{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:QJUA46OXDWAORVOEQU3GFCUJ6F","short_pith_number":"pith:QJUA46OX","canonical_record":{"source":{"id":"1903.05826","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-03-14T06:08:46Z","cross_cats_sorted":[],"title_canon_sha256":"1c4cdcf50b118655534fc15d0392bcf08f88f3b28e0c05bf463a1e7cf6ba6a05","abstract_canon_sha256":"ffd4ee796aa7e30debe62e190334f459e3c336599456423d35d09df49d2e3f6a"},"schema_version":"1.0"},"canonical_sha256":"82680e79d71d80e8d5c48536628a89f152f280326a735eeea145dde7774a0b52","source":{"kind":"arxiv","id":"1903.05826","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.05826","created_at":"2026-05-17T23:51:16Z"},{"alias_kind":"arxiv_version","alias_value":"1903.05826v1","created_at":"2026-05-17T23:51:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.05826","created_at":"2026-05-17T23:51:16Z"},{"alias_kind":"pith_short_12","alias_value":"QJUA46OXDWAO","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"QJUA46OXDWAORVOE","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"QJUA46OX","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:QJUA46OXDWAORVOEQU3GFCUJ6F","target":"record","payload":{"canonical_record":{"source":{"id":"1903.05826","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-03-14T06:08:46Z","cross_cats_sorted":[],"title_canon_sha256":"1c4cdcf50b118655534fc15d0392bcf08f88f3b28e0c05bf463a1e7cf6ba6a05","abstract_canon_sha256":"ffd4ee796aa7e30debe62e190334f459e3c336599456423d35d09df49d2e3f6a"},"schema_version":"1.0"},"canonical_sha256":"82680e79d71d80e8d5c48536628a89f152f280326a735eeea145dde7774a0b52","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:16.058824Z","signature_b64":"SbjZSXYH+fS8+F5GeC4pzWt/x/y7bSCvZvEznP01ptEMz58WXViH9bFjL9+xki2lEInYkz3oB+Cma8Xm+idABw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82680e79d71d80e8d5c48536628a89f152f280326a735eeea145dde7774a0b52","last_reissued_at":"2026-05-17T23:51:16.058220Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:16.058220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.05826","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":"2026-05-17T23:51:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0Xvnss/S+WUJMmrgJQYkjpMpZqiC2mWH9Z3bSvJBXEoN5878FxlhAALVV2KrHukkzrtV3T/hctoq7BKtv9ixDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T16:11:34.906797Z"},"content_sha256":"2582236d84864744e437ddbfa0a0e391494272f26642cea3bb96e27711844dca","schema_version":"1.0","event_id":"sha256:2582236d84864744e437ddbfa0a0e391494272f26642cea3bb96e27711844dca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:QJUA46OXDWAORVOEQU3GFCUJ6F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Hybrid Data Cleaning Framework using Markov Logic Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Bin Yao, Congcong Ge, Haobo Wang, Qing Li, Xiaoye Miao, Yunjun Gao","submitted_at":"2019-03-14T06:08:46Z","abstract_excerpt":"With the increase of dirty data, data cleaning turns into a crux of data analysis. Most of the existing algorithms rely on either qualitative techniques (e.g., data rules) or quantitative ones (e.g., statistical methods). In this paper, we present a novel hybrid data cleaning framework on top of Markov logic networks (MLNs), termed as MLNClean, which is capable of cleaning both schema-level and instance-level errors. MLNClean mainly consists of two cleaning stages, namely, first cleaning multiple data versions separately (each of which corresponds to one data rule), and then deriving the final"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.05826","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xPoIO6NhSIsuAx9jZrmE8CBGiW2odsUbGuaaOElEUMm2YYZwwfb0EbgqtKy+Wf1klCAx5ot+aH11ffz1WC03Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T16:11:34.907170Z"},"content_sha256":"68ea71ddb808ed4ec89b7a130ec853b0b2e53007ea5ea584d3057c3a7d83d8e7","schema_version":"1.0","event_id":"sha256:68ea71ddb808ed4ec89b7a130ec853b0b2e53007ea5ea584d3057c3a7d83d8e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QJUA46OXDWAORVOEQU3GFCUJ6F/bundle.json","state_url":"https://pith.science/pith/QJUA46OXDWAORVOEQU3GFCUJ6F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QJUA46OXDWAORVOEQU3GFCUJ6F/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":"2026-06-27T16:11:34Z","links":{"resolver":"https://pith.science/pith/QJUA46OXDWAORVOEQU3GFCUJ6F","bundle":"https://pith.science/pith/QJUA46OXDWAORVOEQU3GFCUJ6F/bundle.json","state":"https://pith.science/pith/QJUA46OXDWAORVOEQU3GFCUJ6F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QJUA46OXDWAORVOEQU3GFCUJ6F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QJUA46OXDWAORVOEQU3GFCUJ6F","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":"ffd4ee796aa7e30debe62e190334f459e3c336599456423d35d09df49d2e3f6a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-03-14T06:08:46Z","title_canon_sha256":"1c4cdcf50b118655534fc15d0392bcf08f88f3b28e0c05bf463a1e7cf6ba6a05"},"schema_version":"1.0","source":{"id":"1903.05826","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.05826","created_at":"2026-05-17T23:51:16Z"},{"alias_kind":"arxiv_version","alias_value":"1903.05826v1","created_at":"2026-05-17T23:51:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.05826","created_at":"2026-05-17T23:51:16Z"},{"alias_kind":"pith_short_12","alias_value":"QJUA46OXDWAO","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"QJUA46OXDWAORVOE","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"QJUA46OX","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:68ea71ddb808ed4ec89b7a130ec853b0b2e53007ea5ea584d3057c3a7d83d8e7","target":"graph","created_at":"2026-05-17T23:51:16Z","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":"With the increase of dirty data, data cleaning turns into a crux of data analysis. Most of the existing algorithms rely on either qualitative techniques (e.g., data rules) or quantitative ones (e.g., statistical methods). In this paper, we present a novel hybrid data cleaning framework on top of Markov logic networks (MLNs), termed as MLNClean, which is capable of cleaning both schema-level and instance-level errors. MLNClean mainly consists of two cleaning stages, namely, first cleaning multiple data versions separately (each of which corresponds to one data rule), and then deriving the final","authors_text":"Bin Yao, Congcong Ge, Haobo Wang, Qing Li, Xiaoye Miao, Yunjun Gao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-03-14T06:08:46Z","title":"A Hybrid Data Cleaning Framework using Markov Logic Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.05826","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":"sha256:2582236d84864744e437ddbfa0a0e391494272f26642cea3bb96e27711844dca","target":"record","created_at":"2026-05-17T23:51:16Z","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":"ffd4ee796aa7e30debe62e190334f459e3c336599456423d35d09df49d2e3f6a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-03-14T06:08:46Z","title_canon_sha256":"1c4cdcf50b118655534fc15d0392bcf08f88f3b28e0c05bf463a1e7cf6ba6a05"},"schema_version":"1.0","source":{"id":"1903.05826","kind":"arxiv","version":1}},"canonical_sha256":"82680e79d71d80e8d5c48536628a89f152f280326a735eeea145dde7774a0b52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"82680e79d71d80e8d5c48536628a89f152f280326a735eeea145dde7774a0b52","first_computed_at":"2026-05-17T23:51:16.058220Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:16.058220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SbjZSXYH+fS8+F5GeC4pzWt/x/y7bSCvZvEznP01ptEMz58WXViH9bFjL9+xki2lEInYkz3oB+Cma8Xm+idABw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:16.058824Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.05826","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2582236d84864744e437ddbfa0a0e391494272f26642cea3bb96e27711844dca","sha256:68ea71ddb808ed4ec89b7a130ec853b0b2e53007ea5ea584d3057c3a7d83d8e7"],"state_sha256":"62aaf2c4b4d3ff16d60b5f9c10e818482bbfc9055da50c68d9902a4d57f2f2b6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sh5g+qSmJ74VbSQTgqlrGKtTmpLkJ4j0Xd6YJTMUwJ3pJrcYUfmKI+VNsljDkO/ITba4aQazFmjLKvCcdWRfAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T16:11:34.909152Z","bundle_sha256":"c1447daee4089551eda416d3702ecd0e2ff9141f0733305e052366c48804dc9b"}}