{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:AD3476FOWBH477RFGHQITP2NXT","short_pith_number":"pith:AD3476FO","schema_version":"1.0","canonical_sha256":"00f7cff8aeb04fcffe2531e089bf4dbcf6deae8510e6e44ac11f631469a0541d","source":{"kind":"arxiv","id":"2102.04141","version":1},"attestation_state":"computed","paper":{"title":"Empowering Investigative Journalism with Graph-based Heterogeneous Data Management","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Angelos-Christos Anadiotis, Francesco Chimienti, Helena Galhardas, Ioana Manolescu, Mhd Yamen Haddad, Oana Balalau, Stephane Horel, Theo Bouganim, Youssr Youssef","submitted_at":"2021-02-08T11:39:51Z","abstract_excerpt":"Investigative Journalism (IJ, in short) is staple of modern, democratic societies. IJ often necessitates working with large, dynamic sets of heterogeneous, schema-less data sources, which can be structured, semi-structured, or textual, limiting the applicability of classical data integration approaches. In prior work, we have developed ConnectionLens, a system capable of integrating such sources into a single heterogeneous graph, leveraging Information Extraction (IE) techniques; users can then query the graph by means of keywords, and explore query results and their neighborhood using an inte"},"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":"2102.04141","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2021-02-08T11:39:51Z","cross_cats_sorted":[],"title_canon_sha256":"38b737f5a56afa0caa24ce37c041c54463674fdeb9c3c05def745f8a325823dc","abstract_canon_sha256":"48ec7022c8d4afcbd7943d2e10391f54acba36f17ce0ef006a7820af0e45f008"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:13:30.566707Z","signature_b64":"Y/D8smmLVvi1TDyzuXQr6m59G5WNmdSmeZZu0UbOjbbxihc8lhSiHYQTCFsJD3QEG8lk5h1D9TNmxydTEsO5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00f7cff8aeb04fcffe2531e089bf4dbcf6deae8510e6e44ac11f631469a0541d","last_reissued_at":"2026-07-05T02:13:30.566342Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:13:30.566342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Empowering Investigative Journalism with Graph-based Heterogeneous Data Management","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Angelos-Christos Anadiotis, Francesco Chimienti, Helena Galhardas, Ioana Manolescu, Mhd Yamen Haddad, Oana Balalau, Stephane Horel, Theo Bouganim, Youssr Youssef","submitted_at":"2021-02-08T11:39:51Z","abstract_excerpt":"Investigative Journalism (IJ, in short) is staple of modern, democratic societies. IJ often necessitates working with large, dynamic sets of heterogeneous, schema-less data sources, which can be structured, semi-structured, or textual, limiting the applicability of classical data integration approaches. In prior work, we have developed ConnectionLens, a system capable of integrating such sources into a single heterogeneous graph, leveraging Information Extraction (IE) techniques; users can then query the graph by means of keywords, and explore query results and their neighborhood using an inte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.04141","kind":"arxiv","version":1},"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/2102.04141/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":"2102.04141","created_at":"2026-07-05T02:13:30.566405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.04141v1","created_at":"2026-07-05T02:13:30.566405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.04141","created_at":"2026-07-05T02:13:30.566405+00:00"},{"alias_kind":"pith_short_12","alias_value":"AD3476FOWBH4","created_at":"2026-07-05T02:13:30.566405+00:00"},{"alias_kind":"pith_short_16","alias_value":"AD3476FOWBH477RF","created_at":"2026-07-05T02:13:30.566405+00:00"},{"alias_kind":"pith_short_8","alias_value":"AD3476FO","created_at":"2026-07-05T02:13:30.566405+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/AD3476FOWBH477RFGHQITP2NXT","json":"https://pith.science/pith/AD3476FOWBH477RFGHQITP2NXT.json","graph_json":"https://pith.science/api/pith-number/AD3476FOWBH477RFGHQITP2NXT/graph.json","events_json":"https://pith.science/api/pith-number/AD3476FOWBH477RFGHQITP2NXT/events.json","paper":"https://pith.science/paper/AD3476FO"},"agent_actions":{"view_html":"https://pith.science/pith/AD3476FOWBH477RFGHQITP2NXT","download_json":"https://pith.science/pith/AD3476FOWBH477RFGHQITP2NXT.json","view_paper":"https://pith.science/paper/AD3476FO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.04141&json=true","fetch_graph":"https://pith.science/api/pith-number/AD3476FOWBH477RFGHQITP2NXT/graph.json","fetch_events":"https://pith.science/api/pith-number/AD3476FOWBH477RFGHQITP2NXT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AD3476FOWBH477RFGHQITP2NXT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AD3476FOWBH477RFGHQITP2NXT/action/storage_attestation","attest_author":"https://pith.science/pith/AD3476FOWBH477RFGHQITP2NXT/action/author_attestation","sign_citation":"https://pith.science/pith/AD3476FOWBH477RFGHQITP2NXT/action/citation_signature","submit_replication":"https://pith.science/pith/AD3476FOWBH477RFGHQITP2NXT/action/replication_record"}},"created_at":"2026-07-05T02:13:30.566405+00:00","updated_at":"2026-07-05T02:13:30.566405+00:00"}