{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:HXQJSJVKPSZJ6JFNE5UVQHLLVN","short_pith_number":"pith:HXQJSJVK","canonical_record":{"source":{"id":"1804.03054","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2018-04-09T15:21:11Z","cross_cats_sorted":[],"title_canon_sha256":"4c610499eb0fd8d3c679c0895c2b2e3152b5911c0e5aa8c9bc67b2dba65a0439","abstract_canon_sha256":"3b828fed5d35dde1e965b44ccae9eef4440998287313f4c0a2ba5095ed1364e6"},"schema_version":"1.0"},"canonical_sha256":"3de09926aa7cb29f24ad2769581d6bab6d1088e480abd94d9e96db3289472211","source":{"kind":"arxiv","id":"1804.03054","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.03054","created_at":"2026-05-18T00:18:57Z"},{"alias_kind":"arxiv_version","alias_value":"1804.03054v1","created_at":"2026-05-18T00:18:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.03054","created_at":"2026-05-18T00:18:57Z"},{"alias_kind":"pith_short_12","alias_value":"HXQJSJVKPSZJ","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HXQJSJVKPSZJ6JFN","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HXQJSJVK","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:HXQJSJVKPSZJ6JFNE5UVQHLLVN","target":"record","payload":{"canonical_record":{"source":{"id":"1804.03054","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2018-04-09T15:21:11Z","cross_cats_sorted":[],"title_canon_sha256":"4c610499eb0fd8d3c679c0895c2b2e3152b5911c0e5aa8c9bc67b2dba65a0439","abstract_canon_sha256":"3b828fed5d35dde1e965b44ccae9eef4440998287313f4c0a2ba5095ed1364e6"},"schema_version":"1.0"},"canonical_sha256":"3de09926aa7cb29f24ad2769581d6bab6d1088e480abd94d9e96db3289472211","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:57.504900Z","signature_b64":"scyAMHyz5TG403jCrfGBReoUqGstXHtec1C6E6l9QUC/ybs6sLgZZy9inn3tc0V+HvaHD9iUvw4Cgc9sDkzuDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3de09926aa7cb29f24ad2769581d6bab6d1088e480abd94d9e96db3289472211","last_reissued_at":"2026-05-18T00:18:57.504108Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:57.504108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.03054","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":"2026-05-18T00:18:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mF6fD/Ho3+0n+0ePmA/F3qGDSkQTrtqefnp4WnpyS/PZ3bGpKDOVt7LYrK4gGYg1N2221APQkA5PcauGLPkvCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T05:35:18.251716Z"},"content_sha256":"e2d3049280c9cd2099ccbb4833034e3e7f1ede3e25f4256351cc50941a22ef04","schema_version":"1.0","event_id":"sha256:e2d3049280c9cd2099ccbb4833034e3e7f1ede3e25f4256351cc50941a22ef04"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:HXQJSJVKPSZJ6JFNE5UVQHLLVN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Set Similarity Search for Skewed Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Jesper W. Mikkelsen, Rasmus Pagh, Samuel McCauley","submitted_at":"2018-04-09T15:21:11Z","abstract_excerpt":"Set similarity join, as well as the corresponding indexing problem set similarity search, are fundamental primitives for managing noisy or uncertain data. For example, these primitives can be used in data cleaning to identify different representations of the same object. In many cases one can represent an object as a sparse 0-1 vector, or equivalently as the set of nonzero entries in such a vector. A set similarity join can then be used to identify those pairs that have an exceptionally large dot product (or intersection, when viewed as sets). We choose to focus on identifying vectors with lar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.03054","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":"2026-05-18T00:18:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XpwuJK4mtVOA3ok6bh/qN7kFs8YZWGpQE+l3QthUwbacEh1D/GiB4MRkjzRIT4AS48U9AtDciEbbjkmnmXT/Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T05:35:18.252366Z"},"content_sha256":"7e75796055fc9820d45131c3686a19ee0d69508abfc0e429468549ec0bd35f74","schema_version":"1.0","event_id":"sha256:7e75796055fc9820d45131c3686a19ee0d69508abfc0e429468549ec0bd35f74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HXQJSJVKPSZJ6JFNE5UVQHLLVN/bundle.json","state_url":"https://pith.science/pith/HXQJSJVKPSZJ6JFNE5UVQHLLVN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HXQJSJVKPSZJ6JFNE5UVQHLLVN/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":"2026-05-27T05:35:18Z","links":{"resolver":"https://pith.science/pith/HXQJSJVKPSZJ6JFNE5UVQHLLVN","bundle":"https://pith.science/pith/HXQJSJVKPSZJ6JFNE5UVQHLLVN/bundle.json","state":"https://pith.science/pith/HXQJSJVKPSZJ6JFNE5UVQHLLVN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HXQJSJVKPSZJ6JFNE5UVQHLLVN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:HXQJSJVKPSZJ6JFNE5UVQHLLVN","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":"3b828fed5d35dde1e965b44ccae9eef4440998287313f4c0a2ba5095ed1364e6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2018-04-09T15:21:11Z","title_canon_sha256":"4c610499eb0fd8d3c679c0895c2b2e3152b5911c0e5aa8c9bc67b2dba65a0439"},"schema_version":"1.0","source":{"id":"1804.03054","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.03054","created_at":"2026-05-18T00:18:57Z"},{"alias_kind":"arxiv_version","alias_value":"1804.03054v1","created_at":"2026-05-18T00:18:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.03054","created_at":"2026-05-18T00:18:57Z"},{"alias_kind":"pith_short_12","alias_value":"HXQJSJVKPSZJ","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HXQJSJVKPSZJ6JFN","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HXQJSJVK","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:7e75796055fc9820d45131c3686a19ee0d69508abfc0e429468549ec0bd35f74","target":"graph","created_at":"2026-05-18T00:18:57Z","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":"Set similarity join, as well as the corresponding indexing problem set similarity search, are fundamental primitives for managing noisy or uncertain data. For example, these primitives can be used in data cleaning to identify different representations of the same object. In many cases one can represent an object as a sparse 0-1 vector, or equivalently as the set of nonzero entries in such a vector. A set similarity join can then be used to identify those pairs that have an exceptionally large dot product (or intersection, when viewed as sets). We choose to focus on identifying vectors with lar","authors_text":"Jesper W. Mikkelsen, Rasmus Pagh, Samuel McCauley","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2018-04-09T15:21:11Z","title":"Set Similarity Search for Skewed Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.03054","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:e2d3049280c9cd2099ccbb4833034e3e7f1ede3e25f4256351cc50941a22ef04","target":"record","created_at":"2026-05-18T00:18:57Z","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":"3b828fed5d35dde1e965b44ccae9eef4440998287313f4c0a2ba5095ed1364e6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2018-04-09T15:21:11Z","title_canon_sha256":"4c610499eb0fd8d3c679c0895c2b2e3152b5911c0e5aa8c9bc67b2dba65a0439"},"schema_version":"1.0","source":{"id":"1804.03054","kind":"arxiv","version":1}},"canonical_sha256":"3de09926aa7cb29f24ad2769581d6bab6d1088e480abd94d9e96db3289472211","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3de09926aa7cb29f24ad2769581d6bab6d1088e480abd94d9e96db3289472211","first_computed_at":"2026-05-18T00:18:57.504108Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:18:57.504108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"scyAMHyz5TG403jCrfGBReoUqGstXHtec1C6E6l9QUC/ybs6sLgZZy9inn3tc0V+HvaHD9iUvw4Cgc9sDkzuDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:18:57.504900Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.03054","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2d3049280c9cd2099ccbb4833034e3e7f1ede3e25f4256351cc50941a22ef04","sha256:7e75796055fc9820d45131c3686a19ee0d69508abfc0e429468549ec0bd35f74"],"state_sha256":"bd414779252a029a5010d6b9746c3bdf1372e5030e785193ba2924e463e9f4f6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ByzEDfLN6eXloIueMJeq7By3iQEcctnKnLGgCqac09RI/MV1suh+JR2yQqNt937pn3YDpy+SpTo24Tm+rjwxBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T05:35:18.255205Z","bundle_sha256":"60562d4a8ba2bf302c75e010d0d4bc498f03a411e0ab27e65e23238af15a2494"}}