{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:3LS3LRMUDR72QP5AYOF7T4BEAQ","short_pith_number":"pith:3LS3LRMU","canonical_record":{"source":{"id":"1811.04633","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2018-11-12T09:55:53Z","cross_cats_sorted":[],"title_canon_sha256":"9f5f02df27cdc8c64a084355ce10bc7146c5c9b5f46d0040ed6e6ba73190f460","abstract_canon_sha256":"a78cb1cef53334ad4cae7567f858bf560adf3d1f410c082512a790cf36152597"},"schema_version":"1.0"},"canonical_sha256":"dae5b5c5941c7fa83fa0c38bf9f024041f59e4f4c923d08cf7a24229750e15d1","source":{"kind":"arxiv","id":"1811.04633","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.04633","created_at":"2026-05-18T00:01:04Z"},{"alias_kind":"arxiv_version","alias_value":"1811.04633v1","created_at":"2026-05-18T00:01:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.04633","created_at":"2026-05-18T00:01:04Z"},{"alias_kind":"pith_short_12","alias_value":"3LS3LRMUDR72","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"3LS3LRMUDR72QP5A","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"3LS3LRMU","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:3LS3LRMUDR72QP5AYOF7T4BEAQ","target":"record","payload":{"canonical_record":{"source":{"id":"1811.04633","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2018-11-12T09:55:53Z","cross_cats_sorted":[],"title_canon_sha256":"9f5f02df27cdc8c64a084355ce10bc7146c5c9b5f46d0040ed6e6ba73190f460","abstract_canon_sha256":"a78cb1cef53334ad4cae7567f858bf560adf3d1f410c082512a790cf36152597"},"schema_version":"1.0"},"canonical_sha256":"dae5b5c5941c7fa83fa0c38bf9f024041f59e4f4c923d08cf7a24229750e15d1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:04.494989Z","signature_b64":"qIwBJ2ZgJwlS0gpJc4skTnXeLczJydOKSrRtGAo54a5RHEUxJ7rIwrLnuOtsCiLMuR5p751+uHxFrBK48Qn/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dae5b5c5941c7fa83fa0c38bf9f024041f59e4f4c923d08cf7a24229750e15d1","last_reissued_at":"2026-05-18T00:01:04.494368Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:04.494368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.04633","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:01:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lI4sXzaWLlB6bNZBLHk84F5/ibUA7Cvtai7HLIgc7SUETVpMxSKM3VmBrFUU+8Mf64OSXAeNJPRi4HSCzgKiDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T18:16:49.245073Z"},"content_sha256":"9300919f6f8e22df11f7245baeb2ba204dc8689c09a30a1a92b4374392f4f39d","schema_version":"1.0","event_id":"sha256:9300919f6f8e22df11f7245baeb2ba204dc8689c09a30a1a92b4374392f4f39d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:3LS3LRMUDR72QP5AYOF7T4BEAQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Review for Weighted MinHash Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Bin Li, Chengqi Zhang, Junbin Gao, Ling Chen, Wei Wu","submitted_at":"2018-11-12T09:55:53Z","abstract_excerpt":"Data similarity (or distance) computation is a fundamental research topic which underpins many high-level applications based on similarity measures in machine learning and data mining. However, in large-scale real-world scenarios, the exact similarity computation has become daunting due to \"3V\" nature (volume, velocity and variety) of big data. In such cases, the hashing techniques have been verified to efficiently conduct similarity estimation in terms of both theory and practice. Currently, MinHash is a popular technique for efficiently estimating the Jaccard similarity of binary sets and fu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.04633","kind":"arxiv","version":1},"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":"2026-05-18T00:01:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qi3mAP+N6udGpUbWtdYMSlOQH+N6/6rUSiWV9HNDJa3LVOYX707PJfAwuuZ7CNRKlygHgzX8Aq5J2U9Jw5KHDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T18:16:49.245431Z"},"content_sha256":"1bb7c34b8b708014b8a0d39611bcf39a73faba6b38bd48dd2f3b11f0fd7daa01","schema_version":"1.0","event_id":"sha256:1bb7c34b8b708014b8a0d39611bcf39a73faba6b38bd48dd2f3b11f0fd7daa01"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3LS3LRMUDR72QP5AYOF7T4BEAQ/bundle.json","state_url":"https://pith.science/pith/3LS3LRMUDR72QP5AYOF7T4BEAQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3LS3LRMUDR72QP5AYOF7T4BEAQ/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":"2026-06-03T18:16:49Z","links":{"resolver":"https://pith.science/pith/3LS3LRMUDR72QP5AYOF7T4BEAQ","bundle":"https://pith.science/pith/3LS3LRMUDR72QP5AYOF7T4BEAQ/bundle.json","state":"https://pith.science/pith/3LS3LRMUDR72QP5AYOF7T4BEAQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3LS3LRMUDR72QP5AYOF7T4BEAQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:3LS3LRMUDR72QP5AYOF7T4BEAQ","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":"a78cb1cef53334ad4cae7567f858bf560adf3d1f410c082512a790cf36152597","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2018-11-12T09:55:53Z","title_canon_sha256":"9f5f02df27cdc8c64a084355ce10bc7146c5c9b5f46d0040ed6e6ba73190f460"},"schema_version":"1.0","source":{"id":"1811.04633","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.04633","created_at":"2026-05-18T00:01:04Z"},{"alias_kind":"arxiv_version","alias_value":"1811.04633v1","created_at":"2026-05-18T00:01:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.04633","created_at":"2026-05-18T00:01:04Z"},{"alias_kind":"pith_short_12","alias_value":"3LS3LRMUDR72","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"3LS3LRMUDR72QP5A","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"3LS3LRMU","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:1bb7c34b8b708014b8a0d39611bcf39a73faba6b38bd48dd2f3b11f0fd7daa01","target":"graph","created_at":"2026-05-18T00:01:04Z","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":"Data similarity (or distance) computation is a fundamental research topic which underpins many high-level applications based on similarity measures in machine learning and data mining. However, in large-scale real-world scenarios, the exact similarity computation has become daunting due to \"3V\" nature (volume, velocity and variety) of big data. In such cases, the hashing techniques have been verified to efficiently conduct similarity estimation in terms of both theory and practice. Currently, MinHash is a popular technique for efficiently estimating the Jaccard similarity of binary sets and fu","authors_text":"Bin Li, Chengqi Zhang, Junbin Gao, Ling Chen, Wei Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2018-11-12T09:55:53Z","title":"A Review for Weighted MinHash Algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.04633","kind":"arxiv","version":1},"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":"sha256:9300919f6f8e22df11f7245baeb2ba204dc8689c09a30a1a92b4374392f4f39d","target":"record","created_at":"2026-05-18T00:01:04Z","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":"a78cb1cef53334ad4cae7567f858bf560adf3d1f410c082512a790cf36152597","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2018-11-12T09:55:53Z","title_canon_sha256":"9f5f02df27cdc8c64a084355ce10bc7146c5c9b5f46d0040ed6e6ba73190f460"},"schema_version":"1.0","source":{"id":"1811.04633","kind":"arxiv","version":1}},"canonical_sha256":"dae5b5c5941c7fa83fa0c38bf9f024041f59e4f4c923d08cf7a24229750e15d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dae5b5c5941c7fa83fa0c38bf9f024041f59e4f4c923d08cf7a24229750e15d1","first_computed_at":"2026-05-18T00:01:04.494368Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:04.494368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qIwBJ2ZgJwlS0gpJc4skTnXeLczJydOKSrRtGAo54a5RHEUxJ7rIwrLnuOtsCiLMuR5p751+uHxFrBK48Qn/Bg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:04.494989Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.04633","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9300919f6f8e22df11f7245baeb2ba204dc8689c09a30a1a92b4374392f4f39d","sha256:1bb7c34b8b708014b8a0d39611bcf39a73faba6b38bd48dd2f3b11f0fd7daa01"],"state_sha256":"bf425016edd67a54be4340a4cda0109f9509a9169e3aca81c4850c6ba99c596e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A6qmmMyS5k3qSRGWJVELUeFA+SzdaYXYD8NigUpa1WzEb8Ahfmk0vSEKgmy+yrwrV5wxu00/bV7HEQv/lhC0Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T18:16:49.247349Z","bundle_sha256":"2f3fb673328febecbde5afb84dabb5cd8f41e4f7f997a324d0d9da6ccd61d463"}}