{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4OR3JW2KK65I2EGJ5DHXRSNHY5","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":"810a7c32af3979b8dd30eafd9b6a4353d2e45b2934d701dc26fe71f807686fb9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-02-20T21:57:03Z","title_canon_sha256":"fdd18f247ec1e02a8ea961c8a9e3fdf4a459a84fef4d27782ca7d9756bc1171a"},"schema_version":"1.0","source":{"id":"2402.13397","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13397","created_at":"2026-07-05T07:47:31Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13397v1","created_at":"2026-07-05T07:47:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13397","created_at":"2026-07-05T07:47:31Z"},{"alias_kind":"pith_short_12","alias_value":"4OR3JW2KK65I","created_at":"2026-07-05T07:47:31Z"},{"alias_kind":"pith_short_16","alias_value":"4OR3JW2KK65I2EGJ","created_at":"2026-07-05T07:47:31Z"},{"alias_kind":"pith_short_8","alias_value":"4OR3JW2K","created_at":"2026-07-05T07:47:31Z"}],"graph_snapshots":[{"event_id":"sha256:9902d285ad4f55a66d39cd0e2bca937aba662005330052d2f584cf872e37ab56","target":"graph","created_at":"2026-07-05T07:47:31Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.13397/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Similarity join finds all pairs of close points within a given distance threshold. Many similarity join methods have been proposed, but they are usually not efficient on high-dimensional space due to the curse of dimensionality and data-unawareness. We investigate the possibility of using metric space Bloom filter (MSBF), a family of data structures checking if a query point has neighbors in a multi-dimensional space, to speed up similarity join. However, there are several challenges when applying MSBF to similarity join, including excessive information loss, data-unawareness and hard constrai","authors_text":"Daisy Zhe Wang, Vyom Pathak, Yifan Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-02-20T21:57:03Z","title":"Xling: A Learned Filter Framework for Accelerating High-Dimensional Approximate Similarity Join"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13397","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":"sha256:2d66a620f7f9a6911c41027491118d66310cbae3668ee6c9d12ce4237f161164","target":"record","created_at":"2026-07-05T07:47:31Z","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":"810a7c32af3979b8dd30eafd9b6a4353d2e45b2934d701dc26fe71f807686fb9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-02-20T21:57:03Z","title_canon_sha256":"fdd18f247ec1e02a8ea961c8a9e3fdf4a459a84fef4d27782ca7d9756bc1171a"},"schema_version":"1.0","source":{"id":"2402.13397","kind":"arxiv","version":1}},"canonical_sha256":"e3a3b4db4a57ba8d10c9e8cf78c9a7c7734ae730ca725567e415e3c577fcce66","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3a3b4db4a57ba8d10c9e8cf78c9a7c7734ae730ca725567e415e3c577fcce66","first_computed_at":"2026-07-05T07:47:31.433858Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:47:31.433858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O9e9UQ2T5In52/rEAVv7rUpEqmibsMPj+4LZWT6AMwescquMzBk90i892nB7TxmAbabx4eswLoeS9+Cx1oeCBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:47:31.434325Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.13397","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d66a620f7f9a6911c41027491118d66310cbae3668ee6c9d12ce4237f161164","sha256:9902d285ad4f55a66d39cd0e2bca937aba662005330052d2f584cf872e37ab56"],"state_sha256":"027f0cfbb397235bd647e40c153469a93dda589ee6c3d07e7e509ce6fa1ac74b"}