{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:OQNLLBUVZIDEM6KX3UGMG7ZLE7","short_pith_number":"pith:OQNLLBUV","canonical_record":{"source":{"id":"1203.6406","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2012-03-29T00:07:19Z","cross_cats_sorted":[],"title_canon_sha256":"5a9c40eec926ab156da6b85665ddb8be9ed63b58bfcb42e0d6a4608ff1dd65a3","abstract_canon_sha256":"9c2c3f9c14bd9250c44ca627e1be5074619b1d8f79be26302ac00e98c3cc8cec"},"schema_version":"1.0"},"canonical_sha256":"741ab58695ca06467957dd0cc37f2b27f6378251cef85d759d6e48a93f8470de","source":{"kind":"arxiv","id":"1203.6406","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1203.6406","created_at":"2026-05-18T03:59:02Z"},{"alias_kind":"arxiv_version","alias_value":"1203.6406v1","created_at":"2026-05-18T03:59:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1203.6406","created_at":"2026-05-18T03:59:02Z"},{"alias_kind":"pith_short_12","alias_value":"OQNLLBUVZIDE","created_at":"2026-05-18T12:27:16Z"},{"alias_kind":"pith_short_16","alias_value":"OQNLLBUVZIDEM6KX","created_at":"2026-05-18T12:27:16Z"},{"alias_kind":"pith_short_8","alias_value":"OQNLLBUV","created_at":"2026-05-18T12:27:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:OQNLLBUVZIDEM6KX3UGMG7ZLE7","target":"record","payload":{"canonical_record":{"source":{"id":"1203.6406","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2012-03-29T00:07:19Z","cross_cats_sorted":[],"title_canon_sha256":"5a9c40eec926ab156da6b85665ddb8be9ed63b58bfcb42e0d6a4608ff1dd65a3","abstract_canon_sha256":"9c2c3f9c14bd9250c44ca627e1be5074619b1d8f79be26302ac00e98c3cc8cec"},"schema_version":"1.0"},"canonical_sha256":"741ab58695ca06467957dd0cc37f2b27f6378251cef85d759d6e48a93f8470de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:59:02.587803Z","signature_b64":"fnjc+H0ZWwqzKWPNFupkpuMYyAnhc8W8OoXlrdrflGIyhGB7Y77WIb1kla/Biz3Hd40naavTotyFLSGsUTrXAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"741ab58695ca06467957dd0cc37f2b27f6378251cef85d759d6e48a93f8470de","last_reissued_at":"2026-05-18T03:59:02.587261Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:59:02.587261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1203.6406","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":"2026-05-18T03:59:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wbV4+3qfSP3KG2l2VTAOhg3e3L6ilAYNG3yzeY2qLbU3xhh46a/6doqzhEJGanDW+R3DdwefbZoid92hzZxJAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T04:40:41.960047Z"},"content_sha256":"eeaa7b01bcdf5d54ee6d923b4dea941420aa7544a9dc43938ab648fbd910b82e","schema_version":"1.0","event_id":"sha256:eeaa7b01bcdf5d54ee6d923b4dea941420aa7544a9dc43938ab648fbd910b82e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:OQNLLBUVZIDEM6KX3UGMG7ZLE7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Analysis of Structured Data on the Web","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Ashwin Machanavajjhala, Bo Pang, Nilesh Dalvi","submitted_at":"2012-03-29T00:07:19Z","abstract_excerpt":"In this paper, we analyze the nature and distribution of structured data on the Web. Web-scale information extraction, or the problem of creating structured tables using extraction from the entire web, is gathering lots of research interest. We perform a study to understand and quantify the value of Web-scale extraction, and how structured information is distributed amongst top aggregator websites and tail sites for various interesting domains. We believe this is the first study of its kind, and gives us new insights for information extraction over the Web."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1203.6406","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":"2026-05-18T03:59:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/MSeHRS8gx5+lp9KDDvF09cgfoZVIs11F1fOXBhza9fqK+yjM7E7Va5jjKOdfzOZ5JiBQ1vijgluNETI9tfGAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T04:40:41.960755Z"},"content_sha256":"5f499e5d00d725749ed0f4927a831aae9406500b03245e894b2a41d8bc3c612d","schema_version":"1.0","event_id":"sha256:5f499e5d00d725749ed0f4927a831aae9406500b03245e894b2a41d8bc3c612d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OQNLLBUVZIDEM6KX3UGMG7ZLE7/bundle.json","state_url":"https://pith.science/pith/OQNLLBUVZIDEM6KX3UGMG7ZLE7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OQNLLBUVZIDEM6KX3UGMG7ZLE7/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":"2026-06-08T04:40:41Z","links":{"resolver":"https://pith.science/pith/OQNLLBUVZIDEM6KX3UGMG7ZLE7","bundle":"https://pith.science/pith/OQNLLBUVZIDEM6KX3UGMG7ZLE7/bundle.json","state":"https://pith.science/pith/OQNLLBUVZIDEM6KX3UGMG7ZLE7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OQNLLBUVZIDEM6KX3UGMG7ZLE7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:OQNLLBUVZIDEM6KX3UGMG7ZLE7","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":"9c2c3f9c14bd9250c44ca627e1be5074619b1d8f79be26302ac00e98c3cc8cec","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2012-03-29T00:07:19Z","title_canon_sha256":"5a9c40eec926ab156da6b85665ddb8be9ed63b58bfcb42e0d6a4608ff1dd65a3"},"schema_version":"1.0","source":{"id":"1203.6406","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1203.6406","created_at":"2026-05-18T03:59:02Z"},{"alias_kind":"arxiv_version","alias_value":"1203.6406v1","created_at":"2026-05-18T03:59:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1203.6406","created_at":"2026-05-18T03:59:02Z"},{"alias_kind":"pith_short_12","alias_value":"OQNLLBUVZIDE","created_at":"2026-05-18T12:27:16Z"},{"alias_kind":"pith_short_16","alias_value":"OQNLLBUVZIDEM6KX","created_at":"2026-05-18T12:27:16Z"},{"alias_kind":"pith_short_8","alias_value":"OQNLLBUV","created_at":"2026-05-18T12:27:16Z"}],"graph_snapshots":[{"event_id":"sha256:5f499e5d00d725749ed0f4927a831aae9406500b03245e894b2a41d8bc3c612d","target":"graph","created_at":"2026-05-18T03:59:02Z","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":"In this paper, we analyze the nature and distribution of structured data on the Web. Web-scale information extraction, or the problem of creating structured tables using extraction from the entire web, is gathering lots of research interest. We perform a study to understand and quantify the value of Web-scale extraction, and how structured information is distributed amongst top aggregator websites and tail sites for various interesting domains. We believe this is the first study of its kind, and gives us new insights for information extraction over the Web.","authors_text":"Ashwin Machanavajjhala, Bo Pang, Nilesh Dalvi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2012-03-29T00:07:19Z","title":"An Analysis of Structured Data on the Web"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1203.6406","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:eeaa7b01bcdf5d54ee6d923b4dea941420aa7544a9dc43938ab648fbd910b82e","target":"record","created_at":"2026-05-18T03:59:02Z","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":"9c2c3f9c14bd9250c44ca627e1be5074619b1d8f79be26302ac00e98c3cc8cec","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2012-03-29T00:07:19Z","title_canon_sha256":"5a9c40eec926ab156da6b85665ddb8be9ed63b58bfcb42e0d6a4608ff1dd65a3"},"schema_version":"1.0","source":{"id":"1203.6406","kind":"arxiv","version":1}},"canonical_sha256":"741ab58695ca06467957dd0cc37f2b27f6378251cef85d759d6e48a93f8470de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"741ab58695ca06467957dd0cc37f2b27f6378251cef85d759d6e48a93f8470de","first_computed_at":"2026-05-18T03:59:02.587261Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:59:02.587261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fnjc+H0ZWwqzKWPNFupkpuMYyAnhc8W8OoXlrdrflGIyhGB7Y77WIb1kla/Biz3Hd40naavTotyFLSGsUTrXAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:59:02.587803Z","signed_message":"canonical_sha256_bytes"},"source_id":"1203.6406","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eeaa7b01bcdf5d54ee6d923b4dea941420aa7544a9dc43938ab648fbd910b82e","sha256:5f499e5d00d725749ed0f4927a831aae9406500b03245e894b2a41d8bc3c612d"],"state_sha256":"15f54d8c80eeda65113fd4576f2d73daf66d53d64dfd157bf754ee78baa954c7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hu3bSusHbXAGBeB7woT6APCthRcvrKbTwJMyQnwVzR4PXl4xAf+ILe52qO+VTGv3y3BQAKiHno2ez9GUXr5cCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T04:40:41.964239Z","bundle_sha256":"496da31adf7def874e03cd0b551200c697b3add1f54ee704f1fa1bb32957d55a"}}