{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DUG7ZKYNJVBUM6NKO4AU7WGAYG","short_pith_number":"pith:DUG7ZKYN","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"},"canonical_sha256":"1d0dfcab0d4d434679aa77014fd8c0c1b64e121f4278aab4a84c486f7b3cf65a","source":{"kind":"arxiv","id":"2502.07132","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07132","created_at":"2026-07-05T11:49:50Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07132v3","created_at":"2026-07-05T11:49:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07132","created_at":"2026-07-05T11:49:50Z"},{"alias_kind":"pith_short_12","alias_value":"DUG7ZKYNJVBU","created_at":"2026-07-05T11:49:50Z"},{"alias_kind":"pith_short_16","alias_value":"DUG7ZKYNJVBUM6NK","created_at":"2026-07-05T11:49:50Z"},{"alias_kind":"pith_short_8","alias_value":"DUG7ZKYN","created_at":"2026-07-05T11:49:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DUG7ZKYNJVBUM6NKO4AU7WGAYG","target":"record","payload":{"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"},"canonical_sha256":"1d0dfcab0d4d434679aa77014fd8c0c1b64e121f4278aab4a84c486f7b3cf65a","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"},"source_kind":"arxiv","source_id":"2502.07132","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:49:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dgWi1LAg13vx6dJgD2zIzivNfvFyrEgLu0KsA9nD8tEHF2zuntMdOyuLTO0xgP1vIx+eBhVnoQDKVISNKEOgAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:48:01.889738Z"},"content_sha256":"d85f1e69238c8c03eb89b831234e4e8daf6d466eda90458da7ac733d04a37260","schema_version":"1.0","event_id":"sha256:d85f1e69238c8c03eb89b831234e4e8daf6d466eda90458da7ac733d04a37260"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DUG7ZKYNJVBUM6NKO4AU7WGAYG","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:49:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DU0g5+ePaT41g9gp6ZP4shxa5P+6zS9eRWG4k0g6U/GflN8xEMiXpTr6M+uLk1ynnLnMwcRXCDbA9mkWOzlLDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:48:01.890839Z"},"content_sha256":"be6283d8a460277cc4dc37fa0bc3b32ae12066ee5b3b6f822f137bf11d2162c9","schema_version":"1.0","event_id":"sha256:be6283d8a460277cc4dc37fa0bc3b32ae12066ee5b3b6f822f137bf11d2162c9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DUG7ZKYNJVBUM6NKO4AU7WGAYG/bundle.json","state_url":"https://pith.science/pith/DUG7ZKYNJVBUM6NKO4AU7WGAYG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DUG7ZKYNJVBUM6NKO4AU7WGAYG/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":"2026-08-09T11:48:01Z","links":{"resolver":"https://pith.science/pith/DUG7ZKYNJVBUM6NKO4AU7WGAYG","bundle":"https://pith.science/pith/DUG7ZKYNJVBUM6NKO4AU7WGAYG/bundle.json","state":"https://pith.science/pith/DUG7ZKYNJVBUM6NKO4AU7WGAYG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DUG7ZKYNJVBUM6NKO4AU7WGAYG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DUG7ZKYNJVBUM6NKO4AU7WGAYG","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":"05ffc517dfb0d301f0f8fd70339cf52b250dc5b344e9cddfcc1cb0ed17fc2cfa","cross_cats_sorted":["cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-10T23:50:09Z","title_canon_sha256":"62f2bca8ac40e86bef1dfc938bec638ab14abed860bf96d6d893a753fe385163"},"schema_version":"1.0","source":{"id":"2502.07132","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07132","created_at":"2026-07-05T11:49:50Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07132v3","created_at":"2026-07-05T11:49:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07132","created_at":"2026-07-05T11:49:50Z"},{"alias_kind":"pith_short_12","alias_value":"DUG7ZKYNJVBU","created_at":"2026-07-05T11:49:50Z"},{"alias_kind":"pith_short_16","alias_value":"DUG7ZKYNJVBUM6NK","created_at":"2026-07-05T11:49:50Z"},{"alias_kind":"pith_short_8","alias_value":"DUG7ZKYN","created_at":"2026-07-05T11:49:50Z"}],"graph_snapshots":[{"event_id":"sha256:be6283d8a460277cc4dc37fa0bc3b32ae12066ee5b3b6f822f137bf11d2162c9","target":"graph","created_at":"2026-07-05T11:49:50Z","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/2502.07132/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"A\\'ecio Santos, Eduardo H. M. Pena, Juliana Freire, Roque Lopez","cross_cats":["cs.DB"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-10T23:50:09Z","title":"Interactive Data Harmonization with LLM Agents: Opportunities and Challenges"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07132","kind":"arxiv","version":3},"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:d85f1e69238c8c03eb89b831234e4e8daf6d466eda90458da7ac733d04a37260","target":"record","created_at":"2026-07-05T11:49:50Z","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":"05ffc517dfb0d301f0f8fd70339cf52b250dc5b344e9cddfcc1cb0ed17fc2cfa","cross_cats_sorted":["cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-10T23:50:09Z","title_canon_sha256":"62f2bca8ac40e86bef1dfc938bec638ab14abed860bf96d6d893a753fe385163"},"schema_version":"1.0","source":{"id":"2502.07132","kind":"arxiv","version":3}},"canonical_sha256":"1d0dfcab0d4d434679aa77014fd8c0c1b64e121f4278aab4a84c486f7b3cf65a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d0dfcab0d4d434679aa77014fd8c0c1b64e121f4278aab4a84c486f7b3cf65a","first_computed_at":"2026-07-05T11:49:50.490036Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:50.490036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Kq9oQYvJhaH2ynbBAAAtMyw8hSH8t8mIJg6F/ASPKCo6TKbV5pYH1V6b/LhlkGwzP//lGWNL8seDabIqoi6gCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:50.490527Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.07132","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d85f1e69238c8c03eb89b831234e4e8daf6d466eda90458da7ac733d04a37260","sha256:be6283d8a460277cc4dc37fa0bc3b32ae12066ee5b3b6f822f137bf11d2162c9"],"state_sha256":"1ce4b59c997cf680d11b57ae20c5e52360dcf41e3f3473e960e66b03ba64d279"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6nsC/ZjBEiFSNy5UvamCVqT05fnRiol+JIrDXvVYTZDiwJEUkh4JElrYsOUQ0Hy9Jn6LSWOMuRNKc9BmM4/DCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T11:48:01.900094Z","bundle_sha256":"ec8c51a6c3daac181eeeaa2f6b24888f1114e3ac4c22c74d4cb543e629b66c94"}}