{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KEJXNSP6OM4CFKAFP4RLPG6PBI","short_pith_number":"pith:KEJXNSP6","schema_version":"1.0","canonical_sha256":"511376c9fe733822a8057f22b79bcf0a3c4ac6500fa41cfa81c71c08884c259f","source":{"kind":"arxiv","id":"2404.05893","version":5},"attestation_state":"computed","paper":{"title":"Use of a Structured Knowledge Base Enhances Metadata Curation by Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.AI","authors_text":"Anisha Laumas, Avani Khatri, Benjamin Solomon, Mark A. Musen, Purvesh Khatri, Sowmya S. Sundaram","submitted_at":"2024-04-08T22:29:53Z","abstract_excerpt":"Metadata play a crucial role in ensuring the findability, accessibility, interoperability, and reusability of datasets. This paper investigates the potential of large language models (LLMs), specifically GPT-4, to improve adherence to metadata standards. We conducted experiments on 200 random data records describing human samples relating to lung cancer from the NCBI BioSample repository, evaluating GPT-4's ability to suggest edits for adherence to metadata standards. We computed the adherence accuracy of field name-field value pairs through a peer review process, and we observed a marginal av"},"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":"2404.05893","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-08T22:29:53Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"ace537a84f3b2c7aae3444c1b0433a558174be1876d5c56df2f16f4bf2f39ab8","abstract_canon_sha256":"e565a1256d8c89fd7d36951c61986a58342b5b1b78fe3aacbd036dfef7244d05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:46.795088Z","signature_b64":"QwdOc0h64Suy/87dHMRjyngCxQsoZokWCAZPFHinIIdLV/z56+pzMHguAmcvw5lnV7UXbKhFiJWkhOXpu7huBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"511376c9fe733822a8057f22b79bcf0a3c4ac6500fa41cfa81c71c08884c259f","last_reissued_at":"2026-07-05T10:17:46.794582Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:46.794582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Use of a Structured Knowledge Base Enhances Metadata Curation by Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.AI","authors_text":"Anisha Laumas, Avani Khatri, Benjamin Solomon, Mark A. Musen, Purvesh Khatri, Sowmya S. Sundaram","submitted_at":"2024-04-08T22:29:53Z","abstract_excerpt":"Metadata play a crucial role in ensuring the findability, accessibility, interoperability, and reusability of datasets. This paper investigates the potential of large language models (LLMs), specifically GPT-4, to improve adherence to metadata standards. We conducted experiments on 200 random data records describing human samples relating to lung cancer from the NCBI BioSample repository, evaluating GPT-4's ability to suggest edits for adherence to metadata standards. We computed the adherence accuracy of field name-field value pairs through a peer review process, and we observed a marginal av"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05893","kind":"arxiv","version":5},"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/2404.05893/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":"2404.05893","created_at":"2026-07-05T10:17:46.794644+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.05893v5","created_at":"2026-07-05T10:17:46.794644+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05893","created_at":"2026-07-05T10:17:46.794644+00:00"},{"alias_kind":"pith_short_12","alias_value":"KEJXNSP6OM4C","created_at":"2026-07-05T10:17:46.794644+00:00"},{"alias_kind":"pith_short_16","alias_value":"KEJXNSP6OM4CFKAF","created_at":"2026-07-05T10:17:46.794644+00:00"},{"alias_kind":"pith_short_8","alias_value":"KEJXNSP6","created_at":"2026-07-05T10:17:46.794644+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/KEJXNSP6OM4CFKAFP4RLPG6PBI","json":"https://pith.science/pith/KEJXNSP6OM4CFKAFP4RLPG6PBI.json","graph_json":"https://pith.science/api/pith-number/KEJXNSP6OM4CFKAFP4RLPG6PBI/graph.json","events_json":"https://pith.science/api/pith-number/KEJXNSP6OM4CFKAFP4RLPG6PBI/events.json","paper":"https://pith.science/paper/KEJXNSP6"},"agent_actions":{"view_html":"https://pith.science/pith/KEJXNSP6OM4CFKAFP4RLPG6PBI","download_json":"https://pith.science/pith/KEJXNSP6OM4CFKAFP4RLPG6PBI.json","view_paper":"https://pith.science/paper/KEJXNSP6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.05893&json=true","fetch_graph":"https://pith.science/api/pith-number/KEJXNSP6OM4CFKAFP4RLPG6PBI/graph.json","fetch_events":"https://pith.science/api/pith-number/KEJXNSP6OM4CFKAFP4RLPG6PBI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KEJXNSP6OM4CFKAFP4RLPG6PBI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KEJXNSP6OM4CFKAFP4RLPG6PBI/action/storage_attestation","attest_author":"https://pith.science/pith/KEJXNSP6OM4CFKAFP4RLPG6PBI/action/author_attestation","sign_citation":"https://pith.science/pith/KEJXNSP6OM4CFKAFP4RLPG6PBI/action/citation_signature","submit_replication":"https://pith.science/pith/KEJXNSP6OM4CFKAFP4RLPG6PBI/action/replication_record"}},"created_at":"2026-07-05T10:17:46.794644+00:00","updated_at":"2026-07-05T10:17:46.794644+00:00"}