{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:GTNCN6MIFDTS5UTJTVC54JGZNV","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":"f48544042d0047a3a6c3074806264a9f6306cc642ef2daa2e91ef3076b76c4b1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-12-21T16:05:04Z","title_canon_sha256":"0f10568e99d2818b77112a547cbec8994b6f587c7c4d3c3cab8f181b74f5b298"},"schema_version":"1.0","source":{"id":"1812.09221","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.09221","created_at":"2026-05-17T23:57:45Z"},{"alias_kind":"arxiv_version","alias_value":"1812.09221v1","created_at":"2026-05-17T23:57:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.09221","created_at":"2026-05-17T23:57:45Z"},{"alias_kind":"pith_short_12","alias_value":"GTNCN6MIFDTS","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GTNCN6MIFDTS5UTJ","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GTNCN6MI","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:2e8ca140d3572e8b2b118750f0e3314cb1ed0715ffe0c6dc23b6d21c9e21f4ee","target":"graph","created_at":"2026-05-17T23:57:45Z","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 study text reuse related to Wikipedia at scale by compiling the first corpus of text reuse cases within Wikipedia as well as without (i.e., reuse of Wikipedia text in a sample of the Common Crawl). To discover reuse beyond verbatim copy and paste, we employ state-of-the-art text reuse detection technology, scaling it for the first time to process the entire Wikipedia as part of a distributed retrieval pipeline. We further report on a pilot analysis of the 100 million reuse cases inside, and the 1.6 million reuse cases outside Wikipedia that we discovered. Text reuse inside Wikipedia gives r","authors_text":"Benno Stein, Henning Wachsmuth, Martin Potthast, Matthias Hagen, Michael V\\\"olske, Milad Alshomary, Tristan Licht","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-12-21T16:05:04Z","title":"Wikipedia Text Reuse: Within and Without"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.09221","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":"sha256:71e04a37fc3ca1e3399ad1dbbf299e323b15b9fdb054e5ace837d15486cf2791","target":"record","created_at":"2026-05-17T23:57:45Z","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":"f48544042d0047a3a6c3074806264a9f6306cc642ef2daa2e91ef3076b76c4b1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-12-21T16:05:04Z","title_canon_sha256":"0f10568e99d2818b77112a547cbec8994b6f587c7c4d3c3cab8f181b74f5b298"},"schema_version":"1.0","source":{"id":"1812.09221","kind":"arxiv","version":1}},"canonical_sha256":"34da26f98828e72ed2699d45de24d96d4e77412553494a4cfe281b54a576e54d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34da26f98828e72ed2699d45de24d96d4e77412553494a4cfe281b54a576e54d","first_computed_at":"2026-05-17T23:57:45.033654Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:57:45.033654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Pd8FfTyX/XntTC6Y1QoAlk1idOr2dBAPlpE7HyGexe9r03S/ccrYxGDE1qAyEfZTfHwKiGsw1W290SBEEdQICw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:57:45.034338Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.09221","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71e04a37fc3ca1e3399ad1dbbf299e323b15b9fdb054e5ace837d15486cf2791","sha256:2e8ca140d3572e8b2b118750f0e3314cb1ed0715ffe0c6dc23b6d21c9e21f4ee"],"state_sha256":"ab84a178e6c55b2a7e8cc44820c6a693a681cc35606f4cae0b27817095d1491d"}