{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:YUP2NWI3S5VRZURTXJWSBNOU3K","short_pith_number":"pith:YUP2NWI3","schema_version":"1.0","canonical_sha256":"c51fa6d91b976b1cd233ba6d20b5d4da9585b1119be4c411af3b6f576b5167d4","source":{"kind":"arxiv","id":"1812.10315","version":1},"attestation_state":"computed","paper":{"title":"DBpedia NIF: Open, Large-Scale and Multilingual Knowledge Extraction Corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Amit Kirschenbaum, Julio Hernandez, Markus Ackermann, Milan Dojchinovski, Sebastian Hellmann","submitted_at":"2018-12-26T13:50:50Z","abstract_excerpt":"In the past decade, the DBpedia community has put significant amount of effort on developing technical infrastructure and methods for efficient extraction of structured information from Wikipedia. These efforts have been primarily focused on harvesting, refinement and publishing semi-structured information found in Wikipedia articles, such as information from infoboxes, categorization information, images, wikilinks and citations. Nevertheless, still vast amount of valuable information is contained in the unstructured Wikipedia article texts. In this paper, we present DBpedia NIF - a large-scal"},"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":"1812.10315","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-26T13:50:50Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"79f75e599d6a129379319ac7303c88e2692b10641505c39791a6ad55bf70b843","abstract_canon_sha256":"50871a03e4b534a95db1cc6a025b4dab7736f9e50e2603faf822d095f0f1880c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:24.484804Z","signature_b64":"5VvjyXcZD/VHSxitPh0AdXr0en+it2uAuJBH6FdWYJ79+Lwtigd3JB81D9nmVrUwuV0JHT/xQG4pqcLyOyFOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c51fa6d91b976b1cd233ba6d20b5d4da9585b1119be4c411af3b6f576b5167d4","last_reissued_at":"2026-05-17T23:57:24.484106Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:24.484106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DBpedia NIF: Open, Large-Scale and Multilingual Knowledge Extraction Corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Amit Kirschenbaum, Julio Hernandez, Markus Ackermann, Milan Dojchinovski, Sebastian Hellmann","submitted_at":"2018-12-26T13:50:50Z","abstract_excerpt":"In the past decade, the DBpedia community has put significant amount of effort on developing technical infrastructure and methods for efficient extraction of structured information from Wikipedia. These efforts have been primarily focused on harvesting, refinement and publishing semi-structured information found in Wikipedia articles, such as information from infoboxes, categorization information, images, wikilinks and citations. Nevertheless, still vast amount of valuable information is contained in the unstructured Wikipedia article texts. In this paper, we present DBpedia NIF - a large-scal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.10315","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":""},"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":"1812.10315","created_at":"2026-05-17T23:57:24.484219+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.10315v1","created_at":"2026-05-17T23:57:24.484219+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.10315","created_at":"2026-05-17T23:57:24.484219+00:00"},{"alias_kind":"pith_short_12","alias_value":"YUP2NWI3S5VR","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"YUP2NWI3S5VRZURT","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"YUP2NWI3","created_at":"2026-05-18T12:33:04.347982+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/YUP2NWI3S5VRZURTXJWSBNOU3K","json":"https://pith.science/pith/YUP2NWI3S5VRZURTXJWSBNOU3K.json","graph_json":"https://pith.science/api/pith-number/YUP2NWI3S5VRZURTXJWSBNOU3K/graph.json","events_json":"https://pith.science/api/pith-number/YUP2NWI3S5VRZURTXJWSBNOU3K/events.json","paper":"https://pith.science/paper/YUP2NWI3"},"agent_actions":{"view_html":"https://pith.science/pith/YUP2NWI3S5VRZURTXJWSBNOU3K","download_json":"https://pith.science/pith/YUP2NWI3S5VRZURTXJWSBNOU3K.json","view_paper":"https://pith.science/paper/YUP2NWI3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.10315&json=true","fetch_graph":"https://pith.science/api/pith-number/YUP2NWI3S5VRZURTXJWSBNOU3K/graph.json","fetch_events":"https://pith.science/api/pith-number/YUP2NWI3S5VRZURTXJWSBNOU3K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YUP2NWI3S5VRZURTXJWSBNOU3K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YUP2NWI3S5VRZURTXJWSBNOU3K/action/storage_attestation","attest_author":"https://pith.science/pith/YUP2NWI3S5VRZURTXJWSBNOU3K/action/author_attestation","sign_citation":"https://pith.science/pith/YUP2NWI3S5VRZURTXJWSBNOU3K/action/citation_signature","submit_replication":"https://pith.science/pith/YUP2NWI3S5VRZURTXJWSBNOU3K/action/replication_record"}},"created_at":"2026-05-17T23:57:24.484219+00:00","updated_at":"2026-05-17T23:57:24.484219+00:00"}