{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZDES2FJCEQVWQ6D5NWOTFWFCRF","short_pith_number":"pith:ZDES2FJC","canonical_record":{"source":{"id":"2311.06517","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-11-11T09:22:07Z","cross_cats_sorted":["cs.DB","cs.LG","stat.AP"],"title_canon_sha256":"1396324ab58ea3345a98b5e33a33a5e0301fa3f841d91c9ef463f177d1e57664","abstract_canon_sha256":"f80860cef3bfd2917ef2294775637587382455294f10944132f70fc936307d11"},"schema_version":"1.0"},"canonical_sha256":"c8c92d1522242b68787d6d9d32d8a28970693ae07340630bff1009560c1e7876","source":{"kind":"arxiv","id":"2311.06517","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.06517","created_at":"2026-07-05T07:11:41Z"},{"alias_kind":"arxiv_version","alias_value":"2311.06517v1","created_at":"2026-07-05T07:11:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06517","created_at":"2026-07-05T07:11:41Z"},{"alias_kind":"pith_short_12","alias_value":"ZDES2FJCEQVW","created_at":"2026-07-05T07:11:41Z"},{"alias_kind":"pith_short_16","alias_value":"ZDES2FJCEQVWQ6D5","created_at":"2026-07-05T07:11:41Z"},{"alias_kind":"pith_short_8","alias_value":"ZDES2FJC","created_at":"2026-07-05T07:11:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZDES2FJCEQVWQ6D5NWOTFWFCRF","target":"record","payload":{"canonical_record":{"source":{"id":"2311.06517","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-11-11T09:22:07Z","cross_cats_sorted":["cs.DB","cs.LG","stat.AP"],"title_canon_sha256":"1396324ab58ea3345a98b5e33a33a5e0301fa3f841d91c9ef463f177d1e57664","abstract_canon_sha256":"f80860cef3bfd2917ef2294775637587382455294f10944132f70fc936307d11"},"schema_version":"1.0"},"canonical_sha256":"c8c92d1522242b68787d6d9d32d8a28970693ae07340630bff1009560c1e7876","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:41.273245Z","signature_b64":"4+JfjG/T/4ZzlYyEm2VbNvLS2eMN5qy/7FLHXSYikoT/dSOaoxuA+U73kJ+09DzZ1x1vBXOtfXH/nBosnyTXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8c92d1522242b68787d6d9d32d8a28970693ae07340630bff1009560c1e7876","last_reissued_at":"2026-07-05T07:11:41.272721Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:41.272721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.06517","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":"2026-07-05T07:11:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ca3h2Kr1YdLqqvo50HS/VWyRWpoEEs8ZpdBurZd78SAp/gpVGzA4MTAsQiJ8rxmL6N5mZhlH0NAKp0hsZI5uDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T01:10:48.667367Z"},"content_sha256":"65b646080f7ffc1ce3f02f9c8d0783fd671e0963ac9351e3943b728d4e19f0a4","schema_version":"1.0","event_id":"sha256:65b646080f7ffc1ce3f02f9c8d0783fd671e0963ac9351e3943b728d4e19f0a4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZDES2FJCEQVWQ6D5NWOTFWFCRF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BClean: A Bayesian Data Cleaning System","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB","cs.LG","stat.AP"],"primary_cat":"cs.AI","authors_text":"Chuan Xiao, Jianbin Qin, Jing Zhu, Makoto Onizuka, Rui Mao, Sifan Huang, Yaoshu Wang, Yifan Zhang, Yukai Miao","submitted_at":"2023-11-11T09:22:07Z","abstract_excerpt":"There is a considerable body of work on data cleaning which employs various principles to rectify erroneous data and transform a dirty dataset into a cleaner one. One of prevalent approaches is probabilistic methods, including Bayesian methods. However, existing probabilistic methods often assume a simplistic distribution (e.g., Gaussian distribution), which is frequently underfitted in practice, or they necessitate experts to provide a complex prior distribution (e.g., via a programming language). This requirement is both labor-intensive and costly, rendering these methods less suitable for r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.06517","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/2311.06517/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":"2026-07-05T07:11:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m72JvJH8rSE22zO71RIuwpgEdjjZWmdEvFlZhTNqcU7rrz5iVxF6vz8auFw9QTQzAquxDNerYPOTY6K2z1dMAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T01:10:48.667948Z"},"content_sha256":"94ae6db46d26cfc831bd49deac4d09d16e3cf72567724e648d19ea6cd99a8480","schema_version":"1.0","event_id":"sha256:94ae6db46d26cfc831bd49deac4d09d16e3cf72567724e648d19ea6cd99a8480"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZDES2FJCEQVWQ6D5NWOTFWFCRF/bundle.json","state_url":"https://pith.science/pith/ZDES2FJCEQVWQ6D5NWOTFWFCRF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZDES2FJCEQVWQ6D5NWOTFWFCRF/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":"2026-08-20T01:10:48Z","links":{"resolver":"https://pith.science/pith/ZDES2FJCEQVWQ6D5NWOTFWFCRF","bundle":"https://pith.science/pith/ZDES2FJCEQVWQ6D5NWOTFWFCRF/bundle.json","state":"https://pith.science/pith/ZDES2FJCEQVWQ6D5NWOTFWFCRF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZDES2FJCEQVWQ6D5NWOTFWFCRF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZDES2FJCEQVWQ6D5NWOTFWFCRF","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":"f80860cef3bfd2917ef2294775637587382455294f10944132f70fc936307d11","cross_cats_sorted":["cs.DB","cs.LG","stat.AP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-11-11T09:22:07Z","title_canon_sha256":"1396324ab58ea3345a98b5e33a33a5e0301fa3f841d91c9ef463f177d1e57664"},"schema_version":"1.0","source":{"id":"2311.06517","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.06517","created_at":"2026-07-05T07:11:41Z"},{"alias_kind":"arxiv_version","alias_value":"2311.06517v1","created_at":"2026-07-05T07:11:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06517","created_at":"2026-07-05T07:11:41Z"},{"alias_kind":"pith_short_12","alias_value":"ZDES2FJCEQVW","created_at":"2026-07-05T07:11:41Z"},{"alias_kind":"pith_short_16","alias_value":"ZDES2FJCEQVWQ6D5","created_at":"2026-07-05T07:11:41Z"},{"alias_kind":"pith_short_8","alias_value":"ZDES2FJC","created_at":"2026-07-05T07:11:41Z"}],"graph_snapshots":[{"event_id":"sha256:94ae6db46d26cfc831bd49deac4d09d16e3cf72567724e648d19ea6cd99a8480","target":"graph","created_at":"2026-07-05T07:11:41Z","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/2311.06517/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There is a considerable body of work on data cleaning which employs various principles to rectify erroneous data and transform a dirty dataset into a cleaner one. One of prevalent approaches is probabilistic methods, including Bayesian methods. However, existing probabilistic methods often assume a simplistic distribution (e.g., Gaussian distribution), which is frequently underfitted in practice, or they necessitate experts to provide a complex prior distribution (e.g., via a programming language). This requirement is both labor-intensive and costly, rendering these methods less suitable for r","authors_text":"Chuan Xiao, Jianbin Qin, Jing Zhu, Makoto Onizuka, Rui Mao, Sifan Huang, Yaoshu Wang, Yifan Zhang, Yukai Miao","cross_cats":["cs.DB","cs.LG","stat.AP"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-11-11T09:22:07Z","title":"BClean: A Bayesian Data Cleaning System"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.06517","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":"sha256:65b646080f7ffc1ce3f02f9c8d0783fd671e0963ac9351e3943b728d4e19f0a4","target":"record","created_at":"2026-07-05T07:11:41Z","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":"f80860cef3bfd2917ef2294775637587382455294f10944132f70fc936307d11","cross_cats_sorted":["cs.DB","cs.LG","stat.AP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-11-11T09:22:07Z","title_canon_sha256":"1396324ab58ea3345a98b5e33a33a5e0301fa3f841d91c9ef463f177d1e57664"},"schema_version":"1.0","source":{"id":"2311.06517","kind":"arxiv","version":1}},"canonical_sha256":"c8c92d1522242b68787d6d9d32d8a28970693ae07340630bff1009560c1e7876","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8c92d1522242b68787d6d9d32d8a28970693ae07340630bff1009560c1e7876","first_computed_at":"2026-07-05T07:11:41.272721Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:11:41.272721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4+JfjG/T/4ZzlYyEm2VbNvLS2eMN5qy/7FLHXSYikoT/dSOaoxuA+U73kJ+09DzZ1x1vBXOtfXH/nBosnyTXCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:11:41.273245Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.06517","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65b646080f7ffc1ce3f02f9c8d0783fd671e0963ac9351e3943b728d4e19f0a4","sha256:94ae6db46d26cfc831bd49deac4d09d16e3cf72567724e648d19ea6cd99a8480"],"state_sha256":"719b35e329982788d93c5ffd842f02dc20e338cba035e911a00ee3c2236b50a6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+GT0H/fwKnvDyCdnxx3S4Ra0t2CTmEHNTrQWg7kk3n4ZWE13+YFfL1bGw8m2OXcD2rahcUwi1VSAzvjnmK07Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T01:10:48.674299Z","bundle_sha256":"adffc9f0893fbf770d9a8c09a36bc80f4efffd23fcdd6804cb14001209affb0c"}}