{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:K6VU4XZVVMU2INGHGOX3VUKUVR","short_pith_number":"pith:K6VU4XZV","schema_version":"1.0","canonical_sha256":"57ab4e5f35ab29a434c733afbad154ac7ba86d7e556dbe1bc648e72918d00afc","source":{"kind":"arxiv","id":"1704.04370","version":4},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1704.04370","created_at":"2026-07-05T08:15:22.746013+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.04370v4","created_at":"2026-07-05T08:15:22.746013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.04370","created_at":"2026-07-05T08:15:22.746013+00:00"},{"alias_kind":"pith_short_12","alias_value":"K6VU4XZVVMU2","created_at":"2026-07-05T08:15:22.746013+00:00"},{"alias_kind":"pith_short_16","alias_value":"K6VU4XZVVMU2INGH","created_at":"2026-07-05T08:15:22.746013+00:00"},{"alias_kind":"pith_short_8","alias_value":"K6VU4XZV","created_at":"2026-07-05T08:15:22.746013+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1909.01802","citing_title":"Analysis of SparseHash: an efficient embedding of set-similarity via sparse projections","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K6VU4XZVVMU2INGHGOX3VUKUVR","json":"https://pith.science/pith/K6VU4XZVVMU2INGHGOX3VUKUVR.json","graph_json":"https://pith.science/api/pith-number/K6VU4XZVVMU2INGHGOX3VUKUVR/graph.json","events_json":"https://pith.science/api/pith-number/K6VU4XZVVMU2INGHGOX3VUKUVR/events.json","paper":"https://pith.science/paper/K6VU4XZV"},"agent_actions":{"view_html":"https://pith.science/pith/K6VU4XZVVMU2INGHGOX3VUKUVR","download_json":"https://pith.science/pith/K6VU4XZVVMU2INGHGOX3VUKUVR.json","view_paper":"https://pith.science/paper/K6VU4XZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.04370&json=true","fetch_graph":"https://pith.science/api/pith-number/K6VU4XZVVMU2INGHGOX3VUKUVR/graph.json","fetch_events":"https://pith.science/api/pith-number/K6VU4XZVVMU2INGHGOX3VUKUVR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K6VU4XZVVMU2INGHGOX3VUKUVR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K6VU4XZVVMU2INGHGOX3VUKUVR/action/storage_attestation","attest_author":"https://pith.science/pith/K6VU4XZVVMU2INGHGOX3VUKUVR/action/author_attestation","sign_citation":"https://pith.science/pith/K6VU4XZVVMU2INGHGOX3VUKUVR/action/citation_signature","submit_replication":"https://pith.science/pith/K6VU4XZVVMU2INGHGOX3VUKUVR/action/replication_record"}},"created_at":"2026-07-05T08:15:22.746013+00:00","updated_at":"2026-07-05T08:15:22.746013+00:00"}