{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:BU7WQK4XYCZMWHHKAHY5LVJTRI","short_pith_number":"pith:BU7WQK4X","canonical_record":{"source":{"id":"1609.05113","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2016-09-16T15:52:44Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"03e791f6345f0dc039e899eeb504be4718ede670d581512d1602f8ecb94f904c","abstract_canon_sha256":"751fbce06c8b57e10a7f49d9db10989b021262039ddf9690b21a82697d9aa976"},"schema_version":"1.0"},"canonical_sha256":"0d3f682b97c0b2cb1cea01f1d5d5338a369cfa46c0b00a458e29f97531a57570","source":{"kind":"arxiv","id":"1609.05113","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.05113","created_at":"2026-05-18T01:04:31Z"},{"alias_kind":"arxiv_version","alias_value":"1609.05113v1","created_at":"2026-05-18T01:04:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.05113","created_at":"2026-05-18T01:04:31Z"},{"alias_kind":"pith_short_12","alias_value":"BU7WQK4XYCZM","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_16","alias_value":"BU7WQK4XYCZMWHHK","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_8","alias_value":"BU7WQK4X","created_at":"2026-05-18T12:30:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:BU7WQK4XYCZMWHHKAHY5LVJTRI","target":"record","payload":{"canonical_record":{"source":{"id":"1609.05113","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2016-09-16T15:52:44Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"03e791f6345f0dc039e899eeb504be4718ede670d581512d1602f8ecb94f904c","abstract_canon_sha256":"751fbce06c8b57e10a7f49d9db10989b021262039ddf9690b21a82697d9aa976"},"schema_version":"1.0"},"canonical_sha256":"0d3f682b97c0b2cb1cea01f1d5d5338a369cfa46c0b00a458e29f97531a57570","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:04:31.463946Z","signature_b64":"BCom9k8iBcbsxOFyWXrLz8oFkOCOOU2ej0Kep2JhaXwOjxw1qGYSLm0+isVdUsSEclVKFZujBD9g6oMX4Fq4Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d3f682b97c0b2cb1cea01f1d5d5338a369cfa46c0b00a458e29f97531a57570","last_reissued_at":"2026-05-18T01:04:31.463277Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:04:31.463277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1609.05113","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":"2026-05-18T01:04:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8d+dgQhSGcFaF6Ku42rRn1Fib7IJhUkRc6doVZENSb/5M0dnW7d1n23IfoCf4Euuty1+ySt1adNrooxNNa+PAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T12:31:39.891770Z"},"content_sha256":"cc9626ba304101351ddfee4f2c79242404b61b5512c68d7d796ad5c871f69c0f","schema_version":"1.0","event_id":"sha256:cc9626ba304101351ddfee4f2c79242404b61b5512c68d7d796ad5c871f69c0f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:BU7WQK4XYCZMWHHKAHY5LVJTRI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bleach: A Distributed Stream Data Cleaning System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.DB","authors_text":"Marko Vukolic, Pietro Michiardi, Yongchao Tian","submitted_at":"2016-09-16T15:52:44Z","abstract_excerpt":"In this paper we address the problem of rule-based stream data cleaning, which sets stringent requirements on latency, rule dynamics and ability to cope with the unbounded nature of data streams.\n  We design a system, called Bleach, which achieves real-time violation detection and data repair on a dirty data stream. Bleach relies on efficient, compact and distributed data structures to maintain the necessary state to repair data, using an incremental version of the equivalence class algorithm. Additionally, it supports rule dynamics and uses a \"cumulative\" sliding window operation to improve c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.05113","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":"2026-05-18T01:04:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rbbha4A46snXXMs1/CI7/yhw+aBer1ip5wbdICfRLG+Im062cr+rcUtQVbOEbk2Lmm8BmKsi254qwg8PkNVvBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T12:31:39.892560Z"},"content_sha256":"19122df5ee35e7d6c926c8500f39c25f7b14c716ea368d85f26dd47e9145b7b5","schema_version":"1.0","event_id":"sha256:19122df5ee35e7d6c926c8500f39c25f7b14c716ea368d85f26dd47e9145b7b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BU7WQK4XYCZMWHHKAHY5LVJTRI/bundle.json","state_url":"https://pith.science/pith/BU7WQK4XYCZMWHHKAHY5LVJTRI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BU7WQK4XYCZMWHHKAHY5LVJTRI/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":"2026-06-10T12:31:39Z","links":{"resolver":"https://pith.science/pith/BU7WQK4XYCZMWHHKAHY5LVJTRI","bundle":"https://pith.science/pith/BU7WQK4XYCZMWHHKAHY5LVJTRI/bundle.json","state":"https://pith.science/pith/BU7WQK4XYCZMWHHKAHY5LVJTRI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BU7WQK4XYCZMWHHKAHY5LVJTRI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:BU7WQK4XYCZMWHHKAHY5LVJTRI","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":"751fbce06c8b57e10a7f49d9db10989b021262039ddf9690b21a82697d9aa976","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2016-09-16T15:52:44Z","title_canon_sha256":"03e791f6345f0dc039e899eeb504be4718ede670d581512d1602f8ecb94f904c"},"schema_version":"1.0","source":{"id":"1609.05113","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.05113","created_at":"2026-05-18T01:04:31Z"},{"alias_kind":"arxiv_version","alias_value":"1609.05113v1","created_at":"2026-05-18T01:04:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.05113","created_at":"2026-05-18T01:04:31Z"},{"alias_kind":"pith_short_12","alias_value":"BU7WQK4XYCZM","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_16","alias_value":"BU7WQK4XYCZMWHHK","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_8","alias_value":"BU7WQK4X","created_at":"2026-05-18T12:30:09Z"}],"graph_snapshots":[{"event_id":"sha256:19122df5ee35e7d6c926c8500f39c25f7b14c716ea368d85f26dd47e9145b7b5","target":"graph","created_at":"2026-05-18T01:04:31Z","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":"In this paper we address the problem of rule-based stream data cleaning, which sets stringent requirements on latency, rule dynamics and ability to cope with the unbounded nature of data streams.\n  We design a system, called Bleach, which achieves real-time violation detection and data repair on a dirty data stream. Bleach relies on efficient, compact and distributed data structures to maintain the necessary state to repair data, using an incremental version of the equivalence class algorithm. Additionally, it supports rule dynamics and uses a \"cumulative\" sliding window operation to improve c","authors_text":"Marko Vukolic, Pietro Michiardi, Yongchao Tian","cross_cats":["cs.DC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2016-09-16T15:52:44Z","title":"Bleach: A Distributed Stream Data Cleaning System"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.05113","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:cc9626ba304101351ddfee4f2c79242404b61b5512c68d7d796ad5c871f69c0f","target":"record","created_at":"2026-05-18T01:04:31Z","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":"751fbce06c8b57e10a7f49d9db10989b021262039ddf9690b21a82697d9aa976","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2016-09-16T15:52:44Z","title_canon_sha256":"03e791f6345f0dc039e899eeb504be4718ede670d581512d1602f8ecb94f904c"},"schema_version":"1.0","source":{"id":"1609.05113","kind":"arxiv","version":1}},"canonical_sha256":"0d3f682b97c0b2cb1cea01f1d5d5338a369cfa46c0b00a458e29f97531a57570","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d3f682b97c0b2cb1cea01f1d5d5338a369cfa46c0b00a458e29f97531a57570","first_computed_at":"2026-05-18T01:04:31.463277Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:04:31.463277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BCom9k8iBcbsxOFyWXrLz8oFkOCOOU2ej0Kep2JhaXwOjxw1qGYSLm0+isVdUsSEclVKFZujBD9g6oMX4Fq4Cg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:04:31.463946Z","signed_message":"canonical_sha256_bytes"},"source_id":"1609.05113","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc9626ba304101351ddfee4f2c79242404b61b5512c68d7d796ad5c871f69c0f","sha256:19122df5ee35e7d6c926c8500f39c25f7b14c716ea368d85f26dd47e9145b7b5"],"state_sha256":"5b0fc14430888dd30e1284a59e146f9209af9bb91cffb14c87493b03578ba8b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1MqHxS+4LGXKrOVvakvK66Fnp+nqSdytJMfkl2Y8WFpRJLKGoLZiZFaSDUL6SQ2MRx6qHQwsgmfE8m9YB6NVBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T12:31:39.896657Z","bundle_sha256":"73606a7d648978a025de537a91eea3912fc75f98ab6ca15ab28ea2ddb90d0cf1"}}