{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7RGRTGEZYG37O3VRONLYWCFIXV","short_pith_number":"pith:7RGRTGEZ","schema_version":"1.0","canonical_sha256":"fc4d199899c1b7f76eb173578b08a8bd6700923c8c96572db50f8ce5e0c5616c","source":{"kind":"arxiv","id":"2012.08830","version":1},"attestation_state":"computed","paper":{"title":"Graph integration of structured, semistructured and unstructured data for data journalism","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Angelos-Christos Anadiotis, Catarina Conceicao, Helena Galhardas, Ioana Manolescu, Jingmao You, Mhd Yamen Haddad, Oana Balalau, Tayeb Merabti","submitted_at":"2020-12-16T09:59:27Z","abstract_excerpt":"Digital data is a gold mine for modern journalism. However, datasets which interest journalists are extremely heterogeneous, ranging from highly structured (relational databases), semi-structured (JSON, XML, HTML), graphs (e.g., RDF), and text. Journalists (and other classes of users lacking advanced IT expertise, such as most non-governmental-organizations, or small public administrations) need to be able to make sense of such heterogeneous corpora, even if they lack the ability to define and deploy custom extract-transform-load workflows, especially for dynamically varying sets of data sourc"},"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":"2012.08830","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2020-12-16T09:59:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"54351454e7866a010903423c097e5630e3a4a13b58c26aa97f62897c109e40ea","abstract_canon_sha256":"c67a77808144e9555f5a8cf23372e11a929d669d10147ad278d61b58195ff16e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:00:03.907877Z","signature_b64":"Y1FrR9O9jlHWhZcHwHqkiOf6dSvogGqa+6tkkS0XU/Z7EK8kWtsw1AxOPKUnK2ZDttcNv6/rVYUYUorXsqZ1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc4d199899c1b7f76eb173578b08a8bd6700923c8c96572db50f8ce5e0c5616c","last_reissued_at":"2026-07-05T02:00:03.907479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:00:03.907479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph integration of structured, semistructured and unstructured data for data journalism","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Angelos-Christos Anadiotis, Catarina Conceicao, Helena Galhardas, Ioana Manolescu, Jingmao You, Mhd Yamen Haddad, Oana Balalau, Tayeb Merabti","submitted_at":"2020-12-16T09:59:27Z","abstract_excerpt":"Digital data is a gold mine for modern journalism. However, datasets which interest journalists are extremely heterogeneous, ranging from highly structured (relational databases), semi-structured (JSON, XML, HTML), graphs (e.g., RDF), and text. Journalists (and other classes of users lacking advanced IT expertise, such as most non-governmental-organizations, or small public administrations) need to be able to make sense of such heterogeneous corpora, even if they lack the ability to define and deploy custom extract-transform-load workflows, especially for dynamically varying sets of data sourc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.08830","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/2012.08830/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":"2012.08830","created_at":"2026-07-05T02:00:03.907535+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.08830v1","created_at":"2026-07-05T02:00:03.907535+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.08830","created_at":"2026-07-05T02:00:03.907535+00:00"},{"alias_kind":"pith_short_12","alias_value":"7RGRTGEZYG37","created_at":"2026-07-05T02:00:03.907535+00:00"},{"alias_kind":"pith_short_16","alias_value":"7RGRTGEZYG37O3VR","created_at":"2026-07-05T02:00:03.907535+00:00"},{"alias_kind":"pith_short_8","alias_value":"7RGRTGEZ","created_at":"2026-07-05T02:00:03.907535+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/7RGRTGEZYG37O3VRONLYWCFIXV","json":"https://pith.science/pith/7RGRTGEZYG37O3VRONLYWCFIXV.json","graph_json":"https://pith.science/api/pith-number/7RGRTGEZYG37O3VRONLYWCFIXV/graph.json","events_json":"https://pith.science/api/pith-number/7RGRTGEZYG37O3VRONLYWCFIXV/events.json","paper":"https://pith.science/paper/7RGRTGEZ"},"agent_actions":{"view_html":"https://pith.science/pith/7RGRTGEZYG37O3VRONLYWCFIXV","download_json":"https://pith.science/pith/7RGRTGEZYG37O3VRONLYWCFIXV.json","view_paper":"https://pith.science/paper/7RGRTGEZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.08830&json=true","fetch_graph":"https://pith.science/api/pith-number/7RGRTGEZYG37O3VRONLYWCFIXV/graph.json","fetch_events":"https://pith.science/api/pith-number/7RGRTGEZYG37O3VRONLYWCFIXV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7RGRTGEZYG37O3VRONLYWCFIXV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7RGRTGEZYG37O3VRONLYWCFIXV/action/storage_attestation","attest_author":"https://pith.science/pith/7RGRTGEZYG37O3VRONLYWCFIXV/action/author_attestation","sign_citation":"https://pith.science/pith/7RGRTGEZYG37O3VRONLYWCFIXV/action/citation_signature","submit_replication":"https://pith.science/pith/7RGRTGEZYG37O3VRONLYWCFIXV/action/replication_record"}},"created_at":"2026-07-05T02:00:03.907535+00:00","updated_at":"2026-07-05T02:00:03.907535+00:00"}