{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5CUW4JJOA3T7J4QKSPSFKR22Z2","short_pith_number":"pith:5CUW4JJO","schema_version":"1.0","canonical_sha256":"e8a96e252e06e7f4f20a93e455475aceae84c76f1687371547f899bedd6d6a4d","source":{"kind":"arxiv","id":"2305.13338","version":3},"attestation_state":"computed","paper":{"title":"Gene Set Summarization using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","q-bio.QM"],"primary_cat":"q-bio.GN","authors_text":"Christopher J. Mungall, HyeongSik Kim, J. Harry Caufield, Marcin P. Joachimiak, Nomi L. Harris","submitted_at":"2023-05-21T02:06:33Z","abstract_excerpt":"Molecular biologists frequently interpret gene lists derived from high-throughput experiments and computational analysis. This is typically done as a statistical enrichment analysis that measures the over- or under-representation of biological function terms associated with genes or their properties, based on curated assertions from a knowledge base (KB) such as the Gene Ontology (GO). Interpreting gene lists can also be framed as a textual summarization task, enabling the use of Large Language Models (LLMs), potentially utilizing scientific texts directly and avoiding reliance on a KB.\n  We d"},"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":"2305.13338","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2023-05-21T02:06:33Z","cross_cats_sorted":["cs.AI","cs.CL","q-bio.QM"],"title_canon_sha256":"aa289d9ed36b8661f97bb741a7fd327dc5124d3566e22a419a824d35cf73f4be","abstract_canon_sha256":"9433b853692b3e277dc604f0eed269f6d79631761f474a77478af9f2e9f90099"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:49.985332Z","signature_b64":"JjzXW1QiBcHL1Q6hZ9ZU9/ezp8iKGeR+aYRU+oKhI63jgoXb9iQii/mUm1nqyYW5M//Qy5x7o9C23YgcOP3vDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8a96e252e06e7f4f20a93e455475aceae84c76f1687371547f899bedd6d6a4d","last_reissued_at":"2026-07-05T08:39:49.984924Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:49.984924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gene Set Summarization using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","q-bio.QM"],"primary_cat":"q-bio.GN","authors_text":"Christopher J. Mungall, HyeongSik Kim, J. Harry Caufield, Marcin P. Joachimiak, Nomi L. Harris","submitted_at":"2023-05-21T02:06:33Z","abstract_excerpt":"Molecular biologists frequently interpret gene lists derived from high-throughput experiments and computational analysis. This is typically done as a statistical enrichment analysis that measures the over- or under-representation of biological function terms associated with genes or their properties, based on curated assertions from a knowledge base (KB) such as the Gene Ontology (GO). Interpreting gene lists can also be framed as a textual summarization task, enabling the use of Large Language Models (LLMs), potentially utilizing scientific texts directly and avoiding reliance on a KB.\n  We d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13338","kind":"arxiv","version":3},"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/2305.13338/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":"2305.13338","created_at":"2026-07-05T08:39:49.984978+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13338v3","created_at":"2026-07-05T08:39:49.984978+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13338","created_at":"2026-07-05T08:39:49.984978+00:00"},{"alias_kind":"pith_short_12","alias_value":"5CUW4JJOA3T7","created_at":"2026-07-05T08:39:49.984978+00:00"},{"alias_kind":"pith_short_16","alias_value":"5CUW4JJOA3T7J4QK","created_at":"2026-07-05T08:39:49.984978+00:00"},{"alias_kind":"pith_short_8","alias_value":"5CUW4JJO","created_at":"2026-07-05T08:39:49.984978+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/5CUW4JJOA3T7J4QKSPSFKR22Z2","json":"https://pith.science/pith/5CUW4JJOA3T7J4QKSPSFKR22Z2.json","graph_json":"https://pith.science/api/pith-number/5CUW4JJOA3T7J4QKSPSFKR22Z2/graph.json","events_json":"https://pith.science/api/pith-number/5CUW4JJOA3T7J4QKSPSFKR22Z2/events.json","paper":"https://pith.science/paper/5CUW4JJO"},"agent_actions":{"view_html":"https://pith.science/pith/5CUW4JJOA3T7J4QKSPSFKR22Z2","download_json":"https://pith.science/pith/5CUW4JJOA3T7J4QKSPSFKR22Z2.json","view_paper":"https://pith.science/paper/5CUW4JJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13338&json=true","fetch_graph":"https://pith.science/api/pith-number/5CUW4JJOA3T7J4QKSPSFKR22Z2/graph.json","fetch_events":"https://pith.science/api/pith-number/5CUW4JJOA3T7J4QKSPSFKR22Z2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5CUW4JJOA3T7J4QKSPSFKR22Z2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5CUW4JJOA3T7J4QKSPSFKR22Z2/action/storage_attestation","attest_author":"https://pith.science/pith/5CUW4JJOA3T7J4QKSPSFKR22Z2/action/author_attestation","sign_citation":"https://pith.science/pith/5CUW4JJOA3T7J4QKSPSFKR22Z2/action/citation_signature","submit_replication":"https://pith.science/pith/5CUW4JJOA3T7J4QKSPSFKR22Z2/action/replication_record"}},"created_at":"2026-07-05T08:39:49.984978+00:00","updated_at":"2026-07-05T08:39:49.984978+00:00"}