{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:V6IEXRA7TGIO6OLCQY2ZVLSPTF","short_pith_number":"pith:V6IEXRA7","canonical_record":{"source":{"id":"2306.02421","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-06-04T17:53:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b8c17090424185b92371cff22df01bd9184f0e46e9eaf30ab3eca34f502f3b67","abstract_canon_sha256":"091b3898148c34c21aa7e0578bdb72a283004214e989fc5b375c712f23c0abd0"},"schema_version":"1.0"},"canonical_sha256":"af904bc41f9990ef396286359aae4f996bf4f4ec2cebe5414324c0c374c7d695","source":{"kind":"arxiv","id":"2306.02421","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02421","created_at":"2026-07-05T06:17:17Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02421v1","created_at":"2026-07-05T06:17:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02421","created_at":"2026-07-05T06:17:17Z"},{"alias_kind":"pith_short_12","alias_value":"V6IEXRA7TGIO","created_at":"2026-07-05T06:17:17Z"},{"alias_kind":"pith_short_16","alias_value":"V6IEXRA7TGIO6OLC","created_at":"2026-07-05T06:17:17Z"},{"alias_kind":"pith_short_8","alias_value":"V6IEXRA7","created_at":"2026-07-05T06:17:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:V6IEXRA7TGIO6OLCQY2ZVLSPTF","target":"record","payload":{"canonical_record":{"source":{"id":"2306.02421","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-06-04T17:53:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b8c17090424185b92371cff22df01bd9184f0e46e9eaf30ab3eca34f502f3b67","abstract_canon_sha256":"091b3898148c34c21aa7e0578bdb72a283004214e989fc5b375c712f23c0abd0"},"schema_version":"1.0"},"canonical_sha256":"af904bc41f9990ef396286359aae4f996bf4f4ec2cebe5414324c0c374c7d695","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:17.120414Z","signature_b64":"u6Q3vvljH0f1h7HUxXqDv7Zh4JfQ3XHBsgGmqp3j7a8MoOIX1MSDn6lvvZr8ng5uvnHn4OpT+wOzO2G1DaJtCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af904bc41f9990ef396286359aae4f996bf4f4ec2cebe5414324c0c374c7d695","last_reissued_at":"2026-07-05T06:17:17.119897Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:17.119897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.02421","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":"2026-07-05T06:17:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P7SLAYhOMm8eK3XY7DK9OQa2y8FOWCIv0c+TsxjiRG6RM28Gi7t8Vf+C8cHk+w+dvle2X2PqyZf6rqK1cJlHAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T14:48:21.563014Z"},"content_sha256":"3bf6c8795bbb52576ee7f9dce483f22540c97d32fabd2b8996ebea0de2b11e14","schema_version":"1.0","event_id":"sha256:3bf6c8795bbb52576ee7f9dce483f22540c97d32fabd2b8996ebea0de2b11e14"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:V6IEXRA7TGIO6OLCQY2ZVLSPTF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Auto-Validate by-History: Auto-Program Data Quality Constraints to Validate Recurring Data Pipelines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Dezhan Tu, Dongmei Zhang, Haidong Zhang, Han Shi, Song Ge, Surajit Chaudhuri, Weiwei Cui, Yeye He","submitted_at":"2023-06-04T17:53:30Z","abstract_excerpt":"Data pipelines are widely employed in modern enterprises to power a variety of Machine-Learning (ML) and Business-Intelligence (BI) applications. Crucially, these pipelines are \\emph{recurring} (e.g., daily or hourly) in production settings to keep data updated so that ML models can be re-trained regularly, and BI dashboards refreshed frequently. However, data quality (DQ) issues can often creep into recurring pipelines because of upstream schema and data drift over time. As modern enterprises operate thousands of recurring pipelines, today data engineers have to spend substantial efforts to \\"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02421","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/2306.02421/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":"2026-07-05T06:17:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AXgjByfKyR9RtRmBrWF6Cqpm5hRUENw1LmUtYubKZRIDNWAw/oGFuTC7SaUNBv+xJRdo+BFC7l24POR1WSTBBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T14:48:21.563399Z"},"content_sha256":"1d49d4755e2dc729ffa6d563bb144efaef1e53b3d6a0462ec14d97b82e11e07b","schema_version":"1.0","event_id":"sha256:1d49d4755e2dc729ffa6d563bb144efaef1e53b3d6a0462ec14d97b82e11e07b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V6IEXRA7TGIO6OLCQY2ZVLSPTF/bundle.json","state_url":"https://pith.science/pith/V6IEXRA7TGIO6OLCQY2ZVLSPTF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V6IEXRA7TGIO6OLCQY2ZVLSPTF/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":"2026-07-06T14:48:21Z","links":{"resolver":"https://pith.science/pith/V6IEXRA7TGIO6OLCQY2ZVLSPTF","bundle":"https://pith.science/pith/V6IEXRA7TGIO6OLCQY2ZVLSPTF/bundle.json","state":"https://pith.science/pith/V6IEXRA7TGIO6OLCQY2ZVLSPTF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V6IEXRA7TGIO6OLCQY2ZVLSPTF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:V6IEXRA7TGIO6OLCQY2ZVLSPTF","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":"091b3898148c34c21aa7e0578bdb72a283004214e989fc5b375c712f23c0abd0","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-06-04T17:53:30Z","title_canon_sha256":"b8c17090424185b92371cff22df01bd9184f0e46e9eaf30ab3eca34f502f3b67"},"schema_version":"1.0","source":{"id":"2306.02421","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02421","created_at":"2026-07-05T06:17:17Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02421v1","created_at":"2026-07-05T06:17:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02421","created_at":"2026-07-05T06:17:17Z"},{"alias_kind":"pith_short_12","alias_value":"V6IEXRA7TGIO","created_at":"2026-07-05T06:17:17Z"},{"alias_kind":"pith_short_16","alias_value":"V6IEXRA7TGIO6OLC","created_at":"2026-07-05T06:17:17Z"},{"alias_kind":"pith_short_8","alias_value":"V6IEXRA7","created_at":"2026-07-05T06:17:17Z"}],"graph_snapshots":[{"event_id":"sha256:1d49d4755e2dc729ffa6d563bb144efaef1e53b3d6a0462ec14d97b82e11e07b","target":"graph","created_at":"2026-07-05T06:17:17Z","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/2306.02421/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data pipelines are widely employed in modern enterprises to power a variety of Machine-Learning (ML) and Business-Intelligence (BI) applications. Crucially, these pipelines are \\emph{recurring} (e.g., daily or hourly) in production settings to keep data updated so that ML models can be re-trained regularly, and BI dashboards refreshed frequently. However, data quality (DQ) issues can often creep into recurring pipelines because of upstream schema and data drift over time. As modern enterprises operate thousands of recurring pipelines, today data engineers have to spend substantial efforts to \\","authors_text":"Dezhan Tu, Dongmei Zhang, Haidong Zhang, Han Shi, Song Ge, Surajit Chaudhuri, Weiwei Cui, Yeye He","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-06-04T17:53:30Z","title":"Auto-Validate by-History: Auto-Program Data Quality Constraints to Validate Recurring Data Pipelines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02421","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":"sha256:3bf6c8795bbb52576ee7f9dce483f22540c97d32fabd2b8996ebea0de2b11e14","target":"record","created_at":"2026-07-05T06:17:17Z","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":"091b3898148c34c21aa7e0578bdb72a283004214e989fc5b375c712f23c0abd0","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2023-06-04T17:53:30Z","title_canon_sha256":"b8c17090424185b92371cff22df01bd9184f0e46e9eaf30ab3eca34f502f3b67"},"schema_version":"1.0","source":{"id":"2306.02421","kind":"arxiv","version":1}},"canonical_sha256":"af904bc41f9990ef396286359aae4f996bf4f4ec2cebe5414324c0c374c7d695","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af904bc41f9990ef396286359aae4f996bf4f4ec2cebe5414324c0c374c7d695","first_computed_at":"2026-07-05T06:17:17.119897Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:17:17.119897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u6Q3vvljH0f1h7HUxXqDv7Zh4JfQ3XHBsgGmqp3j7a8MoOIX1MSDn6lvvZr8ng5uvnHn4OpT+wOzO2G1DaJtCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:17:17.120414Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.02421","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3bf6c8795bbb52576ee7f9dce483f22540c97d32fabd2b8996ebea0de2b11e14","sha256:1d49d4755e2dc729ffa6d563bb144efaef1e53b3d6a0462ec14d97b82e11e07b"],"state_sha256":"61dfa3bd956e9f43262e593af04ad34846f18dcc3aeb2918c5c34fa49b246368"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PdFJsBicd7OKzWPRQA1fXABESEB18TNMrt0zs7dLbVWFPOhG5NYGFKA9WPy5OL4vyaAFoWmgCznf0qHnBuy8AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T14:48:21.565257Z","bundle_sha256":"f205cda28dfc034e0c35b5143e2a0cf5985b320d0880e5545b4f74bbfe1f76ec"}}