{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OPSL6S5Z7LYMQQJLRBAOZ3QEIY","short_pith_number":"pith:OPSL6S5Z","schema_version":"1.0","canonical_sha256":"73e4bf4bb9faf0c8412b8840ecee0446238eaf2b9a9d891da411c991dbb0878e","source":{"kind":"arxiv","id":"1802.03914","version":2},"attestation_state":"computed","paper":{"title":"BagMinHash - Minwise Hashing Algorithm for Weighted Sets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Otmar Ertl","submitted_at":"2018-02-12T07:07:56Z","abstract_excerpt":"Minwise hashing has become a standard tool to calculate signatures which allow direct estimation of Jaccard similarities. While very efficient algorithms already exist for the unweighted case, the calculation of signatures for weighted sets is still a time consuming task. BagMinHash is a new algorithm that can be orders of magnitude faster than current state of the art without any particular restrictions or assumptions on weights or data dimensionality. Applied to the special case of unweighted sets, it represents the first efficient algorithm producing independent signature components. A seri"},"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":"1802.03914","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2018-02-12T07:07:56Z","cross_cats_sorted":[],"title_canon_sha256":"1d42167905cdd7ee976f63fc8222dd5f90940f15e3b97b1f01a41e93c4ebbb1f","abstract_canon_sha256":"18f5f5a9144775511981f41828cf8c876ebcd0434be21266060e393fb9c83610"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:10.721773Z","signature_b64":"0smQqjWLdtdYiTWgETkyYww90eSeYIdT099Lowk/b+5kxlVERVl5HX9fsFbxr7F6RduSIW7euQHhhGNfzMaVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73e4bf4bb9faf0c8412b8840ecee0446238eaf2b9a9d891da411c991dbb0878e","last_reissued_at":"2026-05-18T00:10:10.721022Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:10.721022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BagMinHash - Minwise Hashing Algorithm for Weighted Sets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Otmar Ertl","submitted_at":"2018-02-12T07:07:56Z","abstract_excerpt":"Minwise hashing has become a standard tool to calculate signatures which allow direct estimation of Jaccard similarities. While very efficient algorithms already exist for the unweighted case, the calculation of signatures for weighted sets is still a time consuming task. BagMinHash is a new algorithm that can be orders of magnitude faster than current state of the art without any particular restrictions or assumptions on weights or data dimensionality. Applied to the special case of unweighted sets, it represents the first efficient algorithm producing independent signature components. A seri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03914","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":""},"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":"1802.03914","created_at":"2026-05-18T00:10:10.721141+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.03914v2","created_at":"2026-05-18T00:10:10.721141+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03914","created_at":"2026-05-18T00:10:10.721141+00:00"},{"alias_kind":"pith_short_12","alias_value":"OPSL6S5Z7LYM","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"OPSL6S5Z7LYMQQJL","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"OPSL6S5Z","created_at":"2026-05-18T12:32:43.782077+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/OPSL6S5Z7LYMQQJLRBAOZ3QEIY","json":"https://pith.science/pith/OPSL6S5Z7LYMQQJLRBAOZ3QEIY.json","graph_json":"https://pith.science/api/pith-number/OPSL6S5Z7LYMQQJLRBAOZ3QEIY/graph.json","events_json":"https://pith.science/api/pith-number/OPSL6S5Z7LYMQQJLRBAOZ3QEIY/events.json","paper":"https://pith.science/paper/OPSL6S5Z"},"agent_actions":{"view_html":"https://pith.science/pith/OPSL6S5Z7LYMQQJLRBAOZ3QEIY","download_json":"https://pith.science/pith/OPSL6S5Z7LYMQQJLRBAOZ3QEIY.json","view_paper":"https://pith.science/paper/OPSL6S5Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.03914&json=true","fetch_graph":"https://pith.science/api/pith-number/OPSL6S5Z7LYMQQJLRBAOZ3QEIY/graph.json","fetch_events":"https://pith.science/api/pith-number/OPSL6S5Z7LYMQQJLRBAOZ3QEIY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OPSL6S5Z7LYMQQJLRBAOZ3QEIY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OPSL6S5Z7LYMQQJLRBAOZ3QEIY/action/storage_attestation","attest_author":"https://pith.science/pith/OPSL6S5Z7LYMQQJLRBAOZ3QEIY/action/author_attestation","sign_citation":"https://pith.science/pith/OPSL6S5Z7LYMQQJLRBAOZ3QEIY/action/citation_signature","submit_replication":"https://pith.science/pith/OPSL6S5Z7LYMQQJLRBAOZ3QEIY/action/replication_record"}},"created_at":"2026-05-18T00:10:10.721141+00:00","updated_at":"2026-05-18T00:10:10.721141+00:00"}