{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PVRIVQGB5BCPO4WXBGP7YAN425","short_pith_number":"pith:PVRIVQGB","schema_version":"1.0","canonical_sha256":"7d628ac0c1e844f772d7099ffc01bcd75220a74df00f2733c69af117085c3856","source":{"kind":"arxiv","id":"2504.05307","version":2},"attestation_state":"computed","paper":{"title":"Toward Total Recall: Enhancing FAIRness through AI-Driven Metadata Standardization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Mark A Musen, Rafael S. Gon\\c{c}alves, Sowmya S Sundaram","submitted_at":"2025-02-13T21:58:27Z","abstract_excerpt":"Scientific metadata often suffer from incompleteness, inconsistency, and formatting errors, which hinder effective discovery and reuse of the associated datasets. We present a method that combines GPT-4 with structured metadata templates from the CEDAR knowledge base to automatically standardize metadata and to ensure compliance with established standards. A CEDAR template specifies the expected fields of a metadata submission and their permissible values. Our standardization process involves using CEDAR templates to guide GPT-4 in accurately correcting and refining metadata entries in bulk, r"},"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":"2504.05307","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-02-13T21:58:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"858ab1e3f61643cc894be0289cd22cf247debb41e776472e2a425d3fba6a2b24","abstract_canon_sha256":"0eaae8a35bf0b05cc2899e213bf49dff18658e700fdaa3c4d30cbed932abc98e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:44.601964Z","signature_b64":"yUWl9S3ER6RAPNZaoO/PPPQdOxW4YeoK37DVMsZ2JqYI4+T4dJf+t++xMdto3cJP3fmv8kaKz5gmVnq1i7LUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d628ac0c1e844f772d7099ffc01bcd75220a74df00f2733c69af117085c3856","last_reissued_at":"2026-07-05T11:17:44.601513Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:44.601513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward Total Recall: Enhancing FAIRness through AI-Driven Metadata Standardization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Mark A Musen, Rafael S. Gon\\c{c}alves, Sowmya S Sundaram","submitted_at":"2025-02-13T21:58:27Z","abstract_excerpt":"Scientific metadata often suffer from incompleteness, inconsistency, and formatting errors, which hinder effective discovery and reuse of the associated datasets. We present a method that combines GPT-4 with structured metadata templates from the CEDAR knowledge base to automatically standardize metadata and to ensure compliance with established standards. A CEDAR template specifies the expected fields of a metadata submission and their permissible values. Our standardization process involves using CEDAR templates to guide GPT-4 in accurately correcting and refining metadata entries in bulk, r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05307","kind":"arxiv","version":2},"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/2504.05307/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":"2504.05307","created_at":"2026-07-05T11:17:44.601570+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.05307v2","created_at":"2026-07-05T11:17:44.601570+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05307","created_at":"2026-07-05T11:17:44.601570+00:00"},{"alias_kind":"pith_short_12","alias_value":"PVRIVQGB5BCP","created_at":"2026-07-05T11:17:44.601570+00:00"},{"alias_kind":"pith_short_16","alias_value":"PVRIVQGB5BCPO4WX","created_at":"2026-07-05T11:17:44.601570+00:00"},{"alias_kind":"pith_short_8","alias_value":"PVRIVQGB","created_at":"2026-07-05T11:17:44.601570+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22391","citing_title":"Knowledge engineering for open science: Building and deploying knowledge bases for metadata standards","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PVRIVQGB5BCPO4WXBGP7YAN425","json":"https://pith.science/pith/PVRIVQGB5BCPO4WXBGP7YAN425.json","graph_json":"https://pith.science/api/pith-number/PVRIVQGB5BCPO4WXBGP7YAN425/graph.json","events_json":"https://pith.science/api/pith-number/PVRIVQGB5BCPO4WXBGP7YAN425/events.json","paper":"https://pith.science/paper/PVRIVQGB"},"agent_actions":{"view_html":"https://pith.science/pith/PVRIVQGB5BCPO4WXBGP7YAN425","download_json":"https://pith.science/pith/PVRIVQGB5BCPO4WXBGP7YAN425.json","view_paper":"https://pith.science/paper/PVRIVQGB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.05307&json=true","fetch_graph":"https://pith.science/api/pith-number/PVRIVQGB5BCPO4WXBGP7YAN425/graph.json","fetch_events":"https://pith.science/api/pith-number/PVRIVQGB5BCPO4WXBGP7YAN425/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PVRIVQGB5BCPO4WXBGP7YAN425/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PVRIVQGB5BCPO4WXBGP7YAN425/action/storage_attestation","attest_author":"https://pith.science/pith/PVRIVQGB5BCPO4WXBGP7YAN425/action/author_attestation","sign_citation":"https://pith.science/pith/PVRIVQGB5BCPO4WXBGP7YAN425/action/citation_signature","submit_replication":"https://pith.science/pith/PVRIVQGB5BCPO4WXBGP7YAN425/action/replication_record"}},"created_at":"2026-07-05T11:17:44.601570+00:00","updated_at":"2026-07-05T11:17:44.601570+00:00"}