{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5JZ3MQOKWYWZ2A5LIC3FDHWHXC","short_pith_number":"pith:5JZ3MQOK","schema_version":"1.0","canonical_sha256":"ea73b641cab62d9d03ab40b6519ec7b8999960803997354e0582767adf544242","source":{"kind":"arxiv","id":"2411.00046","version":1},"attestation_state":"computed","paper":{"title":"CurateGPT: A flexible language-model assisted biocuration tool","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB","q-bio.QM"],"primary_cat":"cs.CL","authors_text":"Carlo Kroll, Christopher J Mungall, Damian Smedley, Harry Caufield, Harshad Hegde, James A McLaughlin, Justin T Reese, Madan Krishnamurthy, Marcin P Joachimiak, Melissa A Haendel, Nomi L Harris, Peter N Robinson, Shawn T O'Neil","submitted_at":"2024-10-29T20:00:04Z","abstract_excerpt":"Effective data-driven biomedical discovery requires data curation: a time-consuming process of finding, organizing, distilling, integrating, interpreting, annotating, and validating diverse information into a structured form suitable for databases and knowledge bases. Accurate and efficient curation of these digital assets is critical to ensuring that they are FAIR, trustworthy, and sustainable. Unfortunately, expert curators face significant time and resource constraints. The rapid pace of new information being published daily is exceeding their capacity for curation. Generative AI, exemplifi"},"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":"2411.00046","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T20:00:04Z","cross_cats_sorted":["cs.AI","cs.DB","q-bio.QM"],"title_canon_sha256":"9cc18e725d2e8492b7f8de543333d6fa6a71ec7e7291f76219423feb3bdcc64d","abstract_canon_sha256":"fbac6638c8de85e7e18497026356d39d3a11caa6a59efaf7f7283c9e3fb9fcc4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:36.803752Z","signature_b64":"JeRaZ+bBJtYtDMGWoYoVRbPzhhZnOo7jAFUdtb4Yy/IL2Cejr9JOO9aPBtHgxOLrYtFs0uMWJyuw02CCwW+TBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea73b641cab62d9d03ab40b6519ec7b8999960803997354e0582767adf544242","last_reissued_at":"2026-07-05T09:29:36.803288Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:36.803288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CurateGPT: A flexible language-model assisted biocuration tool","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB","q-bio.QM"],"primary_cat":"cs.CL","authors_text":"Carlo Kroll, Christopher J Mungall, Damian Smedley, Harry Caufield, Harshad Hegde, James A McLaughlin, Justin T Reese, Madan Krishnamurthy, Marcin P Joachimiak, Melissa A Haendel, Nomi L Harris, Peter N Robinson, Shawn T O'Neil","submitted_at":"2024-10-29T20:00:04Z","abstract_excerpt":"Effective data-driven biomedical discovery requires data curation: a time-consuming process of finding, organizing, distilling, integrating, interpreting, annotating, and validating diverse information into a structured form suitable for databases and knowledge bases. Accurate and efficient curation of these digital assets is critical to ensuring that they are FAIR, trustworthy, and sustainable. Unfortunately, expert curators face significant time and resource constraints. The rapid pace of new information being published daily is exceeding their capacity for curation. Generative AI, exemplifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00046","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/2411.00046/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":"2411.00046","created_at":"2026-07-05T09:29:36.803357+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.00046v1","created_at":"2026-07-05T09:29:36.803357+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00046","created_at":"2026-07-05T09:29:36.803357+00:00"},{"alias_kind":"pith_short_12","alias_value":"5JZ3MQOKWYWZ","created_at":"2026-07-05T09:29:36.803357+00:00"},{"alias_kind":"pith_short_16","alias_value":"5JZ3MQOKWYWZ2A5L","created_at":"2026-07-05T09:29:36.803357+00:00"},{"alias_kind":"pith_short_8","alias_value":"5JZ3MQOK","created_at":"2026-07-05T09:29:36.803357+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28856","citing_title":"Building AI-Ready Data Systems for Space Life Sciences, Aerospace Medicine, and Deep Space Exploration","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03156","citing_title":"A cross-domain tropical species dataset with Chinese vernacular names and CITES source links","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5JZ3MQOKWYWZ2A5LIC3FDHWHXC","json":"https://pith.science/pith/5JZ3MQOKWYWZ2A5LIC3FDHWHXC.json","graph_json":"https://pith.science/api/pith-number/5JZ3MQOKWYWZ2A5LIC3FDHWHXC/graph.json","events_json":"https://pith.science/api/pith-number/5JZ3MQOKWYWZ2A5LIC3FDHWHXC/events.json","paper":"https://pith.science/paper/5JZ3MQOK"},"agent_actions":{"view_html":"https://pith.science/pith/5JZ3MQOKWYWZ2A5LIC3FDHWHXC","download_json":"https://pith.science/pith/5JZ3MQOKWYWZ2A5LIC3FDHWHXC.json","view_paper":"https://pith.science/paper/5JZ3MQOK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.00046&json=true","fetch_graph":"https://pith.science/api/pith-number/5JZ3MQOKWYWZ2A5LIC3FDHWHXC/graph.json","fetch_events":"https://pith.science/api/pith-number/5JZ3MQOKWYWZ2A5LIC3FDHWHXC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5JZ3MQOKWYWZ2A5LIC3FDHWHXC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5JZ3MQOKWYWZ2A5LIC3FDHWHXC/action/storage_attestation","attest_author":"https://pith.science/pith/5JZ3MQOKWYWZ2A5LIC3FDHWHXC/action/author_attestation","sign_citation":"https://pith.science/pith/5JZ3MQOKWYWZ2A5LIC3FDHWHXC/action/citation_signature","submit_replication":"https://pith.science/pith/5JZ3MQOKWYWZ2A5LIC3FDHWHXC/action/replication_record"}},"created_at":"2026-07-05T09:29:36.803357+00:00","updated_at":"2026-07-05T09:29:36.803357+00:00"}