{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:HIFDB5PP5JG3ELQ33S46WXFZY7","short_pith_number":"pith:HIFDB5PP","canonical_record":{"source":{"id":"1603.07410","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2016-03-24T01:43:28Z","cross_cats_sorted":[],"title_canon_sha256":"24046ec4fcf6483ee95c8b7a51f5cec3ae85d46610ae94a1533c9c05bb217baa","abstract_canon_sha256":"74544f31baf30b290dcc5a54bf5a0e8a14c06f4f78e79b070649c6510a0470e6"},"schema_version":"1.0"},"canonical_sha256":"3a0a30f5efea4db22e1bdcb9eb5cb9c7dc4cd8ff841c869ba5c5d095262e92af","source":{"kind":"arxiv","id":"1603.07410","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.07410","created_at":"2026-05-18T01:10:37Z"},{"alias_kind":"arxiv_version","alias_value":"1603.07410v4","created_at":"2026-05-18T01:10:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.07410","created_at":"2026-05-18T01:10:37Z"},{"alias_kind":"pith_short_12","alias_value":"HIFDB5PP5JG3","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"HIFDB5PP5JG3ELQ3","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"HIFDB5PP","created_at":"2026-05-18T12:30:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:HIFDB5PP5JG3ELQ33S46WXFZY7","target":"record","payload":{"canonical_record":{"source":{"id":"1603.07410","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2016-03-24T01:43:28Z","cross_cats_sorted":[],"title_canon_sha256":"24046ec4fcf6483ee95c8b7a51f5cec3ae85d46610ae94a1533c9c05bb217baa","abstract_canon_sha256":"74544f31baf30b290dcc5a54bf5a0e8a14c06f4f78e79b070649c6510a0470e6"},"schema_version":"1.0"},"canonical_sha256":"3a0a30f5efea4db22e1bdcb9eb5cb9c7dc4cd8ff841c869ba5c5d095262e92af","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:10:37.811414Z","signature_b64":"EvKr9X83NM0KL5VZxquDxviTEWgPJKWfjcTmn0Pf9JRAzN4bzoTYnMwlYHmODVwH8wJAPDM2Nvo2uoUi1kbjDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a0a30f5efea4db22e1bdcb9eb5cb9c7dc4cd8ff841c869ba5c5d095262e92af","last_reissued_at":"2026-05-18T01:10:37.810920Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:10:37.810920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1603.07410","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:10:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X1+8ZXhTNBlGBX9zo1oQJpENw5NSzLncFkSrKV/a+I7986upGSbjXYSgWRAh3aoDD0DWJYCxuzx848XMg50jBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T03:44:58.928593Z"},"content_sha256":"039b6af1c8260334e0ddc2593910a87eed917e8b0e3ec03af3f62272e8e2b6c0","schema_version":"1.0","event_id":"sha256:039b6af1c8260334e0ddc2593910a87eed917e8b0e3ec03af3f62272e8e2b6c0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:HIFDB5PP5JG3ELQ33S46WXFZY7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LSH Ensemble: Internet-Scale Domain Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Erkang Zhu, Fatemeh Nargesian, Ken Q. Pu, Ren\\'ee J. Miller","submitted_at":"2016-03-24T01:43:28Z","abstract_excerpt":"We study the problem of domain search where a domain is a set of distinct values from an unspecified universe. We use Jaccard set containment, defined as $|Q \\cap X|/|Q|$, as the relevance measure of a domain $X$ to a query domain $Q$. Our choice of Jaccard set containment over Jaccard similarity makes our work particularly suitable for searching Open Data and data on the web, as Jaccard similarity is known to have poor performance over sets with large differences in their domain sizes. We demonstrate that the domains found in several real-life Open Data and web data repositories show a power-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.07410","kind":"arxiv","version":4},"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":"2026-05-18T01:10:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DHNET+KzpD/oDezEQk1ohC9Y+1OwOs1WRr1yQUwLm9Fh1M6+QdWXYqeCFiXnp/UjSrw6qkf5/vKd9dqJcVAEDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T03:44:58.929344Z"},"content_sha256":"3454557b56de1c15fa8d7a85ae085b32531913739d82a12b09bb67324cb3e038","schema_version":"1.0","event_id":"sha256:3454557b56de1c15fa8d7a85ae085b32531913739d82a12b09bb67324cb3e038"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HIFDB5PP5JG3ELQ33S46WXFZY7/bundle.json","state_url":"https://pith.science/pith/HIFDB5PP5JG3ELQ33S46WXFZY7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HIFDB5PP5JG3ELQ33S46WXFZY7/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":"2026-05-26T03:44:58Z","links":{"resolver":"https://pith.science/pith/HIFDB5PP5JG3ELQ33S46WXFZY7","bundle":"https://pith.science/pith/HIFDB5PP5JG3ELQ33S46WXFZY7/bundle.json","state":"https://pith.science/pith/HIFDB5PP5JG3ELQ33S46WXFZY7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HIFDB5PP5JG3ELQ33S46WXFZY7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:HIFDB5PP5JG3ELQ33S46WXFZY7","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":"74544f31baf30b290dcc5a54bf5a0e8a14c06f4f78e79b070649c6510a0470e6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2016-03-24T01:43:28Z","title_canon_sha256":"24046ec4fcf6483ee95c8b7a51f5cec3ae85d46610ae94a1533c9c05bb217baa"},"schema_version":"1.0","source":{"id":"1603.07410","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.07410","created_at":"2026-05-18T01:10:37Z"},{"alias_kind":"arxiv_version","alias_value":"1603.07410v4","created_at":"2026-05-18T01:10:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.07410","created_at":"2026-05-18T01:10:37Z"},{"alias_kind":"pith_short_12","alias_value":"HIFDB5PP5JG3","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"HIFDB5PP5JG3ELQ3","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"HIFDB5PP","created_at":"2026-05-18T12:30:19Z"}],"graph_snapshots":[{"event_id":"sha256:3454557b56de1c15fa8d7a85ae085b32531913739d82a12b09bb67324cb3e038","target":"graph","created_at":"2026-05-18T01:10:37Z","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":"We study the problem of domain search where a domain is a set of distinct values from an unspecified universe. We use Jaccard set containment, defined as $|Q \\cap X|/|Q|$, as the relevance measure of a domain $X$ to a query domain $Q$. Our choice of Jaccard set containment over Jaccard similarity makes our work particularly suitable for searching Open Data and data on the web, as Jaccard similarity is known to have poor performance over sets with large differences in their domain sizes. We demonstrate that the domains found in several real-life Open Data and web data repositories show a power-","authors_text":"Erkang Zhu, Fatemeh Nargesian, Ken Q. Pu, Ren\\'ee J. Miller","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2016-03-24T01:43:28Z","title":"LSH Ensemble: Internet-Scale Domain Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.07410","kind":"arxiv","version":4},"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":"sha256:039b6af1c8260334e0ddc2593910a87eed917e8b0e3ec03af3f62272e8e2b6c0","target":"record","created_at":"2026-05-18T01:10:37Z","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":"74544f31baf30b290dcc5a54bf5a0e8a14c06f4f78e79b070649c6510a0470e6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2016-03-24T01:43:28Z","title_canon_sha256":"24046ec4fcf6483ee95c8b7a51f5cec3ae85d46610ae94a1533c9c05bb217baa"},"schema_version":"1.0","source":{"id":"1603.07410","kind":"arxiv","version":4}},"canonical_sha256":"3a0a30f5efea4db22e1bdcb9eb5cb9c7dc4cd8ff841c869ba5c5d095262e92af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a0a30f5efea4db22e1bdcb9eb5cb9c7dc4cd8ff841c869ba5c5d095262e92af","first_computed_at":"2026-05-18T01:10:37.810920Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:10:37.810920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EvKr9X83NM0KL5VZxquDxviTEWgPJKWfjcTmn0Pf9JRAzN4bzoTYnMwlYHmODVwH8wJAPDM2Nvo2uoUi1kbjDA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:10:37.811414Z","signed_message":"canonical_sha256_bytes"},"source_id":"1603.07410","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:039b6af1c8260334e0ddc2593910a87eed917e8b0e3ec03af3f62272e8e2b6c0","sha256:3454557b56de1c15fa8d7a85ae085b32531913739d82a12b09bb67324cb3e038"],"state_sha256":"b11028a62bec39bc0bbe9fe46132d457c0c6fa6e805ed1735f2335383d882fb3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"95CR9wa7uGGbLBGX6xYWjSsZNVtTSKzB0pmnZmCzgCpspK1GEKNxiN81xQ+2cMzjwLZ07CHHcovDgt6M0qtADA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T03:44:58.933310Z","bundle_sha256":"7522b2a08b5ad82572ddf3334b90c73e45c6ab0f5cc70f9b9763ebb2eb261af2"}}