{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ILM4QR7CXAKE3QSKKKN5PKEYUO","short_pith_number":"pith:ILM4QR7C","schema_version":"1.0","canonical_sha256":"42d9c847e2b8144dc24a529bd7a898a3a27d2c494b63b9059adc9d2c777235ec","source":{"kind":"arxiv","id":"2505.20131","version":1},"attestation_state":"computed","paper":{"title":"MolEditRL: Structure-Preserving Molecular Editing via Discrete Diffusion and Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Dazhong Shen, Ying Sun, Yuanxin Zhuang","submitted_at":"2025-05-26T15:29:08Z","abstract_excerpt":"Molecular editing aims to modify a given molecule to optimize desired chemical properties while preserving structural similarity. However, current approaches typically rely on string-based or continuous representations, which fail to adequately capture the discrete, graph-structured nature of molecules, resulting in limited structural fidelity and poor controllability. In this paper, we propose MolEditRL, a molecular editing framework that explicitly integrates structural constraints with precise property optimization. Specifically, MolEditRL consists of two stages: (1) a discrete graph diffus"},"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":"2505.20131","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T15:29:08Z","cross_cats_sorted":["q-bio.QM"],"title_canon_sha256":"1638d66516552f4b83d93f9f444248b892066980f525fe725cd986bd9c6ecda5","abstract_canon_sha256":"350766f39fb47d8b97a314837a5095b0312b4a8114cea7a6377574c1fba33da5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:53.000243Z","signature_b64":"5oGNsfii8wVoceEos39gOX9E3/cXBpEImAltBnEwJvk2z9XR6tfp7tC+BZFBnEFSbA0eZUChvJdNtKb56bV2AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42d9c847e2b8144dc24a529bd7a898a3a27d2c494b63b9059adc9d2c777235ec","last_reissued_at":"2026-07-05T11:09:52.999785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:52.999785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MolEditRL: Structure-Preserving Molecular Editing via Discrete Diffusion and Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Dazhong Shen, Ying Sun, Yuanxin Zhuang","submitted_at":"2025-05-26T15:29:08Z","abstract_excerpt":"Molecular editing aims to modify a given molecule to optimize desired chemical properties while preserving structural similarity. However, current approaches typically rely on string-based or continuous representations, which fail to adequately capture the discrete, graph-structured nature of molecules, resulting in limited structural fidelity and poor controllability. In this paper, we propose MolEditRL, a molecular editing framework that explicitly integrates structural constraints with precise property optimization. Specifically, MolEditRL consists of two stages: (1) a discrete graph diffus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20131","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/2505.20131/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":"2505.20131","created_at":"2026-07-05T11:09:52.999846+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20131v1","created_at":"2026-07-05T11:09:52.999846+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20131","created_at":"2026-07-05T11:09:52.999846+00:00"},{"alias_kind":"pith_short_12","alias_value":"ILM4QR7CXAKE","created_at":"2026-07-05T11:09:52.999846+00:00"},{"alias_kind":"pith_short_16","alias_value":"ILM4QR7CXAKE3QSK","created_at":"2026-07-05T11:09:52.999846+00:00"},{"alias_kind":"pith_short_8","alias_value":"ILM4QR7C","created_at":"2026-07-05T11:09:52.999846+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10831","citing_title":"SLIM: Sparse Latent Steering for Interpretable and Property-Directed LLM-Based Molecular Editing","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ILM4QR7CXAKE3QSKKKN5PKEYUO","json":"https://pith.science/pith/ILM4QR7CXAKE3QSKKKN5PKEYUO.json","graph_json":"https://pith.science/api/pith-number/ILM4QR7CXAKE3QSKKKN5PKEYUO/graph.json","events_json":"https://pith.science/api/pith-number/ILM4QR7CXAKE3QSKKKN5PKEYUO/events.json","paper":"https://pith.science/paper/ILM4QR7C"},"agent_actions":{"view_html":"https://pith.science/pith/ILM4QR7CXAKE3QSKKKN5PKEYUO","download_json":"https://pith.science/pith/ILM4QR7CXAKE3QSKKKN5PKEYUO.json","view_paper":"https://pith.science/paper/ILM4QR7C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20131&json=true","fetch_graph":"https://pith.science/api/pith-number/ILM4QR7CXAKE3QSKKKN5PKEYUO/graph.json","fetch_events":"https://pith.science/api/pith-number/ILM4QR7CXAKE3QSKKKN5PKEYUO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ILM4QR7CXAKE3QSKKKN5PKEYUO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ILM4QR7CXAKE3QSKKKN5PKEYUO/action/storage_attestation","attest_author":"https://pith.science/pith/ILM4QR7CXAKE3QSKKKN5PKEYUO/action/author_attestation","sign_citation":"https://pith.science/pith/ILM4QR7CXAKE3QSKKKN5PKEYUO/action/citation_signature","submit_replication":"https://pith.science/pith/ILM4QR7CXAKE3QSKKKN5PKEYUO/action/replication_record"}},"created_at":"2026-07-05T11:09:52.999846+00:00","updated_at":"2026-07-05T11:09:52.999846+00:00"}