3574e54d6ea64d34ddc50f5f597cef747a64ead0ee7becae02dec31f647874cc","last_reissued_at":"2026-07-05T07:38:59.851129Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:59.851129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MolPLA: A Molecular Pretraining Framework for Learning Cores, R-Groups and their Linker Joints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jaewoo Kang, Jueon Park, Junhyun Lee, Mogan Gim, Ngoc-Quang Nguyen, Sanghoon Lee, Seungheun Baek, Soyon Park","submitted_at":"2024-01-30T06:20:08Z","abstract_excerpt":"Molecular core structures and R-groups are essential concepts in drug development. Integration of these concepts with conventional graph pre-training approaches can promote deeper understanding in molecules. We propose MolPLA, a novel pre-training framework that employs masked graph contrastive learning in understanding the underlying decomposable parts inmolecules that implicate their core structure and peripheral R-groups. Furthermore, we formulate an additional framework that grants MolPLA the ability to help chemists find replaceable R-groups in lead optimization scenarios. Experimental re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.16771","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/2401.16771/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":"2401.16771","created_at":"2026-07-05T07:38:59.851194+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.16771v1","created_at":"2026-07-05T07:38:59.851194+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.16771","created_at":"2026-07-05T07:38:59.851194+00:00"},{"alias_kind":"pith_short_12","alias_value":"GV2OKTLOUZGT","created_at":"2026-07-05T07:38:59.851194+00:00"},{"alias_kind":"pith_short_16","alias_value":"GV2OKTLOUZGTJXOF","created_at":"2026-07-05T07:38:59.851194+00:00"},{"alias_kind":"pith_short_8","alias_value":"GV2OKTLO","created_at":"2026-07-05T07:38:59.851194+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/GV2OKTLOUZGTJXOFB5PVS7HPOR","json":"https://pith.science/pith/GV2OKTLOUZGTJXOFB5PVS7HPOR.json","graph_json":"https://pith.science/api/pith-number/GV2OKTLOUZGTJXOFB5PVS7HPOR/graph.json","events_json":"https://pith.science/api/pith-number/GV2OKTLOUZGTJXOFB5PVS7HPOR/events.json","paper":"https://pith.science/paper/GV2OKTLO"},"agent_actions":{"view_html":"https://pith.science/pith/GV2OKTLOUZGTJXOFB5PVS7HPOR","download_json":"https://pith.science/pith/GV2OKTLOUZGTJXOFB5PVS7HPOR.json","view_paper":"https://pith.science/paper/GV2OKTLO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.16771&json=true","fetch_graph":"https://pith.science/api/pith-number/GV2OKTLOUZGTJXOFB5PVS7HPOR/graph.json","fetch_events":"https://pith.science/api/pith-number/GV2OKTLOUZGTJXOFB5PVS7HPOR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GV2OKTLOUZGTJXOFB5PVS7HPOR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GV2OKTLOUZGTJXOFB5PVS7HPOR/action/storage_attestation","attest_author":"https://pith.science/pith/GV2OKTLOUZGTJXOFB5PVS7HPOR/action/author_attestation","sign_citation":"https://pith.science/pith/GV2OKTLOUZGTJXOFB5PVS7HPOR/action/citation_signature","submit_replication":"https://pith.science/pith/GV2OKTLOUZGTJXOFB5PVS7HPOR/action/replication_record"}},"created_at":"2026-07-05T07:38:59.851194+00:00","updated_at":"2026-07-05T07:38:59.851194+00:00"}