{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:SLNEFZKS7BDAADYLKRSUZ7B4HS","short_pith_number":"pith:SLNEFZKS","schema_version":"1.0","canonical_sha256":"92da42e552f846000f0b54654cfc3c3c8dffee6003d2718b7cf7477be011ca66","source":{"kind":"arxiv","id":"1711.02476","version":2},"attestation_state":"computed","paper":{"title":"SWOOP: Top-k Similarity Joins over Set Streams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Christian S. Jensen, Nikolaus Augsten, Willi Mann","submitted_at":"2017-11-07T14:20:30Z","abstract_excerpt":"We provide efficient support for applications that aim to continuously find pairs of similar sets in rapid streams of sets. A prototypical example setting is that of tweets. A tweet is a set of words, and Twitter emits about half a billion tweets per day. Our solution makes it possible to efficiently maintain the top-$k$ most similar tweets from a pair of rapid Twitter streams, e.g., to discover similar trends in two cities if the streams concern cities.\n  Using a sliding window model, the top-$k$ result changes as new sets in the stream enter the window or existing ones leave the window. Main"},"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":"1711.02476","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-11-07T14:20:30Z","cross_cats_sorted":[],"title_canon_sha256":"77d6096cfdc3b0d1961ca4b5538355680854a389bdf8e8b75a63f67f1c5eb70d","abstract_canon_sha256":"c3613fd105241f9948851a37beed6f3c328a8ebe892617b58b68d7efdca2b36b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:23:19.587569Z","signature_b64":"0p9Ou+pPoG6H9n/CL0QwtzNsC2lKsxXmNYyAKn5ADIMXm32LdI8EyAk65gIb9RCLmBSNhqnsPDhk9iKB8DLbAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92da42e552f846000f0b54654cfc3c3c8dffee6003d2718b7cf7477be011ca66","last_reissued_at":"2026-07-05T00:23:19.587050Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:23:19.587050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SWOOP: Top-k Similarity Joins over Set Streams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Christian S. Jensen, Nikolaus Augsten, Willi Mann","submitted_at":"2017-11-07T14:20:30Z","abstract_excerpt":"We provide efficient support for applications that aim to continuously find pairs of similar sets in rapid streams of sets. A prototypical example setting is that of tweets. A tweet is a set of words, and Twitter emits about half a billion tweets per day. Our solution makes it possible to efficiently maintain the top-$k$ most similar tweets from a pair of rapid Twitter streams, e.g., to discover similar trends in two cities if the streams concern cities.\n  Using a sliding window model, the top-$k$ result changes as new sets in the stream enter the window or existing ones leave the window. Main"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.02476","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/1711.02476/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":"1711.02476","created_at":"2026-07-05T00:23:19.587108+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.02476v2","created_at":"2026-07-05T00:23:19.587108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.02476","created_at":"2026-07-05T00:23:19.587108+00:00"},{"alias_kind":"pith_short_12","alias_value":"SLNEFZKS7BDA","created_at":"2026-07-05T00:23:19.587108+00:00"},{"alias_kind":"pith_short_16","alias_value":"SLNEFZKS7BDAADYL","created_at":"2026-07-05T00:23:19.587108+00:00"},{"alias_kind":"pith_short_8","alias_value":"SLNEFZKS","created_at":"2026-07-05T00:23:19.587108+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SLNEFZKS7BDAADYLKRSUZ7B4HS","json":"https://pith.science/pith/SLNEFZKS7BDAADYLKRSUZ7B4HS.json","graph_json":"https://pith.science/api/pith-number/SLNEFZKS7BDAADYLKRSUZ7B4HS/graph.json","events_json":"https://pith.science/api/pith-number/SLNEFZKS7BDAADYLKRSUZ7B4HS/events.json","paper":"https://pith.science/paper/SLNEFZKS"},"agent_actions":{"view_html":"https://pith.science/pith/SLNEFZKS7BDAADYLKRSUZ7B4HS","download_json":"https://pith.science/pith/SLNEFZKS7BDAADYLKRSUZ7B4HS.json","view_paper":"https://pith.science/paper/SLNEFZKS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.02476&json=true","fetch_graph":"https://pith.science/api/pith-number/SLNEFZKS7BDAADYLKRSUZ7B4HS/graph.json","fetch_events":"https://pith.science/api/pith-number/SLNEFZKS7BDAADYLKRSUZ7B4HS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SLNEFZKS7BDAADYLKRSUZ7B4HS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SLNEFZKS7BDAADYLKRSUZ7B4HS/action/storage_attestation","attest_author":"https://pith.science/pith/SLNEFZKS7BDAADYLKRSUZ7B4HS/action/author_attestation","sign_citation":"https://pith.science/pith/SLNEFZKS7BDAADYLKRSUZ7B4HS/action/citation_signature","submit_replication":"https://pith.science/pith/SLNEFZKS7BDAADYLKRSUZ7B4HS/action/replication_record"}},"created_at":"2026-07-05T00:23:19.587108+00:00","updated_at":"2026-07-05T00:23:19.587108+00:00"}