{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:H5NTZJSHHEWNW45Q3Z2AMVHYHU","short_pith_number":"pith:H5NTZJSH","canonical_record":{"source":{"id":"2210.04261","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-09T13:30:42Z","cross_cats_sorted":[],"title_canon_sha256":"0d6525610f72feb725f4e62940313479673566a54ad0c90132347d763631a209","abstract_canon_sha256":"6b6e50ccc19f598d191ba1e15e25aeb00ea766c3df964ed0b6b2cfb67fbea696"},"schema_version":"1.0"},"canonical_sha256":"3f5b3ca647392cdb73b0de740654f83d1af962dcb7e8a5c85d94d9aeaf4d8c84","source":{"kind":"arxiv","id":"2210.04261","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.04261","created_at":"2026-07-05T08:11:38Z"},{"alias_kind":"arxiv_version","alias_value":"2210.04261v2","created_at":"2026-07-05T08:11:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04261","created_at":"2026-07-05T08:11:38Z"},{"alias_kind":"pith_short_12","alias_value":"H5NTZJSHHEWN","created_at":"2026-07-05T08:11:38Z"},{"alias_kind":"pith_short_16","alias_value":"H5NTZJSHHEWNW45Q","created_at":"2026-07-05T08:11:38Z"},{"alias_kind":"pith_short_8","alias_value":"H5NTZJSH","created_at":"2026-07-05T08:11:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:H5NTZJSHHEWNW45Q3Z2AMVHYHU","target":"record","payload":{"canonical_record":{"source":{"id":"2210.04261","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-09T13:30:42Z","cross_cats_sorted":[],"title_canon_sha256":"0d6525610f72feb725f4e62940313479673566a54ad0c90132347d763631a209","abstract_canon_sha256":"6b6e50ccc19f598d191ba1e15e25aeb00ea766c3df964ed0b6b2cfb67fbea696"},"schema_version":"1.0"},"canonical_sha256":"3f5b3ca647392cdb73b0de740654f83d1af962dcb7e8a5c85d94d9aeaf4d8c84","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:38.181529Z","signature_b64":"zE+9vwir4/t+vonBpx6fH0hC+E6JG/NBtZVeCr21/sTZYplc6tFC26ey1/PX2FmTE3kmxbFDyGEEiLy41oBIDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f5b3ca647392cdb73b0de740654f83d1af962dcb7e8a5c85d94d9aeaf4d8c84","last_reissued_at":"2026-07-05T08:11:38.181106Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:38.181106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.04261","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:11:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/aiw/3b5Dad8gdsopz+jAtyhz84AsXZ7/N/mkhJDzUzm+8l/hcEQhFcXNmQY2EBIbynm3MunxR7z8q4PYHR3Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:58:00.349162Z"},"content_sha256":"43daeb749de8ce59fa90affe29bff66683e83ca9d9cffb90370438e736cbf863","schema_version":"1.0","event_id":"sha256:43daeb749de8ce59fa90affe29bff66683e83ca9d9cffb90370438e736cbf863"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:H5NTZJSHHEWNW45Q3Z2AMVHYHU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Noise-Robust De-Duplication at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Emily Silcock, Jinglin Yang, Luca D'Amico-Wong, Melissa Dell","submitted_at":"2022-10-09T13:30:42Z","abstract_excerpt":"Identifying near duplicates within large, noisy text corpora has a myriad of applications that range from de-duplicating training datasets, reducing privacy risk, and evaluating test set leakage, to identifying reproduced news articles and literature within large corpora. Across these diverse applications, the overwhelming majority of work relies on N-grams. Limited efforts have been made to evaluate how well N-gram methods perform, in part because it is unclear how one could create an unbiased evaluation dataset for a massive corpus. This study uses the unique timeliness of historical news wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04261","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2210.04261/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T08:11:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gIlWNWPdAnWrcNLjYwi0mrc13Gm8qAo0sXBafrQDcQdEQ79D2TbHRtgdp9Uk9o7dJBMRCYrBKCqnKNVq0Ca5BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:58:00.349663Z"},"content_sha256":"ebdf70629e189bb3920ba0763ce24d2e6ba8ef2954961840ae4067d3200dc2af","schema_version":"1.0","event_id":"sha256:ebdf70629e189bb3920ba0763ce24d2e6ba8ef2954961840ae4067d3200dc2af"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H5NTZJSHHEWNW45Q3Z2AMVHYHU/bundle.json","state_url":"https://pith.science/pith/H5NTZJSHHEWNW45Q3Z2AMVHYHU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H5NTZJSHHEWNW45Q3Z2AMVHYHU/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":"2026-08-03T19:58:00Z","links":{"resolver":"https://pith.science/pith/H5NTZJSHHEWNW45Q3Z2AMVHYHU","bundle":"https://pith.science/pith/H5NTZJSHHEWNW45Q3Z2AMVHYHU/bundle.json","state":"https://pith.science/pith/H5NTZJSHHEWNW45Q3Z2AMVHYHU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H5NTZJSHHEWNW45Q3Z2AMVHYHU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:H5NTZJSHHEWNW45Q3Z2AMVHYHU","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":"6b6e50ccc19f598d191ba1e15e25aeb00ea766c3df964ed0b6b2cfb67fbea696","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-09T13:30:42Z","title_canon_sha256":"0d6525610f72feb725f4e62940313479673566a54ad0c90132347d763631a209"},"schema_version":"1.0","source":{"id":"2210.04261","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.04261","created_at":"2026-07-05T08:11:38Z"},{"alias_kind":"arxiv_version","alias_value":"2210.04261v2","created_at":"2026-07-05T08:11:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04261","created_at":"2026-07-05T08:11:38Z"},{"alias_kind":"pith_short_12","alias_value":"H5NTZJSHHEWN","created_at":"2026-07-05T08:11:38Z"},{"alias_kind":"pith_short_16","alias_value":"H5NTZJSHHEWNW45Q","created_at":"2026-07-05T08:11:38Z"},{"alias_kind":"pith_short_8","alias_value":"H5NTZJSH","created_at":"2026-07-05T08:11:38Z"}],"graph_snapshots":[{"event_id":"sha256:ebdf70629e189bb3920ba0763ce24d2e6ba8ef2954961840ae4067d3200dc2af","target":"graph","created_at":"2026-07-05T08:11:38Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2210.04261/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Identifying near duplicates within large, noisy text corpora has a myriad of applications that range from de-duplicating training datasets, reducing privacy risk, and evaluating test set leakage, to identifying reproduced news articles and literature within large corpora. Across these diverse applications, the overwhelming majority of work relies on N-grams. Limited efforts have been made to evaluate how well N-gram methods perform, in part because it is unclear how one could create an unbiased evaluation dataset for a massive corpus. This study uses the unique timeliness of historical news wi","authors_text":"Emily Silcock, Jinglin Yang, Luca D'Amico-Wong, Melissa Dell","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-09T13:30:42Z","title":"Noise-Robust De-Duplication at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04261","kind":"arxiv","version":2},"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":"sha256:43daeb749de8ce59fa90affe29bff66683e83ca9d9cffb90370438e736cbf863","target":"record","created_at":"2026-07-05T08:11:38Z","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":"6b6e50ccc19f598d191ba1e15e25aeb00ea766c3df964ed0b6b2cfb67fbea696","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-09T13:30:42Z","title_canon_sha256":"0d6525610f72feb725f4e62940313479673566a54ad0c90132347d763631a209"},"schema_version":"1.0","source":{"id":"2210.04261","kind":"arxiv","version":2}},"canonical_sha256":"3f5b3ca647392cdb73b0de740654f83d1af962dcb7e8a5c85d94d9aeaf4d8c84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f5b3ca647392cdb73b0de740654f83d1af962dcb7e8a5c85d94d9aeaf4d8c84","first_computed_at":"2026-07-05T08:11:38.181106Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:11:38.181106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zE+9vwir4/t+vonBpx6fH0hC+E6JG/NBtZVeCr21/sTZYplc6tFC26ey1/PX2FmTE3kmxbFDyGEEiLy41oBIDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:11:38.181529Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.04261","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43daeb749de8ce59fa90affe29bff66683e83ca9d9cffb90370438e736cbf863","sha256:ebdf70629e189bb3920ba0763ce24d2e6ba8ef2954961840ae4067d3200dc2af"],"state_sha256":"28a42ae5afbc3c08ce11d43cd67d1879ba01e4760af49bd99b8dc2533a8f5691"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"10fhSSdiRHhhXJjFb6s5tOBj7NYyvwukubRPZdyApJ9qbbS5RecDDR3b2UgpBq/w+00L48EGknks/b2npDaqAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:58:00.354836Z","bundle_sha256":"a958a7496cbc6bb1595992431ed7d6faa44d79f1b01fd429e1a3c30dab2f716a"}}