{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JUNM3E7XT5WZADNEY66H4SU2SU","short_pith_number":"pith:JUNM3E7X","schema_version":"1.0","canonical_sha256":"4d1acd93f79f6d900da4c7bc7e4a9a951c02e1f81461fe5d5f943db216209cd0","source":{"kind":"arxiv","id":"2608.01734","version":1},"attestation_state":"computed","paper":{"title":"LLM-Guided Retrieval for Prediction of Molecular Perturbation Responses","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Betty Xiong, Gabriele Scalia, Jan-Christian Huetter, Sepideh Maleki, Tommaso Biancalani","submitted_at":"2026-08-03T05:57:02Z","abstract_excerpt":"Predicting transcriptomic responses to small-molecule perturbations across cell lines is central to drug discovery, but exhaustive profiling of drug-cell combinations is infeasible. We frame molecular perturbation prediction as retrieve-and-aggregate: approximate an unmeasured drug's response in a cell line by aggregating measured responses of a small set of biologically related compounds. We propose LLM-Guided Retrieval (LGR), where a large language model (LLM) ranks candidate neighbor drugs (restricted to those profiled in the target cell line); after which a fixed mean aggregator combines 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":"2608.01734","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-03T05:57:02Z","cross_cats_sorted":[],"title_canon_sha256":"be4f3c17100535741c630d15aa493b70b9c88876ca570d9a9fdbb35405ad24ec","abstract_canon_sha256":"e2aeac7e862ff89ee9c27fd0e6afa3d569d776d6526685c67ab7d8ff3811a04e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:06:38.615179Z","signature_b64":"8bX+HFi3F80gpeWTBJyhMG9CSf0ZU8QSi8Zw2SxkX4jfLJJG11WV1MaxHqJ0tyarX0CcoFJXl6obRz7v5NPZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d1acd93f79f6d900da4c7bc7e4a9a951c02e1f81461fe5d5f943db216209cd0","last_reissued_at":"2026-08-04T02:06:38.613660Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:06:38.613660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-Guided Retrieval for Prediction of Molecular Perturbation Responses","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Betty Xiong, Gabriele Scalia, Jan-Christian Huetter, Sepideh Maleki, Tommaso Biancalani","submitted_at":"2026-08-03T05:57:02Z","abstract_excerpt":"Predicting transcriptomic responses to small-molecule perturbations across cell lines is central to drug discovery, but exhaustive profiling of drug-cell combinations is infeasible. We frame molecular perturbation prediction as retrieve-and-aggregate: approximate an unmeasured drug's response in a cell line by aggregating measured responses of a small set of biologically related compounds. We propose LLM-Guided Retrieval (LGR), where a large language model (LLM) ranks candidate neighbor drugs (restricted to those profiled in the target cell line); after which a fixed mean aggregator combines t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01734","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/2608.01734/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":"2608.01734","created_at":"2026-08-04T02:06:38.615130+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01734v1","created_at":"2026-08-04T02:06:38.615130+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01734","created_at":"2026-08-04T02:06:38.615130+00:00"},{"alias_kind":"pith_short_12","alias_value":"JUNM3E7XT5WZ","created_at":"2026-08-04T02:06:38.615130+00:00"},{"alias_kind":"pith_short_16","alias_value":"JUNM3E7XT5WZADNE","created_at":"2026-08-04T02:06:38.615130+00:00"},{"alias_kind":"pith_short_8","alias_value":"JUNM3E7X","created_at":"2026-08-04T02:06:38.615130+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/JUNM3E7XT5WZADNEY66H4SU2SU","json":"https://pith.science/pith/JUNM3E7XT5WZADNEY66H4SU2SU.json","graph_json":"https://pith.science/api/pith-number/JUNM3E7XT5WZADNEY66H4SU2SU/graph.json","events_json":"https://pith.science/api/pith-number/JUNM3E7XT5WZADNEY66H4SU2SU/events.json","paper":"https://pith.science/paper/JUNM3E7X"},"agent_actions":{"view_html":"https://pith.science/pith/JUNM3E7XT5WZADNEY66H4SU2SU","download_json":"https://pith.science/pith/JUNM3E7XT5WZADNEY66H4SU2SU.json","view_paper":"https://pith.science/paper/JUNM3E7X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01734&json=true","fetch_graph":"https://pith.science/api/pith-number/JUNM3E7XT5WZADNEY66H4SU2SU/graph.json","fetch_events":"https://pith.science/api/pith-number/JUNM3E7XT5WZADNEY66H4SU2SU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JUNM3E7XT5WZADNEY66H4SU2SU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JUNM3E7XT5WZADNEY66H4SU2SU/action/storage_attestation","attest_author":"https://pith.science/pith/JUNM3E7XT5WZADNEY66H4SU2SU/action/author_attestation","sign_citation":"https://pith.science/pith/JUNM3E7XT5WZADNEY66H4SU2SU/action/citation_signature","submit_replication":"https://pith.science/pith/JUNM3E7XT5WZADNEY66H4SU2SU/action/replication_record"}},"created_at":"2026-08-04T02:06:38.615130+00:00","updated_at":"2026-08-04T02:06:38.615130+00:00"}