{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TYHLUMYLVKN5DPVE2D6RZ2OXNV","short_pith_number":"pith:TYHLUMYL","schema_version":"1.0","canonical_sha256":"9e0eba330baa9bd1bea4d0fd1ce9d76d41594d41a2c35846b55b3077d1ae2da4","source":{"kind":"arxiv","id":"2506.00223","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Drug Discovery: Autoencoder-Based Latent Space Augmentation for Improved Molecular Solubility Prediction using LatMixSol","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Mohammad Saleh Hasankhani","submitted_at":"2025-05-30T20:54:57Z","abstract_excerpt":"Accurate prediction of molecular solubility is a cornerstone of early-stage drug discovery, yet conventional machine learning models face significant challenges due to limited labeled data and the high-dimensional nature of molecular descriptors. To address these issues, we propose LatMixSol, a novel latent space augmentation framework that combines autoencoder-based feature compression with guided interpolation to enrich training data. Our approach first encodes molecular descriptors into a low-dimensional latent space using a two-layer autoencoder. Spectral clustering is then applied to grou"},"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":"2506.00223","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-05-30T20:54:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"947119f70f3b91ccf2e6bea1d2a5ed7135bd94e4f76dfcac9fdb106f34238207","abstract_canon_sha256":"c2cd9d0cc5fc01404e9f27b0d7513213351dacc4b93df90290bc7a90a536c7d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:31.176030Z","signature_b64":"fQpRoWyfOad5I0U1vJ/rp07gwvMDGkzzekOViNtklt7e0+xbfX/14wbQBTwHaL/KfBR2QbHRcF9Q4JIm6zjXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e0eba330baa9bd1bea4d0fd1ce9d76d41594d41a2c35846b55b3077d1ae2da4","last_reissued_at":"2026-07-05T11:13:31.175436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:31.175436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Drug Discovery: Autoencoder-Based Latent Space Augmentation for Improved Molecular Solubility Prediction using LatMixSol","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Mohammad Saleh Hasankhani","submitted_at":"2025-05-30T20:54:57Z","abstract_excerpt":"Accurate prediction of molecular solubility is a cornerstone of early-stage drug discovery, yet conventional machine learning models face significant challenges due to limited labeled data and the high-dimensional nature of molecular descriptors. To address these issues, we propose LatMixSol, a novel latent space augmentation framework that combines autoencoder-based feature compression with guided interpolation to enrich training data. Our approach first encodes molecular descriptors into a low-dimensional latent space using a two-layer autoencoder. Spectral clustering is then applied to grou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00223","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/2506.00223/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":"2506.00223","created_at":"2026-07-05T11:13:31.175512+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00223v1","created_at":"2026-07-05T11:13:31.175512+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00223","created_at":"2026-07-05T11:13:31.175512+00:00"},{"alias_kind":"pith_short_12","alias_value":"TYHLUMYLVKN5","created_at":"2026-07-05T11:13:31.175512+00:00"},{"alias_kind":"pith_short_16","alias_value":"TYHLUMYLVKN5DPVE","created_at":"2026-07-05T11:13:31.175512+00:00"},{"alias_kind":"pith_short_8","alias_value":"TYHLUMYL","created_at":"2026-07-05T11:13:31.175512+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/TYHLUMYLVKN5DPVE2D6RZ2OXNV","json":"https://pith.science/pith/TYHLUMYLVKN5DPVE2D6RZ2OXNV.json","graph_json":"https://pith.science/api/pith-number/TYHLUMYLVKN5DPVE2D6RZ2OXNV/graph.json","events_json":"https://pith.science/api/pith-number/TYHLUMYLVKN5DPVE2D6RZ2OXNV/events.json","paper":"https://pith.science/paper/TYHLUMYL"},"agent_actions":{"view_html":"https://pith.science/pith/TYHLUMYLVKN5DPVE2D6RZ2OXNV","download_json":"https://pith.science/pith/TYHLUMYLVKN5DPVE2D6RZ2OXNV.json","view_paper":"https://pith.science/paper/TYHLUMYL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00223&json=true","fetch_graph":"https://pith.science/api/pith-number/TYHLUMYLVKN5DPVE2D6RZ2OXNV/graph.json","fetch_events":"https://pith.science/api/pith-number/TYHLUMYLVKN5DPVE2D6RZ2OXNV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TYHLUMYLVKN5DPVE2D6RZ2OXNV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TYHLUMYLVKN5DPVE2D6RZ2OXNV/action/storage_attestation","attest_author":"https://pith.science/pith/TYHLUMYLVKN5DPVE2D6RZ2OXNV/action/author_attestation","sign_citation":"https://pith.science/pith/TYHLUMYLVKN5DPVE2D6RZ2OXNV/action/citation_signature","submit_replication":"https://pith.science/pith/TYHLUMYLVKN5DPVE2D6RZ2OXNV/action/replication_record"}},"created_at":"2026-07-05T11:13:31.175512+00:00","updated_at":"2026-07-05T11:13:31.175512+00:00"}