{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NPSMBVNCJHODFJEZD3PZUFLC7X","short_pith_number":"pith:NPSMBVNC","schema_version":"1.0","canonical_sha256":"6be4c0d5a249dc32a4991edf9a1562fdc43d0ee46f3b2a01e1b847e04b2a8c33","source":{"kind":"arxiv","id":"2507.09982","version":1},"attestation_state":"computed","paper":{"title":"TextOmics-Guided Diffusion for Hit-like Molecular Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Li, Hang Yuan, Wenjun Ma, Yuncheng Jiang","submitted_at":"2025-07-14T06:56:37Z","abstract_excerpt":"Hit-like molecular generation with therapeutic potential is essential for target-specific drug discovery. However, the field lacks heterogeneous data and unified frameworks for integrating diverse molecular representations. To bridge this gap, we introduce TextOmics, a pioneering benchmark that establishes one-to-one correspondences between omics expressions and molecular textual descriptions. TextOmics provides a heterogeneous dataset that facilitates molecular generation through representations alignment. Built upon this foundation, we propose ToDi, a generative framework that jointly condit"},"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":"2507.09982","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-14T06:56:37Z","cross_cats_sorted":[],"title_canon_sha256":"eb57457560e2b394342a7c65b27dcba2aa93673e4072e35c403943abe52f9487","abstract_canon_sha256":"22581480570cf47e8d26bf33964ebc10aad207f96be0a4f6ae421e6413e9bdd8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:43.248152Z","signature_b64":"0BH2GuPgkIkiJ5MTSfNtZU3VsLiQkDMdczOsLTTJH19cexFTRxqOTrcwDNtynhzuLAi23wj52khNqLbI+W7gCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6be4c0d5a249dc32a4991edf9a1562fdc43d0ee46f3b2a01e1b847e04b2a8c33","last_reissued_at":"2026-07-05T11:36:43.247730Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:43.247730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TextOmics-Guided Diffusion for Hit-like Molecular Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Li, Hang Yuan, Wenjun Ma, Yuncheng Jiang","submitted_at":"2025-07-14T06:56:37Z","abstract_excerpt":"Hit-like molecular generation with therapeutic potential is essential for target-specific drug discovery. However, the field lacks heterogeneous data and unified frameworks for integrating diverse molecular representations. To bridge this gap, we introduce TextOmics, a pioneering benchmark that establishes one-to-one correspondences between omics expressions and molecular textual descriptions. TextOmics provides a heterogeneous dataset that facilitates molecular generation through representations alignment. Built upon this foundation, we propose ToDi, a generative framework that jointly condit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09982","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/2507.09982/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":"2507.09982","created_at":"2026-07-05T11:36:43.247795+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.09982v1","created_at":"2026-07-05T11:36:43.247795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09982","created_at":"2026-07-05T11:36:43.247795+00:00"},{"alias_kind":"pith_short_12","alias_value":"NPSMBVNCJHOD","created_at":"2026-07-05T11:36:43.247795+00:00"},{"alias_kind":"pith_short_16","alias_value":"NPSMBVNCJHODFJEZ","created_at":"2026-07-05T11:36:43.247795+00:00"},{"alias_kind":"pith_short_8","alias_value":"NPSMBVNC","created_at":"2026-07-05T11:36:43.247795+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/NPSMBVNCJHODFJEZD3PZUFLC7X","json":"https://pith.science/pith/NPSMBVNCJHODFJEZD3PZUFLC7X.json","graph_json":"https://pith.science/api/pith-number/NPSMBVNCJHODFJEZD3PZUFLC7X/graph.json","events_json":"https://pith.science/api/pith-number/NPSMBVNCJHODFJEZD3PZUFLC7X/events.json","paper":"https://pith.science/paper/NPSMBVNC"},"agent_actions":{"view_html":"https://pith.science/pith/NPSMBVNCJHODFJEZD3PZUFLC7X","download_json":"https://pith.science/pith/NPSMBVNCJHODFJEZD3PZUFLC7X.json","view_paper":"https://pith.science/paper/NPSMBVNC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.09982&json=true","fetch_graph":"https://pith.science/api/pith-number/NPSMBVNCJHODFJEZD3PZUFLC7X/graph.json","fetch_events":"https://pith.science/api/pith-number/NPSMBVNCJHODFJEZD3PZUFLC7X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NPSMBVNCJHODFJEZD3PZUFLC7X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NPSMBVNCJHODFJEZD3PZUFLC7X/action/storage_attestation","attest_author":"https://pith.science/pith/NPSMBVNCJHODFJEZD3PZUFLC7X/action/author_attestation","sign_citation":"https://pith.science/pith/NPSMBVNCJHODFJEZD3PZUFLC7X/action/citation_signature","submit_replication":"https://pith.science/pith/NPSMBVNCJHODFJEZD3PZUFLC7X/action/replication_record"}},"created_at":"2026-07-05T11:36:43.247795+00:00","updated_at":"2026-07-05T11:36:43.247795+00:00"}