{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:PKRC24YTEL35TCTILJ4AZSEN6G","short_pith_number":"pith:PKRC24YT","schema_version":"1.0","canonical_sha256":"7aa22d731322f7d98a685a780cc88df182584275a6c4f6f466d859abf93adfcd","source":{"kind":"arxiv","id":"1503.00306","version":1},"attestation_state":"computed","paper":{"title":"Fusing Data with Correlations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Alexandra Meliou, Anish Das Sarma, Divesh Srivastava, Ravali Pochampally, Xin Luna Dong","submitted_at":"2015-03-01T16:52:55Z","abstract_excerpt":"Many applications rely on Web data and extraction systems to accomplish knowledge-driven tasks. Web information is not curated, so many sources provide inaccurate, or conflicting information. Moreover, extraction systems introduce additional noise to the data. We wish to automatically distinguish correct data and erroneous data for creating a cleaner set of integrated data. Previous work has shown that a na\\\"ive voting strategy that trusts data provided by the majority or at least a certain number of sources may not work well in the presence of copying between the sources. However, correlation"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1503.00306","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2015-03-01T16:52:55Z","cross_cats_sorted":[],"title_canon_sha256":"2db7270a1f89fb4fb4aa6f5eb9e436aff0b444e8ae752587bae4f00a86b5dd8f","abstract_canon_sha256":"82355080712b23757a7a0723ac89ea1dce8c416a0758fb0fc95d7d39c3348a8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:25:54.720658Z","signature_b64":"NBfp6jjaRG94ldIeNiZSKNa6qOoGfSFoewjb5qWAs3uxI5RgET0/mQ+zonoAJLQLfhIe6kLAikWBE6sjt0DgAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7aa22d731322f7d98a685a780cc88df182584275a6c4f6f466d859abf93adfcd","last_reissued_at":"2026-05-18T02:25:54.720210Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:25:54.720210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fusing Data with Correlations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Alexandra Meliou, Anish Das Sarma, Divesh Srivastava, Ravali Pochampally, Xin Luna Dong","submitted_at":"2015-03-01T16:52:55Z","abstract_excerpt":"Many applications rely on Web data and extraction systems to accomplish knowledge-driven tasks. Web information is not curated, so many sources provide inaccurate, or conflicting information. Moreover, extraction systems introduce additional noise to the data. We wish to automatically distinguish correct data and erroneous data for creating a cleaner set of integrated data. Previous work has shown that a na\\\"ive voting strategy that trusts data provided by the majority or at least a certain number of sources may not work well in the presence of copying between the sources. However, correlation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.00306","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1503.00306","created_at":"2026-05-18T02:25:54.720290+00:00"},{"alias_kind":"arxiv_version","alias_value":"1503.00306v1","created_at":"2026-05-18T02:25:54.720290+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.00306","created_at":"2026-05-18T02:25:54.720290+00:00"},{"alias_kind":"pith_short_12","alias_value":"PKRC24YTEL35","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_16","alias_value":"PKRC24YTEL35TCTI","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_8","alias_value":"PKRC24YT","created_at":"2026-05-18T12:29:37.295048+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PKRC24YTEL35TCTILJ4AZSEN6G","json":"https://pith.science/pith/PKRC24YTEL35TCTILJ4AZSEN6G.json","graph_json":"https://pith.science/api/pith-number/PKRC24YTEL35TCTILJ4AZSEN6G/graph.json","events_json":"https://pith.science/api/pith-number/PKRC24YTEL35TCTILJ4AZSEN6G/events.json","paper":"https://pith.science/paper/PKRC24YT"},"agent_actions":{"view_html":"https://pith.science/pith/PKRC24YTEL35TCTILJ4AZSEN6G","download_json":"https://pith.science/pith/PKRC24YTEL35TCTILJ4AZSEN6G.json","view_paper":"https://pith.science/paper/PKRC24YT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1503.00306&json=true","fetch_graph":"https://pith.science/api/pith-number/PKRC24YTEL35TCTILJ4AZSEN6G/graph.json","fetch_events":"https://pith.science/api/pith-number/PKRC24YTEL35TCTILJ4AZSEN6G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PKRC24YTEL35TCTILJ4AZSEN6G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PKRC24YTEL35TCTILJ4AZSEN6G/action/storage_attestation","attest_author":"https://pith.science/pith/PKRC24YTEL35TCTILJ4AZSEN6G/action/author_attestation","sign_citation":"https://pith.science/pith/PKRC24YTEL35TCTILJ4AZSEN6G/action/citation_signature","submit_replication":"https://pith.science/pith/PKRC24YTEL35TCTILJ4AZSEN6G/action/replication_record"}},"created_at":"2026-05-18T02:25:54.720290+00:00","updated_at":"2026-05-18T02:25:54.720290+00:00"}