{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FYOKSATRPHFP2P72TQZJV2A5DS","short_pith_number":"pith:FYOKSATR","schema_version":"1.0","canonical_sha256":"2e1ca9027179cafd3ffa9c329ae81d1c885576c5c465e59edb9d63286f8a39a9","source":{"kind":"arxiv","id":"1902.00490","version":2},"attestation_state":"computed","paper":{"title":"StaTIX - Statistical Type Inference on Linked Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS","cs.SI","physics.data-an"],"primary_cat":"stat.AP","authors_text":"Artem Lutov, Mourad Khayati, Philippe Cudr\\'e-Mauroux, Soheil Roshankish","submitted_at":"2019-02-01T18:25:08Z","abstract_excerpt":"Large knowledge bases typically contain data adhering to various schemas with incomplete and/or noisy type information. This seriously complicates further integration and post-processing efforts, as type information is crucial in correctly handling the data. In this paper, we introduce a novel statistical type inference method, called StaTIX, to effectively infer instance types in Linked Data sets in a fully unsupervised manner. Our inference technique leverages a new hierarchical clustering algorithm that is robust, highly effective, and scalable. We introduce a novel approach to reduce the p"},"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":"1902.00490","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2019-02-01T18:25:08Z","cross_cats_sorted":["cs.DS","cs.SI","physics.data-an"],"title_canon_sha256":"4fe8d47cbb1d63a2b59bcc576b17468ab2950248def5473a7d6f36c662fdd518","abstract_canon_sha256":"66a0345830b2aa14e7540f89caa178399c3f8841dc32f09b466be335323585ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:49.419535Z","signature_b64":"NCiY5EhCZTjZkOu/EMSPKDlrZCif1MTh5VriqCMYq1hTCyKVyMe3rkj2t5Bw3JpRyz49sf95emLtRh9zamUSDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e1ca9027179cafd3ffa9c329ae81d1c885576c5c465e59edb9d63286f8a39a9","last_reissued_at":"2026-05-17T23:53:49.418895Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:49.418895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StaTIX - Statistical Type Inference on Linked Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS","cs.SI","physics.data-an"],"primary_cat":"stat.AP","authors_text":"Artem Lutov, Mourad Khayati, Philippe Cudr\\'e-Mauroux, Soheil Roshankish","submitted_at":"2019-02-01T18:25:08Z","abstract_excerpt":"Large knowledge bases typically contain data adhering to various schemas with incomplete and/or noisy type information. This seriously complicates further integration and post-processing efforts, as type information is crucial in correctly handling the data. In this paper, we introduce a novel statistical type inference method, called StaTIX, to effectively infer instance types in Linked Data sets in a fully unsupervised manner. Our inference technique leverages a new hierarchical clustering algorithm that is robust, highly effective, and scalable. We introduce a novel approach to reduce the p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00490","kind":"arxiv","version":2},"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":"1902.00490","created_at":"2026-05-17T23:53:49.418988+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.00490v2","created_at":"2026-05-17T23:53:49.418988+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00490","created_at":"2026-05-17T23:53:49.418988+00:00"},{"alias_kind":"pith_short_12","alias_value":"FYOKSATRPHFP","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"FYOKSATRPHFP2P72","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"FYOKSATR","created_at":"2026-05-18T12:33:18.533446+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/FYOKSATRPHFP2P72TQZJV2A5DS","json":"https://pith.science/pith/FYOKSATRPHFP2P72TQZJV2A5DS.json","graph_json":"https://pith.science/api/pith-number/FYOKSATRPHFP2P72TQZJV2A5DS/graph.json","events_json":"https://pith.science/api/pith-number/FYOKSATRPHFP2P72TQZJV2A5DS/events.json","paper":"https://pith.science/paper/FYOKSATR"},"agent_actions":{"view_html":"https://pith.science/pith/FYOKSATRPHFP2P72TQZJV2A5DS","download_json":"https://pith.science/pith/FYOKSATRPHFP2P72TQZJV2A5DS.json","view_paper":"https://pith.science/paper/FYOKSATR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.00490&json=true","fetch_graph":"https://pith.science/api/pith-number/FYOKSATRPHFP2P72TQZJV2A5DS/graph.json","fetch_events":"https://pith.science/api/pith-number/FYOKSATRPHFP2P72TQZJV2A5DS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FYOKSATRPHFP2P72TQZJV2A5DS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FYOKSATRPHFP2P72TQZJV2A5DS/action/storage_attestation","attest_author":"https://pith.science/pith/FYOKSATRPHFP2P72TQZJV2A5DS/action/author_attestation","sign_citation":"https://pith.science/pith/FYOKSATRPHFP2P72TQZJV2A5DS/action/citation_signature","submit_replication":"https://pith.science/pith/FYOKSATRPHFP2P72TQZJV2A5DS/action/replication_record"}},"created_at":"2026-05-17T23:53:49.418988+00:00","updated_at":"2026-05-17T23:53:49.418988+00:00"}