{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5XUFCDXQF6VM6YFPQV2ALVY3IV","short_pith_number":"pith:5XUFCDXQ","schema_version":"1.0","canonical_sha256":"ede8510ef02faacf60af857405d71b457cf0d2c7023c1ba0281639eed6d2c221","source":{"kind":"arxiv","id":"2606.08816","version":1},"attestation_state":"computed","paper":{"title":"Knowledge Graphs and Reasoning LLMs for Finding Simple Yet Effective Transcriptomic Perturbation Predictors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jake Fawkes, Jason Hartford, Liam Hodgson","submitted_at":"2026-06-07T20:09:30Z","abstract_excerpt":"Predicting the effect of an unseen gene knockout perturbation on transcriptomic gene expression remains a highly challenging problem for virtual cell models. Recent progress has been made by leveraging biological knowledge graphs to provide a notion of similar perturbation, allowing for improved extrapolation beyond the set of training perturbations. In this work, we demonstrate that the simplest model to leverage these assumptions - a K-nearest neighbour from the knowledge graph - achieves highly competitive performance on this task, and that this can be improved further using LLMs optimised "},"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":"2606.08816","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-07T20:09:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b035aa836bacae912b086f211e3bd0d9fda9d1108d61c13bbc8b37977e15e4a0","abstract_canon_sha256":"375dd05f1eb727ddec9a16f5ff0c6ee6b6a43313491ff46cf0d2a1cddef7c26f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:41.032733Z","signature_b64":"kRhkofPeSPg7VKfjzlPp5PhvKf7wxCH0OTlSVziSbCqtHEvwIGp0CqzwiVw/KyCDFrGKNJ9cd+lqiEACX7UNBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ede8510ef02faacf60af857405d71b457cf0d2c7023c1ba0281639eed6d2c221","last_reissued_at":"2026-06-09T02:07:41.031841Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:41.031841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Graphs and Reasoning LLMs for Finding Simple Yet Effective Transcriptomic Perturbation Predictors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jake Fawkes, Jason Hartford, Liam Hodgson","submitted_at":"2026-06-07T20:09:30Z","abstract_excerpt":"Predicting the effect of an unseen gene knockout perturbation on transcriptomic gene expression remains a highly challenging problem for virtual cell models. Recent progress has been made by leveraging biological knowledge graphs to provide a notion of similar perturbation, allowing for improved extrapolation beyond the set of training perturbations. In this work, we demonstrate that the simplest model to leverage these assumptions - a K-nearest neighbour from the knowledge graph - achieves highly competitive performance on this task, and that this can be improved further using LLMs optimised "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08816","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/2606.08816/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":"2606.08816","created_at":"2026-06-09T02:07:41.031987+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08816v1","created_at":"2026-06-09T02:07:41.031987+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08816","created_at":"2026-06-09T02:07:41.031987+00:00"},{"alias_kind":"pith_short_12","alias_value":"5XUFCDXQF6VM","created_at":"2026-06-09T02:07:41.031987+00:00"},{"alias_kind":"pith_short_16","alias_value":"5XUFCDXQF6VM6YFP","created_at":"2026-06-09T02:07:41.031987+00:00"},{"alias_kind":"pith_short_8","alias_value":"5XUFCDXQ","created_at":"2026-06-09T02:07:41.031987+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/5XUFCDXQF6VM6YFPQV2ALVY3IV","json":"https://pith.science/pith/5XUFCDXQF6VM6YFPQV2ALVY3IV.json","graph_json":"https://pith.science/api/pith-number/5XUFCDXQF6VM6YFPQV2ALVY3IV/graph.json","events_json":"https://pith.science/api/pith-number/5XUFCDXQF6VM6YFPQV2ALVY3IV/events.json","paper":"https://pith.science/paper/5XUFCDXQ"},"agent_actions":{"view_html":"https://pith.science/pith/5XUFCDXQF6VM6YFPQV2ALVY3IV","download_json":"https://pith.science/pith/5XUFCDXQF6VM6YFPQV2ALVY3IV.json","view_paper":"https://pith.science/paper/5XUFCDXQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08816&json=true","fetch_graph":"https://pith.science/api/pith-number/5XUFCDXQF6VM6YFPQV2ALVY3IV/graph.json","fetch_events":"https://pith.science/api/pith-number/5XUFCDXQF6VM6YFPQV2ALVY3IV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5XUFCDXQF6VM6YFPQV2ALVY3IV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5XUFCDXQF6VM6YFPQV2ALVY3IV/action/storage_attestation","attest_author":"https://pith.science/pith/5XUFCDXQF6VM6YFPQV2ALVY3IV/action/author_attestation","sign_citation":"https://pith.science/pith/5XUFCDXQF6VM6YFPQV2ALVY3IV/action/citation_signature","submit_replication":"https://pith.science/pith/5XUFCDXQF6VM6YFPQV2ALVY3IV/action/replication_record"}},"created_at":"2026-06-09T02:07:41.031987+00:00","updated_at":"2026-06-09T02:07:41.031987+00:00"}