{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DUG7ZKYNJVBUM6NKO4AU7WGAYG","short_pith_number":"pith:DUG7ZKYN","schema_version":"1.0","canonical_sha256":"1d0dfcab0d4d434679aa77014fd8c0c1b64e121f4278aab4a84c486f7b3cf65a","source":{"kind":"arxiv","id":"2502.07132","version":3},"attestation_state":"computed","paper":{"title":"Interactive Data Harmonization with LLM Agents: Opportunities and Challenges","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.AI","authors_text":"A\\'ecio Santos, Eduardo H. M. Pena, Juliana Freire, Roque Lopez","submitted_at":"2025-02-10T23:50:09Z","abstract_excerpt":"Data harmonization is an essential task that entails integrating datasets from diverse sources. Despite years of research in this area, it remains a time-consuming and challenging task due to schema mismatches, varying terminologies, and differences in data collection methodologies. This paper presents the case for agentic data harmonization as a means to both empower experts to harmonize their data and to streamline the process. We introduce Harmonia, a system that combines LLM-based reasoning, an interactive user interface, and a library of data harmonization primitives to automate the synth"},"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":"2502.07132","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-10T23:50:09Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"62f2bca8ac40e86bef1dfc938bec638ab14abed860bf96d6d893a753fe385163","abstract_canon_sha256":"05ffc517dfb0d301f0f8fd70339cf52b250dc5b344e9cddfcc1cb0ed17fc2cfa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:50.490527Z","signature_b64":"Kq9oQYvJhaH2ynbBAAAtMyw8hSH8t8mIJg6F/ASPKCo6TKbV5pYH1V6b/LhlkGwzP//lGWNL8seDabIqoi6gCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d0dfcab0d4d434679aa77014fd8c0c1b64e121f4278aab4a84c486f7b3cf65a","last_reissued_at":"2026-07-05T11:49:50.490036Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:50.490036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interactive Data Harmonization with LLM Agents: Opportunities and Challenges","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.AI","authors_text":"A\\'ecio Santos, Eduardo H. M. Pena, Juliana Freire, Roque Lopez","submitted_at":"2025-02-10T23:50:09Z","abstract_excerpt":"Data harmonization is an essential task that entails integrating datasets from diverse sources. Despite years of research in this area, it remains a time-consuming and challenging task due to schema mismatches, varying terminologies, and differences in data collection methodologies. This paper presents the case for agentic data harmonization as a means to both empower experts to harmonize their data and to streamline the process. We introduce Harmonia, a system that combines LLM-based reasoning, an interactive user interface, and a library of data harmonization primitives to automate the synth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07132","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/2502.07132/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":"2502.07132","created_at":"2026-07-05T11:49:50.490095+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.07132v3","created_at":"2026-07-05T11:49:50.490095+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07132","created_at":"2026-07-05T11:49:50.490095+00:00"},{"alias_kind":"pith_short_12","alias_value":"DUG7ZKYNJVBU","created_at":"2026-07-05T11:49:50.490095+00:00"},{"alias_kind":"pith_short_16","alias_value":"DUG7ZKYNJVBUM6NK","created_at":"2026-07-05T11:49:50.490095+00:00"},{"alias_kind":"pith_short_8","alias_value":"DUG7ZKYN","created_at":"2026-07-05T11:49:50.490095+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08687","citing_title":"PrepBench: How Far Are We from Natural-Language-Driven Data Preparation?","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DUG7ZKYNJVBUM6NKO4AU7WGAYG","json":"https://pith.science/pith/DUG7ZKYNJVBUM6NKO4AU7WGAYG.json","graph_json":"https://pith.science/api/pith-number/DUG7ZKYNJVBUM6NKO4AU7WGAYG/graph.json","events_json":"https://pith.science/api/pith-number/DUG7ZKYNJVBUM6NKO4AU7WGAYG/events.json","paper":"https://pith.science/paper/DUG7ZKYN"},"agent_actions":{"view_html":"https://pith.science/pith/DUG7ZKYNJVBUM6NKO4AU7WGAYG","download_json":"https://pith.science/pith/DUG7ZKYNJVBUM6NKO4AU7WGAYG.json","view_paper":"https://pith.science/paper/DUG7ZKYN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.07132&json=true","fetch_graph":"https://pith.science/api/pith-number/DUG7ZKYNJVBUM6NKO4AU7WGAYG/graph.json","fetch_events":"https://pith.science/api/pith-number/DUG7ZKYNJVBUM6NKO4AU7WGAYG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DUG7ZKYNJVBUM6NKO4AU7WGAYG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DUG7ZKYNJVBUM6NKO4AU7WGAYG/action/storage_attestation","attest_author":"https://pith.science/pith/DUG7ZKYNJVBUM6NKO4AU7WGAYG/action/author_attestation","sign_citation":"https://pith.science/pith/DUG7ZKYNJVBUM6NKO4AU7WGAYG/action/citation_signature","submit_replication":"https://pith.science/pith/DUG7ZKYNJVBUM6NKO4AU7WGAYG/action/replication_record"}},"created_at":"2026-07-05T11:49:50.490095+00:00","updated_at":"2026-07-05T11:49:50.490095+00:00"}