{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KEJXNSP6OM4CFKAFP4RLPG6PBI","short_pith_number":"pith:KEJXNSP6","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"},"canonical_sha256":"511376c9fe733822a8057f22b79bcf0a3c4ac6500fa41cfa81c71c08884c259f","source":{"kind":"arxiv","id":"2404.05893","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.05893","created_at":"2026-07-05T10:17:46Z"},{"alias_kind":"arxiv_version","alias_value":"2404.05893v5","created_at":"2026-07-05T10:17:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05893","created_at":"2026-07-05T10:17:46Z"},{"alias_kind":"pith_short_12","alias_value":"KEJXNSP6OM4C","created_at":"2026-07-05T10:17:46Z"},{"alias_kind":"pith_short_16","alias_value":"KEJXNSP6OM4CFKAF","created_at":"2026-07-05T10:17:46Z"},{"alias_kind":"pith_short_8","alias_value":"KEJXNSP6","created_at":"2026-07-05T10:17:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KEJXNSP6OM4CFKAFP4RLPG6PBI","target":"record","payload":{"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"},"canonical_sha256":"511376c9fe733822a8057f22b79bcf0a3c4ac6500fa41cfa81c71c08884c259f","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"},"source_kind":"arxiv","source_id":"2404.05893","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:17:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m0jUBrHpCibielwvq1TCcNFAfhXHe5x08dHltTlS3+zJ55HF4CxEclpqAjqlCqOYaQfN0NOWHsQFesd0iZ+JAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T13:50:17.077382Z"},"content_sha256":"9772d72f0cc2c434875aa11f5ac058098d2ce96f175f31d0033291dce048f933","schema_version":"1.0","event_id":"sha256:9772d72f0cc2c434875aa11f5ac058098d2ce96f175f31d0033291dce048f933"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KEJXNSP6OM4CFKAFP4RLPG6PBI","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:17:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5krxgkYIFrHg7dITi6isCyAhWWhYiW6vTs6zB19cTybnZdX/+YK6z8l+jLPC3unwWtWyoazw+8iexfPvARtUCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T13:50:17.078267Z"},"content_sha256":"873305d24e9eec10f38dbcf2a469e6c882063457fdbb4360b99bc3cf294af848","schema_version":"1.0","event_id":"sha256:873305d24e9eec10f38dbcf2a469e6c882063457fdbb4360b99bc3cf294af848"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KEJXNSP6OM4CFKAFP4RLPG6PBI/bundle.json","state_url":"https://pith.science/pith/KEJXNSP6OM4CFKAFP4RLPG6PBI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KEJXNSP6OM4CFKAFP4RLPG6PBI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-21T13:50:17Z","links":{"resolver":"https://pith.science/pith/KEJXNSP6OM4CFKAFP4RLPG6PBI","bundle":"https://pith.science/pith/KEJXNSP6OM4CFKAFP4RLPG6PBI/bundle.json","state":"https://pith.science/pith/KEJXNSP6OM4CFKAFP4RLPG6PBI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KEJXNSP6OM4CFKAFP4RLPG6PBI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KEJXNSP6OM4CFKAFP4RLPG6PBI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e565a1256d8c89fd7d36951c61986a58342b5b1b78fe3aacbd036dfef7244d05","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-08T22:29:53Z","title_canon_sha256":"ace537a84f3b2c7aae3444c1b0433a558174be1876d5c56df2f16f4bf2f39ab8"},"schema_version":"1.0","source":{"id":"2404.05893","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.05893","created_at":"2026-07-05T10:17:46Z"},{"alias_kind":"arxiv_version","alias_value":"2404.05893v5","created_at":"2026-07-05T10:17:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05893","created_at":"2026-07-05T10:17:46Z"},{"alias_kind":"pith_short_12","alias_value":"KEJXNSP6OM4C","created_at":"2026-07-05T10:17:46Z"},{"alias_kind":"pith_short_16","alias_value":"KEJXNSP6OM4CFKAF","created_at":"2026-07-05T10:17:46Z"},{"alias_kind":"pith_short_8","alias_value":"KEJXNSP6","created_at":"2026-07-05T10:17:46Z"}],"graph_snapshots":[{"event_id":"sha256:873305d24e9eec10f38dbcf2a469e6c882063457fdbb4360b99bc3cf294af848","target":"graph","created_at":"2026-07-05T10:17:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.05893/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Anisha Laumas, Avani Khatri, Benjamin Solomon, Mark A. Musen, Purvesh Khatri, Sowmya S. Sundaram","cross_cats":["cs.CL","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-08T22:29:53Z","title":"Use of a Structured Knowledge Base Enhances Metadata Curation by Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05893","kind":"arxiv","version":5},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9772d72f0cc2c434875aa11f5ac058098d2ce96f175f31d0033291dce048f933","target":"record","created_at":"2026-07-05T10:17:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e565a1256d8c89fd7d36951c61986a58342b5b1b78fe3aacbd036dfef7244d05","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-08T22:29:53Z","title_canon_sha256":"ace537a84f3b2c7aae3444c1b0433a558174be1876d5c56df2f16f4bf2f39ab8"},"schema_version":"1.0","source":{"id":"2404.05893","kind":"arxiv","version":5}},"canonical_sha256":"511376c9fe733822a8057f22b79bcf0a3c4ac6500fa41cfa81c71c08884c259f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"511376c9fe733822a8057f22b79bcf0a3c4ac6500fa41cfa81c71c08884c259f","first_computed_at":"2026-07-05T10:17:46.794582Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:46.794582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QwdOc0h64Suy/87dHMRjyngCxQsoZokWCAZPFHinIIdLV/z56+pzMHguAmcvw5lnV7UXbKhFiJWkhOXpu7huBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:46.795088Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.05893","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9772d72f0cc2c434875aa11f5ac058098d2ce96f175f31d0033291dce048f933","sha256:873305d24e9eec10f38dbcf2a469e6c882063457fdbb4360b99bc3cf294af848"],"state_sha256":"7b7bf165e932edd907b669e3e59ccb015fb36142fd799dd0c4a7f2eecf8d363d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RGXAmAN/gg8dSEloOt2bEHndGPB6pJzTLXeAyeMuFCItqDWy+vH+zQGV3bWRdH6POJfqZS03bG5rtt2WdN2cBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T13:50:17.084062Z","bundle_sha256":"d6b0d34330c45a107f28cbc86d05f14dc2d3855124640f1905296a6b250b6cca"}}