{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:NOAN6KSLFLKME4JNXULNFHTHP5","short_pith_number":"pith:NOAN6KSL","schema_version":"1.0","canonical_sha256":"6b80df2a4b2ad4c2712dbd16d29e677f464b366c8bda1116da552b07377b75fa","source":{"kind":"arxiv","id":"1809.00221","version":1},"attestation_state":"computed","paper":{"title":"A Multilingual Information Extraction Pipeline for Investigative Journalism","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Biemann, Gregor Wiedemann, Seid Muhie Yimam","submitted_at":"2018-09-01T16:54:15Z","abstract_excerpt":"We introduce an advanced information extraction pipeline to automatically process very large collections of unstructured textual data for the purpose of investigative journalism. The pipeline serves as a new input processor for the upcoming major release of our New/s/leak 2.0 software, which we develop in cooperation with a large German news organization. The use case is that journalists receive a large collection of files up to several Gigabytes containing unknown contents. Collections may originate either from official disclosures of documents, e.g. Freedom of Information Act requests, or un"},"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":"1809.00221","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-09-01T16:54:15Z","cross_cats_sorted":[],"title_canon_sha256":"3c4767a5a837309a4e100d7e05e09f9371a4495406487003906afb45d721ea54","abstract_canon_sha256":"7e4a6072ac21838300045b1916debeb5e29fca50d740f705a4d6b9a752d2029b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:44.994599Z","signature_b64":"CkL/mBW5k56+53rq2yxXPWScQIs4VUFsxsRKTvyoZxP/5iW3G5j/1VhTRSNAuwC56i2awlj8hqDoEzO528stCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b80df2a4b2ad4c2712dbd16d29e677f464b366c8bda1116da552b07377b75fa","last_reissued_at":"2026-05-18T00:05:44.993814Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:44.993814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Multilingual Information Extraction Pipeline for Investigative Journalism","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Biemann, Gregor Wiedemann, Seid Muhie Yimam","submitted_at":"2018-09-01T16:54:15Z","abstract_excerpt":"We introduce an advanced information extraction pipeline to automatically process very large collections of unstructured textual data for the purpose of investigative journalism. The pipeline serves as a new input processor for the upcoming major release of our New/s/leak 2.0 software, which we develop in cooperation with a large German news organization. The use case is that journalists receive a large collection of files up to several Gigabytes containing unknown contents. Collections may originate either from official disclosures of documents, e.g. Freedom of Information Act requests, or un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.00221","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":"1809.00221","created_at":"2026-05-18T00:05:44.993958+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.00221v1","created_at":"2026-05-18T00:05:44.993958+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.00221","created_at":"2026-05-18T00:05:44.993958+00:00"},{"alias_kind":"pith_short_12","alias_value":"NOAN6KSLFLKM","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"NOAN6KSLFLKME4JN","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"NOAN6KSL","created_at":"2026-05-18T12:32:40.477152+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/NOAN6KSLFLKME4JNXULNFHTHP5","json":"https://pith.science/pith/NOAN6KSLFLKME4JNXULNFHTHP5.json","graph_json":"https://pith.science/api/pith-number/NOAN6KSLFLKME4JNXULNFHTHP5/graph.json","events_json":"https://pith.science/api/pith-number/NOAN6KSLFLKME4JNXULNFHTHP5/events.json","paper":"https://pith.science/paper/NOAN6KSL"},"agent_actions":{"view_html":"https://pith.science/pith/NOAN6KSLFLKME4JNXULNFHTHP5","download_json":"https://pith.science/pith/NOAN6KSLFLKME4JNXULNFHTHP5.json","view_paper":"https://pith.science/paper/NOAN6KSL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.00221&json=true","fetch_graph":"https://pith.science/api/pith-number/NOAN6KSLFLKME4JNXULNFHTHP5/graph.json","fetch_events":"https://pith.science/api/pith-number/NOAN6KSLFLKME4JNXULNFHTHP5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NOAN6KSLFLKME4JNXULNFHTHP5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NOAN6KSLFLKME4JNXULNFHTHP5/action/storage_attestation","attest_author":"https://pith.science/pith/NOAN6KSLFLKME4JNXULNFHTHP5/action/author_attestation","sign_citation":"https://pith.science/pith/NOAN6KSLFLKME4JNXULNFHTHP5/action/citation_signature","submit_replication":"https://pith.science/pith/NOAN6KSLFLKME4JNXULNFHTHP5/action/replication_record"}},"created_at":"2026-05-18T00:05:44.993958+00:00","updated_at":"2026-05-18T00:05:44.993958+00:00"}