{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:IV6NCFT6MHILN2Y2K4B23CMGLF","short_pith_number":"pith:IV6NCFT6","canonical_record":{"source":{"id":"2004.14478","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-04-26T12:19:04Z","cross_cats_sorted":[],"title_canon_sha256":"cc6dcdc2a8539b177d1b5e787a461959a3725ad2ec68c27175fdf048ec81a346","abstract_canon_sha256":"7d32c8d4e8c836f53b20997eae570c8c10a600a1bc71139dab6b2b9e444b5b20"},"schema_version":"1.0"},"canonical_sha256":"457cd1167e61d0b6eb1a5703ad8986596d1506b526e7277ece649fed39453ea0","source":{"kind":"arxiv","id":"2004.14478","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14478","created_at":"2026-07-05T00:59:26Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14478v1","created_at":"2026-07-05T00:59:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14478","created_at":"2026-07-05T00:59:26Z"},{"alias_kind":"pith_short_12","alias_value":"IV6NCFT6MHIL","created_at":"2026-07-05T00:59:26Z"},{"alias_kind":"pith_short_16","alias_value":"IV6NCFT6MHILN2Y2","created_at":"2026-07-05T00:59:26Z"},{"alias_kind":"pith_short_8","alias_value":"IV6NCFT6","created_at":"2026-07-05T00:59:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:IV6NCFT6MHILN2Y2K4B23CMGLF","target":"record","payload":{"canonical_record":{"source":{"id":"2004.14478","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-04-26T12:19:04Z","cross_cats_sorted":[],"title_canon_sha256":"cc6dcdc2a8539b177d1b5e787a461959a3725ad2ec68c27175fdf048ec81a346","abstract_canon_sha256":"7d32c8d4e8c836f53b20997eae570c8c10a600a1bc71139dab6b2b9e444b5b20"},"schema_version":"1.0"},"canonical_sha256":"457cd1167e61d0b6eb1a5703ad8986596d1506b526e7277ece649fed39453ea0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:26.755652Z","signature_b64":"SED7uBs4+XNimRgWxDDMpZjf8fjM01YEOp0sUDm/SzOEopgZ4xbCu4SQK8tJUCnwjUXN7GALms6bWbfUf8QeDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"457cd1167e61d0b6eb1a5703ad8986596d1506b526e7277ece649fed39453ea0","last_reissued_at":"2026-07-05T00:59:26.755241Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:26.755241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.14478","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":"2026-07-05T00:59:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m9eK2TV4iQm/X2DrEh97pk0CKkP51WoqA+uhW7yVAiyEWoolnmhvGryK1v7h6suKmg4bpvXT2S3rWvZTjoppBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:29:03.131999Z"},"content_sha256":"373f83ea9695eea0afdbe5c06bc69561417e296d640f66f21e1fd4bd08868c98","schema_version":"1.0","event_id":"sha256:373f83ea9695eea0afdbe5c06bc69561417e296d640f66f21e1fd4bd08868c98"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:IV6NCFT6MHILN2Y2K4B23CMGLF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"KGClean: An Embedding Powered Knowledge Graph Cleaning Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Baihua Zheng, Chong Zhang, Congcong Ge, Honghui Weng, Xiaoye Miao, Yunjun Gao","submitted_at":"2020-04-26T12:19:04Z","abstract_excerpt":"The quality assurance of the knowledge graph is a prerequisite for various knowledge-driven applications. We propose KGClean, a novel cleaning framework powered by knowledge graph embedding, to detect and repair the heterogeneous dirty data. In contrast to previous approaches that either focus on filling missing data or clean errors violated limited rules, KGClean enables (i) cleaning both missing data and other erroneous values, and (ii) mining potential rules automatically, which expands the coverage of error detecting. KGClean first learns data representations by TransGAT, an effective know"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14478","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2004.14478/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T00:59:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KrVgC82nyHo4Ab9+1AFLOFZbzPA1j3ho44Cn92FdE2tJ1kXz/VhvNGCmhwjnSGPSNGQwal8fNZReKZz5XMCCBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:29:03.132514Z"},"content_sha256":"7028e228998d24802a3168816649921c2b15a410e894ba2b0da3e853f76b9df5","schema_version":"1.0","event_id":"sha256:7028e228998d24802a3168816649921c2b15a410e894ba2b0da3e853f76b9df5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IV6NCFT6MHILN2Y2K4B23CMGLF/bundle.json","state_url":"https://pith.science/pith/IV6NCFT6MHILN2Y2K4B23CMGLF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IV6NCFT6MHILN2Y2K4B23CMGLF/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":"2026-08-07T23:29:03Z","links":{"resolver":"https://pith.science/pith/IV6NCFT6MHILN2Y2K4B23CMGLF","bundle":"https://pith.science/pith/IV6NCFT6MHILN2Y2K4B23CMGLF/bundle.json","state":"https://pith.science/pith/IV6NCFT6MHILN2Y2K4B23CMGLF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IV6NCFT6MHILN2Y2K4B23CMGLF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:IV6NCFT6MHILN2Y2K4B23CMGLF","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":"7d32c8d4e8c836f53b20997eae570c8c10a600a1bc71139dab6b2b9e444b5b20","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-04-26T12:19:04Z","title_canon_sha256":"cc6dcdc2a8539b177d1b5e787a461959a3725ad2ec68c27175fdf048ec81a346"},"schema_version":"1.0","source":{"id":"2004.14478","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14478","created_at":"2026-07-05T00:59:26Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14478v1","created_at":"2026-07-05T00:59:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14478","created_at":"2026-07-05T00:59:26Z"},{"alias_kind":"pith_short_12","alias_value":"IV6NCFT6MHIL","created_at":"2026-07-05T00:59:26Z"},{"alias_kind":"pith_short_16","alias_value":"IV6NCFT6MHILN2Y2","created_at":"2026-07-05T00:59:26Z"},{"alias_kind":"pith_short_8","alias_value":"IV6NCFT6","created_at":"2026-07-05T00:59:26Z"}],"graph_snapshots":[{"event_id":"sha256:7028e228998d24802a3168816649921c2b15a410e894ba2b0da3e853f76b9df5","target":"graph","created_at":"2026-07-05T00:59:26Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2004.14478/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The quality assurance of the knowledge graph is a prerequisite for various knowledge-driven applications. We propose KGClean, a novel cleaning framework powered by knowledge graph embedding, to detect and repair the heterogeneous dirty data. In contrast to previous approaches that either focus on filling missing data or clean errors violated limited rules, KGClean enables (i) cleaning both missing data and other erroneous values, and (ii) mining potential rules automatically, which expands the coverage of error detecting. KGClean first learns data representations by TransGAT, an effective know","authors_text":"Baihua Zheng, Chong Zhang, Congcong Ge, Honghui Weng, Xiaoye Miao, Yunjun Gao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-04-26T12:19:04Z","title":"KGClean: An Embedding Powered Knowledge Graph Cleaning Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14478","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":"sha256:373f83ea9695eea0afdbe5c06bc69561417e296d640f66f21e1fd4bd08868c98","target":"record","created_at":"2026-07-05T00:59:26Z","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":"7d32c8d4e8c836f53b20997eae570c8c10a600a1bc71139dab6b2b9e444b5b20","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-04-26T12:19:04Z","title_canon_sha256":"cc6dcdc2a8539b177d1b5e787a461959a3725ad2ec68c27175fdf048ec81a346"},"schema_version":"1.0","source":{"id":"2004.14478","kind":"arxiv","version":1}},"canonical_sha256":"457cd1167e61d0b6eb1a5703ad8986596d1506b526e7277ece649fed39453ea0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"457cd1167e61d0b6eb1a5703ad8986596d1506b526e7277ece649fed39453ea0","first_computed_at":"2026-07-05T00:59:26.755241Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:59:26.755241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SED7uBs4+XNimRgWxDDMpZjf8fjM01YEOp0sUDm/SzOEopgZ4xbCu4SQK8tJUCnwjUXN7GALms6bWbfUf8QeDA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:59:26.755652Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.14478","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:373f83ea9695eea0afdbe5c06bc69561417e296d640f66f21e1fd4bd08868c98","sha256:7028e228998d24802a3168816649921c2b15a410e894ba2b0da3e853f76b9df5"],"state_sha256":"0d3bd9993057d7497323428cd2c41811fd703bf3ebcd8c0abb454291b6f9d118"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4VzH0xkux8GnNkWujlU1+hD7afExENHc2Nrr8gV2Guu+HDygdT2uZNvqI3ZCFfo+r2qC4twRR3UhyAaAa5CLBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:29:03.137501Z","bundle_sha256":"117e09ea14007ab6e457c56636c47c80ec225d98745ea6fb2f309db029691b6c"}}