{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:6HNHKLBTKCR7S7ZOAS4QHG5TQR","short_pith_number":"pith:6HNHKLBT","canonical_record":{"source":{"id":"1406.1143","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2014-06-04T18:59:00Z","cross_cats_sorted":["cs.CL","cs.DL","cs.SI"],"title_canon_sha256":"3e5af46d327dad8bffca34ed67333449cf80d46780a9d157908a5d68fcd1e9bb","abstract_canon_sha256":"5b7da59dc5eecdacd67bfcec835a3ea549af974acfa0b8d381c7776bb83db038"},"schema_version":"1.0"},"canonical_sha256":"f1da752c3350a3f97f2e04b9039bb38457e2d1d8ddf2adad2cc02c7e357b365e","source":{"kind":"arxiv","id":"1406.1143","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1406.1143","created_at":"2026-05-18T02:50:24Z"},{"alias_kind":"arxiv_version","alias_value":"1406.1143v1","created_at":"2026-05-18T02:50:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.1143","created_at":"2026-05-18T02:50:24Z"},{"alias_kind":"pith_short_12","alias_value":"6HNHKLBTKCR7","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_16","alias_value":"6HNHKLBTKCR7S7ZO","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_8","alias_value":"6HNHKLBT","created_at":"2026-05-18T12:28:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:6HNHKLBTKCR7S7ZOAS4QHG5TQR","target":"record","payload":{"canonical_record":{"source":{"id":"1406.1143","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2014-06-04T18:59:00Z","cross_cats_sorted":["cs.CL","cs.DL","cs.SI"],"title_canon_sha256":"3e5af46d327dad8bffca34ed67333449cf80d46780a9d157908a5d68fcd1e9bb","abstract_canon_sha256":"5b7da59dc5eecdacd67bfcec835a3ea549af974acfa0b8d381c7776bb83db038"},"schema_version":"1.0"},"canonical_sha256":"f1da752c3350a3f97f2e04b9039bb38457e2d1d8ddf2adad2cc02c7e357b365e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:50:24.768615Z","signature_b64":"BnjD0fPUBh7cKRtnqA+qprlgB4lI3WcWD6VWvCBNk8i9lbOxyhoDK/Jykc7ynKO3q8GKkzLZ10NJgmF1yZ2qAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1da752c3350a3f97f2e04b9039bb38457e2d1d8ddf2adad2cc02c7e357b365e","last_reissued_at":"2026-05-18T02:50:24.768086Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:50:24.768086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1406.1143","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":"2026-05-18T02:50:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"USuIiXHXY+OiCm/XN56FlryJMGVbespKBQfIkanaTeXT0DNPJbPmawfTW7v4jFm4p6/VKpDpIgkpJNswZLmLAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T12:56:27.003278Z"},"content_sha256":"4aafe9d9972717f1b8a34ee4ab84ad1764b0ae4a5f15b2cc652debb348d99e7f","schema_version":"1.0","event_id":"sha256:4aafe9d9972717f1b8a34ee4ab84ad1764b0ae4a5f15b2cc652debb348d99e7f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:6HNHKLBTKCR7S7ZOAS4QHG5TQR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Identifying Duplicate and Contradictory Information in Wikipedia","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.DL","cs.SI"],"primary_cat":"cs.IR","authors_text":"Jimmy Lin, Joshua Bradley, Samet Ayhan, Sarah Weissman","submitted_at":"2014-06-04T18:59:00Z","abstract_excerpt":"Our study identifies sentences in Wikipedia articles that are either identical or highly similar by applying techniques for near-duplicate detection of web pages. This is accomplished with a MapReduce implementation of minhash to identify clusters of sentences with high Jaccard similarity. We show that these clusters can be categorized into six different types, two of which are particularly interesting: identical sentences quantify the extent to which content in Wikipedia is copied and pasted, and near-duplicate sentences that state contradictory facts point to quality issues in Wikipedia."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.1143","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":"2026-05-18T02:50:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rjj7ao9pwGQY/wLMxNjjOQGHyGUcGMJ19KPMo3vXcP+ODVHnIf91SPYaeFbgjZ6m6s8n4MV105XIZ3e+GSg8BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T12:56:27.003670Z"},"content_sha256":"91eb03a9ed32d2af1b32d7f2f764d7353be2b68599d77f554eadf7e3591e7680","schema_version":"1.0","event_id":"sha256:91eb03a9ed32d2af1b32d7f2f764d7353be2b68599d77f554eadf7e3591e7680"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6HNHKLBTKCR7S7ZOAS4QHG5TQR/bundle.json","state_url":"https://pith.science/pith/6HNHKLBTKCR7S7ZOAS4QHG5TQR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6HNHKLBTKCR7S7ZOAS4QHG5TQR/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":"2026-06-01T12:56:27Z","links":{"resolver":"https://pith.science/pith/6HNHKLBTKCR7S7ZOAS4QHG5TQR","bundle":"https://pith.science/pith/6HNHKLBTKCR7S7ZOAS4QHG5TQR/bundle.json","state":"https://pith.science/pith/6HNHKLBTKCR7S7ZOAS4QHG5TQR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6HNHKLBTKCR7S7ZOAS4QHG5TQR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:6HNHKLBTKCR7S7ZOAS4QHG5TQR","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":"5b7da59dc5eecdacd67bfcec835a3ea549af974acfa0b8d381c7776bb83db038","cross_cats_sorted":["cs.CL","cs.DL","cs.SI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2014-06-04T18:59:00Z","title_canon_sha256":"3e5af46d327dad8bffca34ed67333449cf80d46780a9d157908a5d68fcd1e9bb"},"schema_version":"1.0","source":{"id":"1406.1143","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1406.1143","created_at":"2026-05-18T02:50:24Z"},{"alias_kind":"arxiv_version","alias_value":"1406.1143v1","created_at":"2026-05-18T02:50:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.1143","created_at":"2026-05-18T02:50:24Z"},{"alias_kind":"pith_short_12","alias_value":"6HNHKLBTKCR7","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_16","alias_value":"6HNHKLBTKCR7S7ZO","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_8","alias_value":"6HNHKLBT","created_at":"2026-05-18T12:28:16Z"}],"graph_snapshots":[{"event_id":"sha256:91eb03a9ed32d2af1b32d7f2f764d7353be2b68599d77f554eadf7e3591e7680","target":"graph","created_at":"2026-05-18T02:50:24Z","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":"Our study identifies sentences in Wikipedia articles that are either identical or highly similar by applying techniques for near-duplicate detection of web pages. This is accomplished with a MapReduce implementation of minhash to identify clusters of sentences with high Jaccard similarity. We show that these clusters can be categorized into six different types, two of which are particularly interesting: identical sentences quantify the extent to which content in Wikipedia is copied and pasted, and near-duplicate sentences that state contradictory facts point to quality issues in Wikipedia.","authors_text":"Jimmy Lin, Joshua Bradley, Samet Ayhan, Sarah Weissman","cross_cats":["cs.CL","cs.DL","cs.SI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2014-06-04T18:59:00Z","title":"Identifying Duplicate and Contradictory Information in Wikipedia"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.1143","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":"sha256:4aafe9d9972717f1b8a34ee4ab84ad1764b0ae4a5f15b2cc652debb348d99e7f","target":"record","created_at":"2026-05-18T02:50:24Z","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":"5b7da59dc5eecdacd67bfcec835a3ea549af974acfa0b8d381c7776bb83db038","cross_cats_sorted":["cs.CL","cs.DL","cs.SI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2014-06-04T18:59:00Z","title_canon_sha256":"3e5af46d327dad8bffca34ed67333449cf80d46780a9d157908a5d68fcd1e9bb"},"schema_version":"1.0","source":{"id":"1406.1143","kind":"arxiv","version":1}},"canonical_sha256":"f1da752c3350a3f97f2e04b9039bb38457e2d1d8ddf2adad2cc02c7e357b365e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1da752c3350a3f97f2e04b9039bb38457e2d1d8ddf2adad2cc02c7e357b365e","first_computed_at":"2026-05-18T02:50:24.768086Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:50:24.768086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BnjD0fPUBh7cKRtnqA+qprlgB4lI3WcWD6VWvCBNk8i9lbOxyhoDK/Jykc7ynKO3q8GKkzLZ10NJgmF1yZ2qAw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:50:24.768615Z","signed_message":"canonical_sha256_bytes"},"source_id":"1406.1143","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4aafe9d9972717f1b8a34ee4ab84ad1764b0ae4a5f15b2cc652debb348d99e7f","sha256:91eb03a9ed32d2af1b32d7f2f764d7353be2b68599d77f554eadf7e3591e7680"],"state_sha256":"b9506842f22b477e6964bec01a2fe149b7ace7c3532d261e8a3dff95eeaef143"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"keBTpLUHfMpWNBy74RjhEi2/TMRyXPdo/ZQ8ElqUzc2WZR/9bXfLBe06IFOf8txwV+J1CK7kxf53j76deIFiCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T12:56:27.005692Z","bundle_sha256":"11bac0a32aebe2ffd7e1bd8dea0811283b4cd642a88b8e2c5fcad243bb3045d8"}}