{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TYHLUMYLVKN5DPVE2D6RZ2OXNV","short_pith_number":"pith:TYHLUMYL","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"},"canonical_sha256":"9e0eba330baa9bd1bea4d0fd1ce9d76d41594d41a2c35846b55b3077d1ae2da4","source":{"kind":"arxiv","id":"2506.00223","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00223","created_at":"2026-07-05T11:13:31Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00223v1","created_at":"2026-07-05T11:13:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00223","created_at":"2026-07-05T11:13:31Z"},{"alias_kind":"pith_short_12","alias_value":"TYHLUMYLVKN5","created_at":"2026-07-05T11:13:31Z"},{"alias_kind":"pith_short_16","alias_value":"TYHLUMYLVKN5DPVE","created_at":"2026-07-05T11:13:31Z"},{"alias_kind":"pith_short_8","alias_value":"TYHLUMYL","created_at":"2026-07-05T11:13:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TYHLUMYLVKN5DPVE2D6RZ2OXNV","target":"record","payload":{"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"},"canonical_sha256":"9e0eba330baa9bd1bea4d0fd1ce9d76d41594d41a2c35846b55b3077d1ae2da4","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"},"source_kind":"arxiv","source_id":"2506.00223","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:13:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/V7R76bQb09cW2SidGsVy5SfAP8Xeb+e35n1I+Vb4i5fGfN9m6J+VYLUO7CDgOgcsSEYLDtgfs6lF/Z+25bHAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:21:27.403416Z"},"content_sha256":"82e32751de1d6425fc8f5c70a8d3a169f22f2868710657f11ff0d53c0182eab9","schema_version":"1.0","event_id":"sha256:82e32751de1d6425fc8f5c70a8d3a169f22f2868710657f11ff0d53c0182eab9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TYHLUMYLVKN5DPVE2D6RZ2OXNV","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:13:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zIjbmCEtyVltgcLqq2VG9sOTMEquYbhmXcgnMI8CjEmVK7giXAkmhV0rcCP6QpjqauATHFJlSpEx8nZOeeDXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:21:27.404123Z"},"content_sha256":"22a9d93b7c445d7c214966ad5cf6b06400a30a41dd7de4ef37937a6efc8cb8bc","schema_version":"1.0","event_id":"sha256:22a9d93b7c445d7c214966ad5cf6b06400a30a41dd7de4ef37937a6efc8cb8bc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TYHLUMYLVKN5DPVE2D6RZ2OXNV/bundle.json","state_url":"https://pith.science/pith/TYHLUMYLVKN5DPVE2D6RZ2OXNV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TYHLUMYLVKN5DPVE2D6RZ2OXNV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T01:21:27Z","links":{"resolver":"https://pith.science/pith/TYHLUMYLVKN5DPVE2D6RZ2OXNV","bundle":"https://pith.science/pith/TYHLUMYLVKN5DPVE2D6RZ2OXNV/bundle.json","state":"https://pith.science/pith/TYHLUMYLVKN5DPVE2D6RZ2OXNV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TYHLUMYLVKN5DPVE2D6RZ2OXNV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TYHLUMYLVKN5DPVE2D6RZ2OXNV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c2cd9d0cc5fc01404e9f27b0d7513213351dacc4b93df90290bc7a90a536c7d9","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-05-30T20:54:57Z","title_canon_sha256":"947119f70f3b91ccf2e6bea1d2a5ed7135bd94e4f76dfcac9fdb106f34238207"},"schema_version":"1.0","source":{"id":"2506.00223","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00223","created_at":"2026-07-05T11:13:31Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00223v1","created_at":"2026-07-05T11:13:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00223","created_at":"2026-07-05T11:13:31Z"},{"alias_kind":"pith_short_12","alias_value":"TYHLUMYLVKN5","created_at":"2026-07-05T11:13:31Z"},{"alias_kind":"pith_short_16","alias_value":"TYHLUMYLVKN5DPVE","created_at":"2026-07-05T11:13:31Z"},{"alias_kind":"pith_short_8","alias_value":"TYHLUMYL","created_at":"2026-07-05T11:13:31Z"}],"graph_snapshots":[{"event_id":"sha256:22a9d93b7c445d7c214966ad5cf6b06400a30a41dd7de4ef37937a6efc8cb8bc","target":"graph","created_at":"2026-07-05T11:13:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.00223/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Mohammad Saleh Hasankhani","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-05-30T20:54:57Z","title":"Enhancing Drug Discovery: Autoencoder-Based Latent Space Augmentation for Improved Molecular Solubility Prediction using LatMixSol"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00223","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:82e32751de1d6425fc8f5c70a8d3a169f22f2868710657f11ff0d53c0182eab9","target":"record","created_at":"2026-07-05T11:13:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c2cd9d0cc5fc01404e9f27b0d7513213351dacc4b93df90290bc7a90a536c7d9","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-05-30T20:54:57Z","title_canon_sha256":"947119f70f3b91ccf2e6bea1d2a5ed7135bd94e4f76dfcac9fdb106f34238207"},"schema_version":"1.0","source":{"id":"2506.00223","kind":"arxiv","version":1}},"canonical_sha256":"9e0eba330baa9bd1bea4d0fd1ce9d76d41594d41a2c35846b55b3077d1ae2da4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e0eba330baa9bd1bea4d0fd1ce9d76d41594d41a2c35846b55b3077d1ae2da4","first_computed_at":"2026-07-05T11:13:31.175436Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:31.175436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fQpRoWyfOad5I0U1vJ/rp07gwvMDGkzzekOViNtklt7e0+xbfX/14wbQBTwHaL/KfBR2QbHRcF9Q4JIm6zjXCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:31.176030Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00223","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82e32751de1d6425fc8f5c70a8d3a169f22f2868710657f11ff0d53c0182eab9","sha256:22a9d93b7c445d7c214966ad5cf6b06400a30a41dd7de4ef37937a6efc8cb8bc"],"state_sha256":"c0bc2d6243bfcdcc22e5a7b3f672336e884f35188f4b4396a238d07b88b486f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O70B1DzoGQ7CgLEcMr/yoPn6zFVskDis8UOxkJ0pFcM68h4GtmJ3Th9QQMUHIMEm4ngjZ240tT0g5y7WMEuJDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T01:21:27.409763Z","bundle_sha256":"40562e127ef12c17d85aba64b96b55a9cea66f0abcb78b96674c389fea14d5e7"}}