{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2006:ZLKQZFP3VJI6JGWZJ6EKNCOH42","short_pith_number":"pith:ZLKQZFP3","canonical_record":{"source":{"id":"cs/0610010","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/3.0/","primary_cat":"cs.DB","submitted_at":"2006-10-03T18:04:22Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7b085531ca75a745423507e026c8dc72fe0f009b5eb989e4b630b69a3e2a5e05","abstract_canon_sha256":"be30ae5293f736a9b6873d2ccb185d1cba77e5e4e63aea1090025f2183243531"},"schema_version":"1.0"},"canonical_sha256":"cad50c95fbaa51e49ad94f88a689c7e6b160a7122d87ed57c6427995859002f7","source":{"kind":"arxiv","id":"cs/0610010","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"cs/0610010","created_at":"2026-05-18T03:00:11Z"},{"alias_kind":"arxiv_version","alias_value":"cs/0610010v4","created_at":"2026-05-18T03:00:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cs/0610010","created_at":"2026-05-18T03:00:11Z"},{"alias_kind":"pith_short_12","alias_value":"ZLKQZFP3VJI6","created_at":"2026-05-18T12:25:54Z"},{"alias_kind":"pith_short_16","alias_value":"ZLKQZFP3VJI6JGWZ","created_at":"2026-05-18T12:25:54Z"},{"alias_kind":"pith_short_8","alias_value":"ZLKQZFP3","created_at":"2026-05-18T12:25:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2006:ZLKQZFP3VJI6JGWZJ6EKNCOH42","target":"record","payload":{"canonical_record":{"source":{"id":"cs/0610010","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/3.0/","primary_cat":"cs.DB","submitted_at":"2006-10-03T18:04:22Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7b085531ca75a745423507e026c8dc72fe0f009b5eb989e4b630b69a3e2a5e05","abstract_canon_sha256":"be30ae5293f736a9b6873d2ccb185d1cba77e5e4e63aea1090025f2183243531"},"schema_version":"1.0"},"canonical_sha256":"cad50c95fbaa51e49ad94f88a689c7e6b160a7122d87ed57c6427995859002f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:00:11.756162Z","signature_b64":"ntXLkRgwOYMvWIn4yhR2OtjRM/BPczQs1nWCLu1yzbpsD6eKz4EZ7/BfH0SM++a3C+9FtCoskxOmXPNVcO9fDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cad50c95fbaa51e49ad94f88a689c7e6b160a7122d87ed57c6427995859002f7","last_reissued_at":"2026-05-18T03:00:11.755353Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:00:11.755353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"cs/0610010","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:00:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VOfKE1oWpNfdD1vVVgAutv2TAJrlOrZEwuEmXb+jW1c3VGooYPsEEJam8AIp+xcJbCLc8YLEu4K2Pzcra9InCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T07:10:26.376223Z"},"content_sha256":"63881df8babe6718bea9af0ecfe76bbf573cc8ff3ff675466c40118d3f6dd1ce","schema_version":"1.0","event_id":"sha256:63881df8babe6718bea9af0ecfe76bbf573cc8ff3ff675466c40118d3f6dd1ce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2006:ZLKQZFP3VJI6JGWZJ6EKNCOH42","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"One-Pass, One-Hash n-Gram Statistics Estimation","license":"http://creativecommons.org/licenses/by/3.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.DB","authors_text":"Daniel Lemire, Owen Kaser","submitted_at":"2006-10-03T18:04:22Z","abstract_excerpt":"In multimedia, text or bioinformatics databases, applications query sequences of n consecutive symbols called n-grams. Estimating the number of distinct n-grams is a view-size estimation problem. While view sizes can be estimated by sampling under statistical assumptions, we desire an unassuming algorithm with universally valid accuracy bounds. Most related work has focused on repeatedly hashing the data, which is prohibitive for large data sources. We prove that a one-pass one-hash algorithm is sufficient for accurate estimates if the hashing is sufficiently independent. To reduce costs furth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cs/0610010","kind":"arxiv","version":4},"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":"2026-05-18T03:00:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8anqBSwopKDGNb25sUxu93+z6laHe511v38Lt5FBme656pK/zmwPbEsQSI1nzQRLJi2QIAtVB73bQ2XAqBq8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T07:10:26.376577Z"},"content_sha256":"45caa3d8cf553178b54ef57d52ca3e2da4edf846c2967095f0755a60339d66a2","schema_version":"1.0","event_id":"sha256:45caa3d8cf553178b54ef57d52ca3e2da4edf846c2967095f0755a60339d66a2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZLKQZFP3VJI6JGWZJ6EKNCOH42/bundle.json","state_url":"https://pith.science/pith/ZLKQZFP3VJI6JGWZJ6EKNCOH42/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZLKQZFP3VJI6JGWZJ6EKNCOH42/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":"2026-06-27T07:10:26Z","links":{"resolver":"https://pith.science/pith/ZLKQZFP3VJI6JGWZJ6EKNCOH42","bundle":"https://pith.science/pith/ZLKQZFP3VJI6JGWZJ6EKNCOH42/bundle.json","state":"https://pith.science/pith/ZLKQZFP3VJI6JGWZJ6EKNCOH42/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZLKQZFP3VJI6JGWZJ6EKNCOH42/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2006:ZLKQZFP3VJI6JGWZJ6EKNCOH42","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":"be30ae5293f736a9b6873d2ccb185d1cba77e5e4e63aea1090025f2183243531","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/3.0/","primary_cat":"cs.DB","submitted_at":"2006-10-03T18:04:22Z","title_canon_sha256":"7b085531ca75a745423507e026c8dc72fe0f009b5eb989e4b630b69a3e2a5e05"},"schema_version":"1.0","source":{"id":"cs/0610010","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"cs/0610010","created_at":"2026-05-18T03:00:11Z"},{"alias_kind":"arxiv_version","alias_value":"cs/0610010v4","created_at":"2026-05-18T03:00:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cs/0610010","created_at":"2026-05-18T03:00:11Z"},{"alias_kind":"pith_short_12","alias_value":"ZLKQZFP3VJI6","created_at":"2026-05-18T12:25:54Z"},{"alias_kind":"pith_short_16","alias_value":"ZLKQZFP3VJI6JGWZ","created_at":"2026-05-18T12:25:54Z"},{"alias_kind":"pith_short_8","alias_value":"ZLKQZFP3","created_at":"2026-05-18T12:25:54Z"}],"graph_snapshots":[{"event_id":"sha256:45caa3d8cf553178b54ef57d52ca3e2da4edf846c2967095f0755a60339d66a2","target":"graph","created_at":"2026-05-18T03:00:11Z","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":"In multimedia, text or bioinformatics databases, applications query sequences of n consecutive symbols called n-grams. Estimating the number of distinct n-grams is a view-size estimation problem. While view sizes can be estimated by sampling under statistical assumptions, we desire an unassuming algorithm with universally valid accuracy bounds. Most related work has focused on repeatedly hashing the data, which is prohibitive for large data sources. We prove that a one-pass one-hash algorithm is sufficient for accurate estimates if the hashing is sufficiently independent. To reduce costs furth","authors_text":"Daniel Lemire, Owen Kaser","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/3.0/","primary_cat":"cs.DB","submitted_at":"2006-10-03T18:04:22Z","title":"One-Pass, One-Hash n-Gram Statistics Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cs/0610010","kind":"arxiv","version":4},"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":"sha256:63881df8babe6718bea9af0ecfe76bbf573cc8ff3ff675466c40118d3f6dd1ce","target":"record","created_at":"2026-05-18T03:00:11Z","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":"be30ae5293f736a9b6873d2ccb185d1cba77e5e4e63aea1090025f2183243531","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/3.0/","primary_cat":"cs.DB","submitted_at":"2006-10-03T18:04:22Z","title_canon_sha256":"7b085531ca75a745423507e026c8dc72fe0f009b5eb989e4b630b69a3e2a5e05"},"schema_version":"1.0","source":{"id":"cs/0610010","kind":"arxiv","version":4}},"canonical_sha256":"cad50c95fbaa51e49ad94f88a689c7e6b160a7122d87ed57c6427995859002f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cad50c95fbaa51e49ad94f88a689c7e6b160a7122d87ed57c6427995859002f7","first_computed_at":"2026-05-18T03:00:11.755353Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:00:11.755353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ntXLkRgwOYMvWIn4yhR2OtjRM/BPczQs1nWCLu1yzbpsD6eKz4EZ7/BfH0SM++a3C+9FtCoskxOmXPNVcO9fDw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:00:11.756162Z","signed_message":"canonical_sha256_bytes"},"source_id":"cs/0610010","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63881df8babe6718bea9af0ecfe76bbf573cc8ff3ff675466c40118d3f6dd1ce","sha256:45caa3d8cf553178b54ef57d52ca3e2da4edf846c2967095f0755a60339d66a2"],"state_sha256":"2ccf9cbd80a23974103a0901f98e9ca06ae3cb9f0ada2c3fda8fece53fb9f264"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iLoxVbSr7T89GnF3b53UhzQeE3gqAiBiUAq7MSyQF6XTUW+HtXYffXDD17eis3VrmbKoVNX9I50iiX0+w6OjAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T07:10:26.378384Z","bundle_sha256":"95d9ab9f97a7463952814b9921da66dc084322a5fdd76211742dd1239e37a0fd"}}