{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:QSPCKZ47AEAEQKDRTPFYCZLF4K","short_pith_number":"pith:QSPCKZ47","canonical_record":{"source":{"id":"2006.06894","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-06-12T00:54:15Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"c09d10ef0bac27c769052c0e9e0c8c81849ef981cb0eec84fab985f543876125","abstract_canon_sha256":"6e8e94012a663c16b1ff49f5497824bb528a43b73a59b721b1d95ceab3386286"},"schema_version":"1.0"},"canonical_sha256":"849e25679f01004828719bcb816565e285bdacea387367d6c6f28b00f2d39750","source":{"kind":"arxiv","id":"2006.06894","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.06894","created_at":"2026-07-05T01:09:47Z"},{"alias_kind":"arxiv_version","alias_value":"2006.06894v1","created_at":"2026-07-05T01:09:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.06894","created_at":"2026-07-05T01:09:47Z"},{"alias_kind":"pith_short_12","alias_value":"QSPCKZ47AEAE","created_at":"2026-07-05T01:09:47Z"},{"alias_kind":"pith_short_16","alias_value":"QSPCKZ47AEAEQKDR","created_at":"2026-07-05T01:09:47Z"},{"alias_kind":"pith_short_8","alias_value":"QSPCKZ47","created_at":"2026-07-05T01:09:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:QSPCKZ47AEAEQKDRTPFYCZLF4K","target":"record","payload":{"canonical_record":{"source":{"id":"2006.06894","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-06-12T00:54:15Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"c09d10ef0bac27c769052c0e9e0c8c81849ef981cb0eec84fab985f543876125","abstract_canon_sha256":"6e8e94012a663c16b1ff49f5497824bb528a43b73a59b721b1d95ceab3386286"},"schema_version":"1.0"},"canonical_sha256":"849e25679f01004828719bcb816565e285bdacea387367d6c6f28b00f2d39750","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:09:47.866880Z","signature_b64":"lvNKIZ5AWwqGNVQTl2Pat82lrdcKEjAZu+vlAEmcFf2R3nEX5pmpAZGNE33dpLjCtMuQbzYYolnEjInFbdIXDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"849e25679f01004828719bcb816565e285bdacea387367d6c6f28b00f2d39750","last_reissued_at":"2026-07-05T01:09:47.866486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:09:47.866486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.06894","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":"2026-07-05T01:09:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H3jujpd6GI1z/3rfZaC9wi98/O5M/96iW/yvFRPlnDsZnFl0QA3jy1CfBLxlrcKMqQjFxlO8L7qANED6T4LtCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:38:49.212652Z"},"content_sha256":"b1ee93dd78c6f791bed5ce18dbba8a82982a232ae3f5285f1cbcb91b87d2baab","schema_version":"1.0","event_id":"sha256:b1ee93dd78c6f791bed5ce18dbba8a82982a232ae3f5285f1cbcb91b87d2baab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:QSPCKZ47AEAEQKDRTPFYCZLF4K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Google Dataset Search by the Numbers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.IR","authors_text":"Natasha Noy, Omar Benjelloun, Shiyu Chen","submitted_at":"2020-06-12T00:54:15Z","abstract_excerpt":"Scientists, governments, and companies increasingly publish datasets on the Web. Google's Dataset Search extracts dataset metadata -- expressed using schema.org and similar vocabularies -- from Web pages in order to make datasets discoverable. Since we started the work on Dataset Search in 2016, the number of datasets described in schema.org has grown from about 500K to almost 30M. Thus, this corpus has become a valuable snapshot of data on the Web. To the best of our knowledge, this corpus is the largest and most diverse of its kind. We analyze this corpus and discuss where the datasets origi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.06894","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.06894/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T01:09:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dmtjqCFnllRr7vCJ+TSsx8xhRi1TRi5Lgyjj0FDr79cdlJlmiRw4Vb/sqbEsjQqCCZ/d/GjVi2WnxKI6ou2WCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:38:49.213027Z"},"content_sha256":"c16f9c634500398e0c5c3e4783e820fd604ccdaf3cec770e2709205dcca13275","schema_version":"1.0","event_id":"sha256:c16f9c634500398e0c5c3e4783e820fd604ccdaf3cec770e2709205dcca13275"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QSPCKZ47AEAEQKDRTPFYCZLF4K/bundle.json","state_url":"https://pith.science/pith/QSPCKZ47AEAEQKDRTPFYCZLF4K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QSPCKZ47AEAEQKDRTPFYCZLF4K/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":"2026-07-07T11:38:49Z","links":{"resolver":"https://pith.science/pith/QSPCKZ47AEAEQKDRTPFYCZLF4K","bundle":"https://pith.science/pith/QSPCKZ47AEAEQKDRTPFYCZLF4K/bundle.json","state":"https://pith.science/pith/QSPCKZ47AEAEQKDRTPFYCZLF4K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QSPCKZ47AEAEQKDRTPFYCZLF4K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:QSPCKZ47AEAEQKDRTPFYCZLF4K","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":"6e8e94012a663c16b1ff49f5497824bb528a43b73a59b721b1d95ceab3386286","cross_cats_sorted":["cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-06-12T00:54:15Z","title_canon_sha256":"c09d10ef0bac27c769052c0e9e0c8c81849ef981cb0eec84fab985f543876125"},"schema_version":"1.0","source":{"id":"2006.06894","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.06894","created_at":"2026-07-05T01:09:47Z"},{"alias_kind":"arxiv_version","alias_value":"2006.06894v1","created_at":"2026-07-05T01:09:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.06894","created_at":"2026-07-05T01:09:47Z"},{"alias_kind":"pith_short_12","alias_value":"QSPCKZ47AEAE","created_at":"2026-07-05T01:09:47Z"},{"alias_kind":"pith_short_16","alias_value":"QSPCKZ47AEAEQKDR","created_at":"2026-07-05T01:09:47Z"},{"alias_kind":"pith_short_8","alias_value":"QSPCKZ47","created_at":"2026-07-05T01:09:47Z"}],"graph_snapshots":[{"event_id":"sha256:c16f9c634500398e0c5c3e4783e820fd604ccdaf3cec770e2709205dcca13275","target":"graph","created_at":"2026-07-05T01:09:47Z","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/2006.06894/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scientists, governments, and companies increasingly publish datasets on the Web. Google's Dataset Search extracts dataset metadata -- expressed using schema.org and similar vocabularies -- from Web pages in order to make datasets discoverable. Since we started the work on Dataset Search in 2016, the number of datasets described in schema.org has grown from about 500K to almost 30M. Thus, this corpus has become a valuable snapshot of data on the Web. To the best of our knowledge, this corpus is the largest and most diverse of its kind. We analyze this corpus and discuss where the datasets origi","authors_text":"Natasha Noy, Omar Benjelloun, Shiyu Chen","cross_cats":["cs.DB"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-06-12T00:54:15Z","title":"Google Dataset Search by the Numbers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.06894","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:b1ee93dd78c6f791bed5ce18dbba8a82982a232ae3f5285f1cbcb91b87d2baab","target":"record","created_at":"2026-07-05T01:09:47Z","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":"6e8e94012a663c16b1ff49f5497824bb528a43b73a59b721b1d95ceab3386286","cross_cats_sorted":["cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-06-12T00:54:15Z","title_canon_sha256":"c09d10ef0bac27c769052c0e9e0c8c81849ef981cb0eec84fab985f543876125"},"schema_version":"1.0","source":{"id":"2006.06894","kind":"arxiv","version":1}},"canonical_sha256":"849e25679f01004828719bcb816565e285bdacea387367d6c6f28b00f2d39750","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"849e25679f01004828719bcb816565e285bdacea387367d6c6f28b00f2d39750","first_computed_at":"2026-07-05T01:09:47.866486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:09:47.866486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lvNKIZ5AWwqGNVQTl2Pat82lrdcKEjAZu+vlAEmcFf2R3nEX5pmpAZGNE33dpLjCtMuQbzYYolnEjInFbdIXDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:09:47.866880Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.06894","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1ee93dd78c6f791bed5ce18dbba8a82982a232ae3f5285f1cbcb91b87d2baab","sha256:c16f9c634500398e0c5c3e4783e820fd604ccdaf3cec770e2709205dcca13275"],"state_sha256":"e41d89cb05a056013e1c9e48914484241160b368ec72578660459e9a1e806057"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v9SsDbQzhvNOGhG/Iv8HalF+Lyf7gYKpAHJ7cs/Eeiug/sLF2nx62ucU2s0XlDmaB1WwtTmW5Fmq8SbMbRIxBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:38:49.215010Z","bundle_sha256":"c6b4493b437721e3b9f72a16c09bc66bae83579c71d607ce077c9381049e8102"}}