{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:VBTGKBSEJPXYXDHK2ZNLSVG7GY","short_pith_number":"pith:VBTGKBSE","canonical_record":{"source":{"id":"1503.05157","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2015-03-17T18:39:22Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"afc3ad4591a3e5cf7dab27b0e8626f485d3ac524d8bbc1864bba538b8949ccbd","abstract_canon_sha256":"160a813b34ff5c968684636c7921de01650dbd6ccfc9dc7af14171ee42599ca3"},"schema_version":"1.0"},"canonical_sha256":"a8666506444bef8b8cead65ab954df3614c52bc18a8af0b5fd62f3342d96f7f3","source":{"kind":"arxiv","id":"1503.05157","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1503.05157","created_at":"2026-05-18T02:22:20Z"},{"alias_kind":"arxiv_version","alias_value":"1503.05157v1","created_at":"2026-05-18T02:22:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.05157","created_at":"2026-05-18T02:22:20Z"},{"alias_kind":"pith_short_12","alias_value":"VBTGKBSEJPXY","created_at":"2026-05-18T12:29:44Z"},{"alias_kind":"pith_short_16","alias_value":"VBTGKBSEJPXYXDHK","created_at":"2026-05-18T12:29:44Z"},{"alias_kind":"pith_short_8","alias_value":"VBTGKBSE","created_at":"2026-05-18T12:29:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:VBTGKBSEJPXYXDHK2ZNLSVG7GY","target":"record","payload":{"canonical_record":{"source":{"id":"1503.05157","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2015-03-17T18:39:22Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"afc3ad4591a3e5cf7dab27b0e8626f485d3ac524d8bbc1864bba538b8949ccbd","abstract_canon_sha256":"160a813b34ff5c968684636c7921de01650dbd6ccfc9dc7af14171ee42599ca3"},"schema_version":"1.0"},"canonical_sha256":"a8666506444bef8b8cead65ab954df3614c52bc18a8af0b5fd62f3342d96f7f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:22:20.187903Z","signature_b64":"wgg/L1UtP30wtmXzPHXwuKW8Zo3Db++lwJbVrNDHXRwqMkKGJ88Do2BmUEj3E3QLzneO/Lqlrc9Fl0p7BHnhAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8666506444bef8b8cead65ab954df3614c52bc18a8af0b5fd62f3342d96f7f3","last_reissued_at":"2026-05-18T02:22:20.187107Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:22:20.187107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1503.05157","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":"2026-05-18T02:22:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u8iPtuA6Z3Eo9BcxyiOyaNvdt+loL7kBd38cSTg+cwhpVJZobdqZd7KC0N/VjTBp74wLUi1uravnoH/NGwhwDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T17:05:46.525927Z"},"content_sha256":"fc53820d67f419821373875f2d4c259bd60ac982fc303679ac418938119bd673","schema_version":"1.0","event_id":"sha256:fc53820d67f419821373875f2d4c259bd60ac982fc303679ac418938119bd673"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:VBTGKBSEJPXYXDHK2ZNLSVG7GY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quality Assessment of Linked Datasets using Probabilistic Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.DB","authors_text":"Christoph Lange, Jeremy Debattista, Santiago Londo\\~no, S\\\"oren Auer","submitted_at":"2015-03-17T18:39:22Z","abstract_excerpt":"With the increasing application of Linked Open Data, assessing the quality of datasets by computing quality metrics becomes an issue of crucial importance. For large and evolving datasets, an exact, deterministic computation of the quality metrics is too time consuming or expensive. We employ probabilistic techniques such as Reservoir Sampling, Bloom Filters and Clustering Coefficient estimation for implementing a broad set of data quality metrics in an approximate but sufficiently accurate way. Our implementation is integrated in the comprehensive data quality assessment framework Luzzu. We e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.05157","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":"2026-05-18T02:22:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5TCAkLT0WV5R2EFLGdov4xzp61GILlrExovLGXIR/sPqhOCTUs4BO4/eimT0sv1shiXRwIIn7wZMQ5kJm7trCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T17:05:46.526616Z"},"content_sha256":"66b987efe529127d85acb049e017e861f4d63501d5265d92c3d02298bf791d11","schema_version":"1.0","event_id":"sha256:66b987efe529127d85acb049e017e861f4d63501d5265d92c3d02298bf791d11"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VBTGKBSEJPXYXDHK2ZNLSVG7GY/bundle.json","state_url":"https://pith.science/pith/VBTGKBSEJPXYXDHK2ZNLSVG7GY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VBTGKBSEJPXYXDHK2ZNLSVG7GY/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":"2026-05-26T17:05:46Z","links":{"resolver":"https://pith.science/pith/VBTGKBSEJPXYXDHK2ZNLSVG7GY","bundle":"https://pith.science/pith/VBTGKBSEJPXYXDHK2ZNLSVG7GY/bundle.json","state":"https://pith.science/pith/VBTGKBSEJPXYXDHK2ZNLSVG7GY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VBTGKBSEJPXYXDHK2ZNLSVG7GY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:VBTGKBSEJPXYXDHK2ZNLSVG7GY","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":"160a813b34ff5c968684636c7921de01650dbd6ccfc9dc7af14171ee42599ca3","cross_cats_sorted":["cs.DS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2015-03-17T18:39:22Z","title_canon_sha256":"afc3ad4591a3e5cf7dab27b0e8626f485d3ac524d8bbc1864bba538b8949ccbd"},"schema_version":"1.0","source":{"id":"1503.05157","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1503.05157","created_at":"2026-05-18T02:22:20Z"},{"alias_kind":"arxiv_version","alias_value":"1503.05157v1","created_at":"2026-05-18T02:22:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.05157","created_at":"2026-05-18T02:22:20Z"},{"alias_kind":"pith_short_12","alias_value":"VBTGKBSEJPXY","created_at":"2026-05-18T12:29:44Z"},{"alias_kind":"pith_short_16","alias_value":"VBTGKBSEJPXYXDHK","created_at":"2026-05-18T12:29:44Z"},{"alias_kind":"pith_short_8","alias_value":"VBTGKBSE","created_at":"2026-05-18T12:29:44Z"}],"graph_snapshots":[{"event_id":"sha256:66b987efe529127d85acb049e017e861f4d63501d5265d92c3d02298bf791d11","target":"graph","created_at":"2026-05-18T02:22:20Z","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":"With the increasing application of Linked Open Data, assessing the quality of datasets by computing quality metrics becomes an issue of crucial importance. For large and evolving datasets, an exact, deterministic computation of the quality metrics is too time consuming or expensive. We employ probabilistic techniques such as Reservoir Sampling, Bloom Filters and Clustering Coefficient estimation for implementing a broad set of data quality metrics in an approximate but sufficiently accurate way. Our implementation is integrated in the comprehensive data quality assessment framework Luzzu. We e","authors_text":"Christoph Lange, Jeremy Debattista, Santiago Londo\\~no, S\\\"oren Auer","cross_cats":["cs.DS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2015-03-17T18:39:22Z","title":"Quality Assessment of Linked Datasets using Probabilistic Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.05157","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:fc53820d67f419821373875f2d4c259bd60ac982fc303679ac418938119bd673","target":"record","created_at":"2026-05-18T02:22:20Z","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":"160a813b34ff5c968684636c7921de01650dbd6ccfc9dc7af14171ee42599ca3","cross_cats_sorted":["cs.DS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2015-03-17T18:39:22Z","title_canon_sha256":"afc3ad4591a3e5cf7dab27b0e8626f485d3ac524d8bbc1864bba538b8949ccbd"},"schema_version":"1.0","source":{"id":"1503.05157","kind":"arxiv","version":1}},"canonical_sha256":"a8666506444bef8b8cead65ab954df3614c52bc18a8af0b5fd62f3342d96f7f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8666506444bef8b8cead65ab954df3614c52bc18a8af0b5fd62f3342d96f7f3","first_computed_at":"2026-05-18T02:22:20.187107Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:22:20.187107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wgg/L1UtP30wtmXzPHXwuKW8Zo3Db++lwJbVrNDHXRwqMkKGJ88Do2BmUEj3E3QLzneO/Lqlrc9Fl0p7BHnhAg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:22:20.187903Z","signed_message":"canonical_sha256_bytes"},"source_id":"1503.05157","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc53820d67f419821373875f2d4c259bd60ac982fc303679ac418938119bd673","sha256:66b987efe529127d85acb049e017e861f4d63501d5265d92c3d02298bf791d11"],"state_sha256":"d6ceb37ad95c9ac04665bc2d2e2a9b8925a3cacd70f9b10ce77d34bc37e711f7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xmaov5tGt02TiFNPZSsWMqGE5xpRYBbDti1IaiYBzVl7Jx7mGQ6A5b8FLs8TuM7SkyeC4ZRmJG5eVpydnIxhBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T17:05:46.530207Z","bundle_sha256":"a4f1da7cf369f08058724f448618b32196c70b05ebd471a1ff5f9581a63c7926"}}