{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:K6VU4XZVVMU2INGHGOX3VUKUVR","short_pith_number":"pith:K6VU4XZV","canonical_record":{"source":{"id":"1704.04370","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2017-04-14T09:24:04Z","cross_cats_sorted":[],"title_canon_sha256":"53b4da5521b9201ec9bb8b3e63b3eac88897a54aa4da7a0502680daf8d3342c3","abstract_canon_sha256":"c50ef515639adea509c62b415040fda9e537e34526e3bb820efe1e939f6f8210"},"schema_version":"1.0"},"canonical_sha256":"57ab4e5f35ab29a434c733afbad154ac7ba86d7e556dbe1bc648e72918d00afc","source":{"kind":"arxiv","id":"1704.04370","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.04370","created_at":"2026-07-05T08:15:22Z"},{"alias_kind":"arxiv_version","alias_value":"1704.04370v4","created_at":"2026-07-05T08:15:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.04370","created_at":"2026-07-05T08:15:22Z"},{"alias_kind":"pith_short_12","alias_value":"K6VU4XZVVMU2","created_at":"2026-07-05T08:15:22Z"},{"alias_kind":"pith_short_16","alias_value":"K6VU4XZVVMU2INGH","created_at":"2026-07-05T08:15:22Z"},{"alias_kind":"pith_short_8","alias_value":"K6VU4XZV","created_at":"2026-07-05T08:15:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:K6VU4XZVVMU2INGHGOX3VUKUVR","target":"record","payload":{"canonical_record":{"source":{"id":"1704.04370","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2017-04-14T09:24:04Z","cross_cats_sorted":[],"title_canon_sha256":"53b4da5521b9201ec9bb8b3e63b3eac88897a54aa4da7a0502680daf8d3342c3","abstract_canon_sha256":"c50ef515639adea509c62b415040fda9e537e34526e3bb820efe1e939f6f8210"},"schema_version":"1.0"},"canonical_sha256":"57ab4e5f35ab29a434c733afbad154ac7ba86d7e556dbe1bc648e72918d00afc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:22.746372Z","signature_b64":"c+PUVjPiSvqR+D67o/KRjpOK/39bw6B10C2LHMzrfFKaQnfhpmPBQ8DhDFUve2NOr+AIDmFgmjyIysXlcR4mDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57ab4e5f35ab29a434c733afbad154ac7ba86d7e556dbe1bc648e72918d00afc","last_reissued_at":"2026-07-05T08:15:22.745944Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:22.745944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.04370","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":"2026-07-05T08:15:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"inY1Otq0WanVFiTES0n8/0BnObognf/HI+WHt/wKCDs3cSzS9uA0UTmy2WdW4xkY1WeqJUgvWrVBakfR7vLeCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T03:30:11.654949Z"},"content_sha256":"0235e402eb57b7517f5bfc50e0c043bd4dc390c7bf68fb918dc2c452ee924b8d","schema_version":"1.0","event_id":"sha256:0235e402eb57b7517f5bfc50e0c043bd4dc390c7bf68fb918dc2c452ee924b8d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:K6VU4XZVVMU2INGHGOX3VUKUVR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fast Similarity Sketching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Jakob B{\\ae}k Tejs Houen, Mathias B{\\ae}k Tejs Langhede, Mikkel Thorup, S{\\o}ren Dahlgaard","submitted_at":"2017-04-14T09:24:04Z","abstract_excerpt":"We consider the $\\textit{Similarity Sketching}$ problem: Given a universe $[u] = \\{0,\\ldots, u-1\\}$ we want a random function $S$ mapping subsets $A\\subseteq [u]$ into vectors $S(A)$ of size $t$, such that the Jaccard similarity $J(A,B) = |A\\cap B|/|A\\cup B|$ between sets $A$ and $B$ is preserved. More precisely, define $X_i = [S(A)[i] =\n  S(B)[i]]$ and $X = \\sum_{i\\in [t]} X_i$. We want $E[X_i]=J(A,B)$, and we want $X$ to be strongly concentrated around $E[X] = t \\cdot J(A,B)$ (i.e. Chernoff-style bounds). This is a fundamental problem which has found numerous applications in data mining, lar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.04370","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1704.04370/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":"2026-07-05T08:15:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6oL8eTW4TQmFjkRKxj5yZbEB24Ab7hUErJT2L1t42N58f+nIW02tPOux1Q8TEAZzEE2ZnBmQBJJb0rN1PRPWBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T03:30:11.655291Z"},"content_sha256":"307b715c1878d08d4f0cf51a986330838275ba0cb82e7aa7c3cdceaf1859b940","schema_version":"1.0","event_id":"sha256:307b715c1878d08d4f0cf51a986330838275ba0cb82e7aa7c3cdceaf1859b940"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K6VU4XZVVMU2INGHGOX3VUKUVR/bundle.json","state_url":"https://pith.science/pith/K6VU4XZVVMU2INGHGOX3VUKUVR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K6VU4XZVVMU2INGHGOX3VUKUVR/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":"2026-08-21T03:30:11Z","links":{"resolver":"https://pith.science/pith/K6VU4XZVVMU2INGHGOX3VUKUVR","bundle":"https://pith.science/pith/K6VU4XZVVMU2INGHGOX3VUKUVR/bundle.json","state":"https://pith.science/pith/K6VU4XZVVMU2INGHGOX3VUKUVR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K6VU4XZVVMU2INGHGOX3VUKUVR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:K6VU4XZVVMU2INGHGOX3VUKUVR","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":"c50ef515639adea509c62b415040fda9e537e34526e3bb820efe1e939f6f8210","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2017-04-14T09:24:04Z","title_canon_sha256":"53b4da5521b9201ec9bb8b3e63b3eac88897a54aa4da7a0502680daf8d3342c3"},"schema_version":"1.0","source":{"id":"1704.04370","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.04370","created_at":"2026-07-05T08:15:22Z"},{"alias_kind":"arxiv_version","alias_value":"1704.04370v4","created_at":"2026-07-05T08:15:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.04370","created_at":"2026-07-05T08:15:22Z"},{"alias_kind":"pith_short_12","alias_value":"K6VU4XZVVMU2","created_at":"2026-07-05T08:15:22Z"},{"alias_kind":"pith_short_16","alias_value":"K6VU4XZVVMU2INGH","created_at":"2026-07-05T08:15:22Z"},{"alias_kind":"pith_short_8","alias_value":"K6VU4XZV","created_at":"2026-07-05T08:15:22Z"}],"graph_snapshots":[{"event_id":"sha256:307b715c1878d08d4f0cf51a986330838275ba0cb82e7aa7c3cdceaf1859b940","target":"graph","created_at":"2026-07-05T08:15:22Z","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/1704.04370/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the $\\textit{Similarity Sketching}$ problem: Given a universe $[u] = \\{0,\\ldots, u-1\\}$ we want a random function $S$ mapping subsets $A\\subseteq [u]$ into vectors $S(A)$ of size $t$, such that the Jaccard similarity $J(A,B) = |A\\cap B|/|A\\cup B|$ between sets $A$ and $B$ is preserved. More precisely, define $X_i = [S(A)[i] =\n  S(B)[i]]$ and $X = \\sum_{i\\in [t]} X_i$. We want $E[X_i]=J(A,B)$, and we want $X$ to be strongly concentrated around $E[X] = t \\cdot J(A,B)$ (i.e. Chernoff-style bounds). This is a fundamental problem which has found numerous applications in data mining, lar","authors_text":"Jakob B{\\ae}k Tejs Houen, Mathias B{\\ae}k Tejs Langhede, Mikkel Thorup, S{\\o}ren Dahlgaard","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2017-04-14T09:24:04Z","title":"Fast Similarity Sketching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.04370","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":"sha256:0235e402eb57b7517f5bfc50e0c043bd4dc390c7bf68fb918dc2c452ee924b8d","target":"record","created_at":"2026-07-05T08:15:22Z","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":"c50ef515639adea509c62b415040fda9e537e34526e3bb820efe1e939f6f8210","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2017-04-14T09:24:04Z","title_canon_sha256":"53b4da5521b9201ec9bb8b3e63b3eac88897a54aa4da7a0502680daf8d3342c3"},"schema_version":"1.0","source":{"id":"1704.04370","kind":"arxiv","version":4}},"canonical_sha256":"57ab4e5f35ab29a434c733afbad154ac7ba86d7e556dbe1bc648e72918d00afc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57ab4e5f35ab29a434c733afbad154ac7ba86d7e556dbe1bc648e72918d00afc","first_computed_at":"2026-07-05T08:15:22.745944Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:15:22.745944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c+PUVjPiSvqR+D67o/KRjpOK/39bw6B10C2LHMzrfFKaQnfhpmPBQ8DhDFUve2NOr+AIDmFgmjyIysXlcR4mDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:15:22.746372Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.04370","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0235e402eb57b7517f5bfc50e0c043bd4dc390c7bf68fb918dc2c452ee924b8d","sha256:307b715c1878d08d4f0cf51a986330838275ba0cb82e7aa7c3cdceaf1859b940"],"state_sha256":"f00af6819210f7cd8612bb7d74d9838f1959fb426cc1e321641112c18a4c097a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nd8QSMgqJO6PGIyi1esLgERPyPcni30uxoPGnlhqo0kWXr1NyYyevER9wNIUkyAIoDvwcpX/UqhEPOeJpdDnCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T03:30:11.658409Z","bundle_sha256":"420c6986a3631fcb20f6dfb3aad08d45fec5d46b078d35fc0f1fd2bcf85dfea1"}}