{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:7RXRJYPZTXPIT634KZHWU62BGQ","short_pith_number":"pith:7RXRJYPZ","schema_version":"1.0","canonical_sha256":"fc6f14e1f99dde89fb7c564f6a7b41342ba9a58a77ce2903cecc8d44db4dc664","source":{"kind":"arxiv","id":"1503.00302","version":1},"attestation_state":"computed","paper":{"title":"From Data Fusion to Knowledge Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Evgeniy Gabrilovich, Geremy Heitz, Kevin Murphy, Shaohua Sun, Wei Zhang, Wilko Horn, Xin Luna Dong","submitted_at":"2015-03-01T16:46:26Z","abstract_excerpt":"The task of {\\em data fusion} is to identify the true values of data items (eg, the true date of birth for {\\em Tom Cruise}) among multiple observed values drawn from different sources (eg, Web sites) of varying (and unknown) reliability. A recent survey\\cite{LDL+12} has provided a detailed comparison of various fusion methods on Deep Web data. In this paper, we study the applicability and limitations of different fusion techniques on a more challenging problem: {\\em knowledge fusion}. Knowledge fusion identifies true subject-predicate-object triples extracted by multiple information extractor"},"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":"1503.00302","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2015-03-01T16:46:26Z","cross_cats_sorted":[],"title_canon_sha256":"6d51ca5dfcdc5313256fb1b964f508b485269aaf3cb70977a60c9ef31825597e","abstract_canon_sha256":"a232ed5a8f0ac4ff92d1c7ce16ae3887503dcbe9bd6682acef85fb1a37686853"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:25:54.731429Z","signature_b64":"7FV329wXsAXdVG9v/pg0aStLdCGVB9QUeP9UgwWsQT4Z3Tb7BXutf84aMdSn4XWlXaNrDx4Bkc+0Uwug3BxnCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc6f14e1f99dde89fb7c564f6a7b41342ba9a58a77ce2903cecc8d44db4dc664","last_reissued_at":"2026-05-18T02:25:54.730995Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:25:54.730995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Data Fusion to Knowledge Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Evgeniy Gabrilovich, Geremy Heitz, Kevin Murphy, Shaohua Sun, Wei Zhang, Wilko Horn, Xin Luna Dong","submitted_at":"2015-03-01T16:46:26Z","abstract_excerpt":"The task of {\\em data fusion} is to identify the true values of data items (eg, the true date of birth for {\\em Tom Cruise}) among multiple observed values drawn from different sources (eg, Web sites) of varying (and unknown) reliability. A recent survey\\cite{LDL+12} has provided a detailed comparison of various fusion methods on Deep Web data. In this paper, we study the applicability and limitations of different fusion techniques on a more challenging problem: {\\em knowledge fusion}. Knowledge fusion identifies true subject-predicate-object triples extracted by multiple information extractor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.00302","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":"1503.00302","created_at":"2026-05-18T02:25:54.731074+00:00"},{"alias_kind":"arxiv_version","alias_value":"1503.00302v1","created_at":"2026-05-18T02:25:54.731074+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.00302","created_at":"2026-05-18T02:25:54.731074+00:00"},{"alias_kind":"pith_short_12","alias_value":"7RXRJYPZTXPI","created_at":"2026-05-18T12:29:10.953037+00:00"},{"alias_kind":"pith_short_16","alias_value":"7RXRJYPZTXPIT634","created_at":"2026-05-18T12:29:10.953037+00:00"},{"alias_kind":"pith_short_8","alias_value":"7RXRJYPZ","created_at":"2026-05-18T12:29:10.953037+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.06814","citing_title":"Metadata Management for AI-Augmented Data Workflows","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7RXRJYPZTXPIT634KZHWU62BGQ","json":"https://pith.science/pith/7RXRJYPZTXPIT634KZHWU62BGQ.json","graph_json":"https://pith.science/api/pith-number/7RXRJYPZTXPIT634KZHWU62BGQ/graph.json","events_json":"https://pith.science/api/pith-number/7RXRJYPZTXPIT634KZHWU62BGQ/events.json","paper":"https://pith.science/paper/7RXRJYPZ"},"agent_actions":{"view_html":"https://pith.science/pith/7RXRJYPZTXPIT634KZHWU62BGQ","download_json":"https://pith.science/pith/7RXRJYPZTXPIT634KZHWU62BGQ.json","view_paper":"https://pith.science/paper/7RXRJYPZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1503.00302&json=true","fetch_graph":"https://pith.science/api/pith-number/7RXRJYPZTXPIT634KZHWU62BGQ/graph.json","fetch_events":"https://pith.science/api/pith-number/7RXRJYPZTXPIT634KZHWU62BGQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7RXRJYPZTXPIT634KZHWU62BGQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7RXRJYPZTXPIT634KZHWU62BGQ/action/storage_attestation","attest_author":"https://pith.science/pith/7RXRJYPZTXPIT634KZHWU62BGQ/action/author_attestation","sign_citation":"https://pith.science/pith/7RXRJYPZTXPIT634KZHWU62BGQ/action/citation_signature","submit_replication":"https://pith.science/pith/7RXRJYPZTXPIT634KZHWU62BGQ/action/replication_record"}},"created_at":"2026-05-18T02:25:54.731074+00:00","updated_at":"2026-05-18T02:25:54.731074+00:00"}