{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:FYOKSATRPHFP2P72TQZJV2A5DS","short_pith_number":"pith:FYOKSATR","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"},"canonical_sha256":"2e1ca9027179cafd3ffa9c329ae81d1c885576c5c465e59edb9d63286f8a39a9","source":{"kind":"arxiv","id":"1902.00490","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.00490","created_at":"2026-05-17T23:53:49Z"},{"alias_kind":"arxiv_version","alias_value":"1902.00490v2","created_at":"2026-05-17T23:53:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00490","created_at":"2026-05-17T23:53:49Z"},{"alias_kind":"pith_short_12","alias_value":"FYOKSATRPHFP","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"FYOKSATRPHFP2P72","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"FYOKSATR","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:FYOKSATRPHFP2P72TQZJV2A5DS","target":"record","payload":{"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"},"canonical_sha256":"2e1ca9027179cafd3ffa9c329ae81d1c885576c5c465e59edb9d63286f8a39a9","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"},"source_kind":"arxiv","source_id":"1902.00490","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:53:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qrkNhNY+LLz1U+RUvXTMqenhEYpV6h0jOwkcwDhNSAAqEG1JnDXxDlBZaUbE3//BrjyipJLmo3UTxxVf8UfzBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T13:45:32.880056Z"},"content_sha256":"4a32515dbe7674f074066fbd082fae9831e715ce0ce8bf0549092385b25fdce5","schema_version":"1.0","event_id":"sha256:4a32515dbe7674f074066fbd082fae9831e715ce0ce8bf0549092385b25fdce5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:FYOKSATRPHFP2P72TQZJV2A5DS","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:53:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7AsZi73VK9TLRci044g6vlGrBL4XbOGub3Mzu+cL1RBIT6X+wTVgox0eK6oTdWgdpgFsWFARhHk6qtrIccDVCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T13:45:32.880715Z"},"content_sha256":"3ab2ea51ac26f6c321f71b10e2a62d4352c2d895647fbedc70271b983bc6ec5f","schema_version":"1.0","event_id":"sha256:3ab2ea51ac26f6c321f71b10e2a62d4352c2d895647fbedc70271b983bc6ec5f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FYOKSATRPHFP2P72TQZJV2A5DS/bundle.json","state_url":"https://pith.science/pith/FYOKSATRPHFP2P72TQZJV2A5DS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FYOKSATRPHFP2P72TQZJV2A5DS/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":"2026-05-27T13:45:32Z","links":{"resolver":"https://pith.science/pith/FYOKSATRPHFP2P72TQZJV2A5DS","bundle":"https://pith.science/pith/FYOKSATRPHFP2P72TQZJV2A5DS/bundle.json","state":"https://pith.science/pith/FYOKSATRPHFP2P72TQZJV2A5DS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FYOKSATRPHFP2P72TQZJV2A5DS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:FYOKSATRPHFP2P72TQZJV2A5DS","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":"66a0345830b2aa14e7540f89caa178399c3f8841dc32f09b466be335323585ae","cross_cats_sorted":["cs.DS","cs.SI","physics.data-an"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2019-02-01T18:25:08Z","title_canon_sha256":"4fe8d47cbb1d63a2b59bcc576b17468ab2950248def5473a7d6f36c662fdd518"},"schema_version":"1.0","source":{"id":"1902.00490","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.00490","created_at":"2026-05-17T23:53:49Z"},{"alias_kind":"arxiv_version","alias_value":"1902.00490v2","created_at":"2026-05-17T23:53:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00490","created_at":"2026-05-17T23:53:49Z"},{"alias_kind":"pith_short_12","alias_value":"FYOKSATRPHFP","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"FYOKSATRPHFP2P72","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"FYOKSATR","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:3ab2ea51ac26f6c321f71b10e2a62d4352c2d895647fbedc70271b983bc6ec5f","target":"graph","created_at":"2026-05-17T23:53:49Z","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":"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","authors_text":"Artem Lutov, Mourad Khayati, Philippe Cudr\\'e-Mauroux, Soheil Roshankish","cross_cats":["cs.DS","cs.SI","physics.data-an"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2019-02-01T18:25:08Z","title":"StaTIX - Statistical Type Inference on Linked Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00490","kind":"arxiv","version":2},"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":"sha256:4a32515dbe7674f074066fbd082fae9831e715ce0ce8bf0549092385b25fdce5","target":"record","created_at":"2026-05-17T23:53:49Z","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":"66a0345830b2aa14e7540f89caa178399c3f8841dc32f09b466be335323585ae","cross_cats_sorted":["cs.DS","cs.SI","physics.data-an"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2019-02-01T18:25:08Z","title_canon_sha256":"4fe8d47cbb1d63a2b59bcc576b17468ab2950248def5473a7d6f36c662fdd518"},"schema_version":"1.0","source":{"id":"1902.00490","kind":"arxiv","version":2}},"canonical_sha256":"2e1ca9027179cafd3ffa9c329ae81d1c885576c5c465e59edb9d63286f8a39a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e1ca9027179cafd3ffa9c329ae81d1c885576c5c465e59edb9d63286f8a39a9","first_computed_at":"2026-05-17T23:53:49.418895Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:53:49.418895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NCiY5EhCZTjZkOu/EMSPKDlrZCif1MTh5VriqCMYq1hTCyKVyMe3rkj2t5Bw3JpRyz49sf95emLtRh9zamUSDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:53:49.419535Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.00490","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a32515dbe7674f074066fbd082fae9831e715ce0ce8bf0549092385b25fdce5","sha256:3ab2ea51ac26f6c321f71b10e2a62d4352c2d895647fbedc70271b983bc6ec5f"],"state_sha256":"dfea6b07a461ff9643bcf3b6f8afaa0318fd5e44066b2c2966392b2e9743b98e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UfaG36JtBMNluyqQB44MwQP3xVxkcab2sbSqWjUWKxwFO08XnU9PikmDtnHWTZqmm5EN6wOngsQBtDKc9zGDCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T13:45:32.883842Z","bundle_sha256":"ac89e6cf0878ea5647302062d95d4454b9ae257d62380dc9491862254fa3b22b"}}