{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WTGSW4APDEPICW4ITAD4B5J4TZ","short_pith_number":"pith:WTGSW4AP","schema_version":"1.0","canonical_sha256":"b4cd2b700f191e815b889807c0f53c9e6ef6e09f6e21a2e64b0e8eed6e21cb72","source":{"kind":"arxiv","id":"2508.01799","version":2},"attestation_state":"computed","paper":{"title":"Contrastive Multi-Task Learning with Solvent-Aware Augmentation for Drug Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Gerald W.Y. Cheng, Hexiao Ding, Hongzhao Chen, Jing Cai, Jing Lan, Jung Sun Yoo, Liang-ting Lin, Nga-Chun Ng, Yufeng Jiang, Zongxi Li","submitted_at":"2025-08-03T15:25:42Z","abstract_excerpt":"Accurate prediction of protein-ligand interactions is essential for computer-aided drug discovery. However, existing methods often fail to capture solvent-dependent conformational changes and lack the ability to jointly learn multiple related tasks. To address these limitations, we introduce a pre-training method that incorporates ligand conformational ensembles generated under diverse solvent conditions as augmented input. This design enables the model to learn both structural flexibility and environmental context in a unified manner. The training process integrates molecular reconstruction t"},"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":"2508.01799","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-08-03T15:25:42Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"26db77719debdde7579c35bbbf30f785767aeb8a01725c3c97319cef254caf22","abstract_canon_sha256":"1e7268d4ac0e379bab73d33137fdf6764ccffe7768f1ff25e30a3e9e786a6ed5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:07.312422Z","signature_b64":"kai4Y/8APLHT/HzwigLfgxOVbAPtIJ4ne7wpSWOqL9d6nAuGeowQIg0LM55+D6z4ecFjKk9LcvtU+e4T7apUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4cd2b700f191e815b889807c0f53c9e6ef6e09f6e21a2e64b0e8eed6e21cb72","last_reissued_at":"2026-07-05T12:00:07.311905Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:07.311905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Multi-Task Learning with Solvent-Aware Augmentation for Drug Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Gerald W.Y. Cheng, Hexiao Ding, Hongzhao Chen, Jing Cai, Jing Lan, Jung Sun Yoo, Liang-ting Lin, Nga-Chun Ng, Yufeng Jiang, Zongxi Li","submitted_at":"2025-08-03T15:25:42Z","abstract_excerpt":"Accurate prediction of protein-ligand interactions is essential for computer-aided drug discovery. However, existing methods often fail to capture solvent-dependent conformational changes and lack the ability to jointly learn multiple related tasks. To address these limitations, we introduce a pre-training method that incorporates ligand conformational ensembles generated under diverse solvent conditions as augmented input. This design enables the model to learn both structural flexibility and environmental context in a unified manner. The training process integrates molecular reconstruction t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01799","kind":"arxiv","version":2},"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/2508.01799/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":"2508.01799","created_at":"2026-07-05T12:00:07.311968+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.01799v2","created_at":"2026-07-05T12:00:07.311968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01799","created_at":"2026-07-05T12:00:07.311968+00:00"},{"alias_kind":"pith_short_12","alias_value":"WTGSW4APDEPI","created_at":"2026-07-05T12:00:07.311968+00:00"},{"alias_kind":"pith_short_16","alias_value":"WTGSW4APDEPICW4I","created_at":"2026-07-05T12:00:07.311968+00:00"},{"alias_kind":"pith_short_8","alias_value":"WTGSW4AP","created_at":"2026-07-05T12:00:07.311968+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22307","citing_title":"Enhancing Protein Representation Learning via Manifold Restore Mixing","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WTGSW4APDEPICW4ITAD4B5J4TZ","json":"https://pith.science/pith/WTGSW4APDEPICW4ITAD4B5J4TZ.json","graph_json":"https://pith.science/api/pith-number/WTGSW4APDEPICW4ITAD4B5J4TZ/graph.json","events_json":"https://pith.science/api/pith-number/WTGSW4APDEPICW4ITAD4B5J4TZ/events.json","paper":"https://pith.science/paper/WTGSW4AP"},"agent_actions":{"view_html":"https://pith.science/pith/WTGSW4APDEPICW4ITAD4B5J4TZ","download_json":"https://pith.science/pith/WTGSW4APDEPICW4ITAD4B5J4TZ.json","view_paper":"https://pith.science/paper/WTGSW4AP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.01799&json=true","fetch_graph":"https://pith.science/api/pith-number/WTGSW4APDEPICW4ITAD4B5J4TZ/graph.json","fetch_events":"https://pith.science/api/pith-number/WTGSW4APDEPICW4ITAD4B5J4TZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WTGSW4APDEPICW4ITAD4B5J4TZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WTGSW4APDEPICW4ITAD4B5J4TZ/action/storage_attestation","attest_author":"https://pith.science/pith/WTGSW4APDEPICW4ITAD4B5J4TZ/action/author_attestation","sign_citation":"https://pith.science/pith/WTGSW4APDEPICW4ITAD4B5J4TZ/action/citation_signature","submit_replication":"https://pith.science/pith/WTGSW4APDEPICW4ITAD4B5J4TZ/action/replication_record"}},"created_at":"2026-07-05T12:00:07.311968+00:00","updated_at":"2026-07-05T12:00:07.311968+00:00"}