{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NFFW33XT7CURNRDHFGOYWKXWRS","short_pith_number":"pith:NFFW33XT","schema_version":"1.0","canonical_sha256":"694b6deef3f8a916c467299d8b2af68c8555ba3aa211c0c1f973d94fa3df9362","source":{"kind":"arxiv","id":"2210.07145","version":1},"attestation_state":"computed","paper":{"title":"Accurate, reliable and interpretable solubility prediction of druglike molecules with attention pooling and Bayesian learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Seongok Ryu, Sumin Lee","submitted_at":"2022-09-29T07:48:10Z","abstract_excerpt":"In drug discovery, aqueous solubility is an important pharmacokinetic property which affects absorption and assay availability of drug. Thus, in silico prediction of solubility has been studied for its utility in virtual screening and lead optimization. Recently, machine learning (ML) methods using experimental data has been popular because physics-based methods like quantum mechanics and molecular dynamics are not suitable for high-throughput tasks due to its computational costs. However, ML method can exhibit over-fitting problem in a data-deficient condition, and this is the case for most c"},"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":"2210.07145","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2022-09-29T07:48:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"789494da71b7f7c0f7d205de5a5f6bea1dda6be721ecb16fe34ca42b63bfbf0b","abstract_canon_sha256":"7132294ebc538a75e41297eebfac051a7064e8e38a3364ea8474d90548154b69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:24.971024Z","signature_b64":"l4j7AXjgq1SoC6/N1HBdXAwYax/Up7woDkASgy8tB1F8Xfz0qarvGqCH1l3B5gdb37i6eAjpNF9zY+OmEzMEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"694b6deef3f8a916c467299d8b2af68c8555ba3aa211c0c1f973d94fa3df9362","last_reissued_at":"2026-07-05T05:06:24.970608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:24.970608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accurate, reliable and interpretable solubility prediction of druglike molecules with attention pooling and Bayesian learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Seongok Ryu, Sumin Lee","submitted_at":"2022-09-29T07:48:10Z","abstract_excerpt":"In drug discovery, aqueous solubility is an important pharmacokinetic property which affects absorption and assay availability of drug. Thus, in silico prediction of solubility has been studied for its utility in virtual screening and lead optimization. Recently, machine learning (ML) methods using experimental data has been popular because physics-based methods like quantum mechanics and molecular dynamics are not suitable for high-throughput tasks due to its computational costs. However, ML method can exhibit over-fitting problem in a data-deficient condition, and this is the case for most c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.07145","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/2210.07145/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":"2210.07145","created_at":"2026-07-05T05:06:24.970663+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.07145v1","created_at":"2026-07-05T05:06:24.970663+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.07145","created_at":"2026-07-05T05:06:24.970663+00:00"},{"alias_kind":"pith_short_12","alias_value":"NFFW33XT7CUR","created_at":"2026-07-05T05:06:24.970663+00:00"},{"alias_kind":"pith_short_16","alias_value":"NFFW33XT7CURNRDH","created_at":"2026-07-05T05:06:24.970663+00:00"},{"alias_kind":"pith_short_8","alias_value":"NFFW33XT","created_at":"2026-07-05T05:06:24.970663+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.00223","citing_title":"Enhancing Drug Discovery: Autoencoder-Based Latent Space Augmentation for Improved Molecular Solubility Prediction using LatMixSol","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NFFW33XT7CURNRDHFGOYWKXWRS","json":"https://pith.science/pith/NFFW33XT7CURNRDHFGOYWKXWRS.json","graph_json":"https://pith.science/api/pith-number/NFFW33XT7CURNRDHFGOYWKXWRS/graph.json","events_json":"https://pith.science/api/pith-number/NFFW33XT7CURNRDHFGOYWKXWRS/events.json","paper":"https://pith.science/paper/NFFW33XT"},"agent_actions":{"view_html":"https://pith.science/pith/NFFW33XT7CURNRDHFGOYWKXWRS","download_json":"https://pith.science/pith/NFFW33XT7CURNRDHFGOYWKXWRS.json","view_paper":"https://pith.science/paper/NFFW33XT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.07145&json=true","fetch_graph":"https://pith.science/api/pith-number/NFFW33XT7CURNRDHFGOYWKXWRS/graph.json","fetch_events":"https://pith.science/api/pith-number/NFFW33XT7CURNRDHFGOYWKXWRS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NFFW33XT7CURNRDHFGOYWKXWRS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NFFW33XT7CURNRDHFGOYWKXWRS/action/storage_attestation","attest_author":"https://pith.science/pith/NFFW33XT7CURNRDHFGOYWKXWRS/action/author_attestation","sign_citation":"https://pith.science/pith/NFFW33XT7CURNRDHFGOYWKXWRS/action/citation_signature","submit_replication":"https://pith.science/pith/NFFW33XT7CURNRDHFGOYWKXWRS/action/replication_record"}},"created_at":"2026-07-05T05:06:24.970663+00:00","updated_at":"2026-07-05T05:06:24.970663+00:00"}