{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:NOAN6KSLFLKME4JNXULNFHTHP5","short_pith_number":"pith:NOAN6KSL","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"},"canonical_sha256":"6b80df2a4b2ad4c2712dbd16d29e677f464b366c8bda1116da552b07377b75fa","source":{"kind":"arxiv","id":"1809.00221","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.00221","created_at":"2026-05-18T00:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"1809.00221v1","created_at":"2026-05-18T00:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.00221","created_at":"2026-05-18T00:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"NOAN6KSLFLKM","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NOAN6KSLFLKME4JN","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NOAN6KSL","created_at":"2026-05-18T12:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:NOAN6KSLFLKME4JNXULNFHTHP5","target":"record","payload":{"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"},"canonical_sha256":"6b80df2a4b2ad4c2712dbd16d29e677f464b366c8bda1116da552b07377b75fa","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"},"source_kind":"arxiv","source_id":"1809.00221","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:05:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ArGkQgduI9BiJYiLAHsYgyClR4asDUUNjdblUV+7ntyW1U24+lTKGjIiTnwmdF7C9uBrnVRmUSDs0wMehEowCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T10:42:23.674151Z"},"content_sha256":"7fac73f4e9e565ff4077936486c09c462330b21e74377f8457cbd38ae93b09ad","schema_version":"1.0","event_id":"sha256:7fac73f4e9e565ff4077936486c09c462330b21e74377f8457cbd38ae93b09ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:NOAN6KSLFLKME4JNXULNFHTHP5","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:05:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"USu03eFJA3M1QLJARD+QfXUIvJZdoKV3h2L8XXNDEa+vObD7c/7UJATE3hOo7I9fnnc74/rUP6zW+xhWCVw6CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T10:42:23.674513Z"},"content_sha256":"e5abccf6340dfef8bdb60ab9e85343eb0342f65eab564be582ff63b39d4fb87b","schema_version":"1.0","event_id":"sha256:e5abccf6340dfef8bdb60ab9e85343eb0342f65eab564be582ff63b39d4fb87b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NOAN6KSLFLKME4JNXULNFHTHP5/bundle.json","state_url":"https://pith.science/pith/NOAN6KSLFLKME4JNXULNFHTHP5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NOAN6KSLFLKME4JNXULNFHTHP5/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":"2026-06-26T10:42:23Z","links":{"resolver":"https://pith.science/pith/NOAN6KSLFLKME4JNXULNFHTHP5","bundle":"https://pith.science/pith/NOAN6KSLFLKME4JNXULNFHTHP5/bundle.json","state":"https://pith.science/pith/NOAN6KSLFLKME4JNXULNFHTHP5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NOAN6KSLFLKME4JNXULNFHTHP5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:NOAN6KSLFLKME4JNXULNFHTHP5","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":"7e4a6072ac21838300045b1916debeb5e29fca50d740f705a4d6b9a752d2029b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-09-01T16:54:15Z","title_canon_sha256":"3c4767a5a837309a4e100d7e05e09f9371a4495406487003906afb45d721ea54"},"schema_version":"1.0","source":{"id":"1809.00221","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.00221","created_at":"2026-05-18T00:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"1809.00221v1","created_at":"2026-05-18T00:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.00221","created_at":"2026-05-18T00:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"NOAN6KSLFLKM","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NOAN6KSLFLKME4JN","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NOAN6KSL","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:e5abccf6340dfef8bdb60ab9e85343eb0342f65eab564be582ff63b39d4fb87b","target":"graph","created_at":"2026-05-18T00:05:44Z","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"},"paper":{"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","authors_text":"Chris Biemann, Gregor Wiedemann, Seid Muhie Yimam","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-09-01T16:54:15Z","title":"A Multilingual Information Extraction Pipeline for Investigative Journalism"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.00221","kind":"arxiv","version":1},"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":"sha256:7fac73f4e9e565ff4077936486c09c462330b21e74377f8457cbd38ae93b09ad","target":"record","created_at":"2026-05-18T00:05:44Z","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":"7e4a6072ac21838300045b1916debeb5e29fca50d740f705a4d6b9a752d2029b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-09-01T16:54:15Z","title_canon_sha256":"3c4767a5a837309a4e100d7e05e09f9371a4495406487003906afb45d721ea54"},"schema_version":"1.0","source":{"id":"1809.00221","kind":"arxiv","version":1}},"canonical_sha256":"6b80df2a4b2ad4c2712dbd16d29e677f464b366c8bda1116da552b07377b75fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b80df2a4b2ad4c2712dbd16d29e677f464b366c8bda1116da552b07377b75fa","first_computed_at":"2026-05-18T00:05:44.993814Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:44.993814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CkL/mBW5k56+53rq2yxXPWScQIs4VUFsxsRKTvyoZxP/5iW3G5j/1VhTRSNAuwC56i2awlj8hqDoEzO528stCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:44.994599Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.00221","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7fac73f4e9e565ff4077936486c09c462330b21e74377f8457cbd38ae93b09ad","sha256:e5abccf6340dfef8bdb60ab9e85343eb0342f65eab564be582ff63b39d4fb87b"],"state_sha256":"1d393c54caa28b7013133a1323d51fdab631a4743fac574e31e6a65d64e12039"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dEF4JY+ECvYs6BM+6H0R3QyyQDhSPfogryoI6Ki2iJP+Vd1TLQ4hCBr42DNWGAq0M8tHEcjqeLQtjQdKwVZvAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T10:42:23.676432Z","bundle_sha256":"48bf128a202a1597afd5c28cbcb1ed5d6a26a26202a6f679bed810536b8c42c5"}}