{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:O6OCHJ5JNX7CP5TFBNJHUGRRGS","short_pith_number":"pith:O6OCHJ5J","canonical_record":{"source":{"id":"2412.05240","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-12-06T18:18:26Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"9aefbef81fd8331315addebc02b21358902c7a9e363c4b876b5c082a980341ed","abstract_canon_sha256":"20987555ea96e50bb571fb906c6059df05d0a21bc363250ba0151b3a4ebf5405"},"schema_version":"1.0"},"canonical_sha256":"779c23a7a96dfe27f6650b527a1a3134b689507e8964f443abbfc6488a230e8c","source":{"kind":"arxiv","id":"2412.05240","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.05240","created_at":"2026-07-05T09:45:30Z"},{"alias_kind":"arxiv_version","alias_value":"2412.05240v1","created_at":"2026-07-05T09:45:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05240","created_at":"2026-07-05T09:45:30Z"},{"alias_kind":"pith_short_12","alias_value":"O6OCHJ5JNX7C","created_at":"2026-07-05T09:45:30Z"},{"alias_kind":"pith_short_16","alias_value":"O6OCHJ5JNX7CP5TF","created_at":"2026-07-05T09:45:30Z"},{"alias_kind":"pith_short_8","alias_value":"O6OCHJ5J","created_at":"2026-07-05T09:45:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:O6OCHJ5JNX7CP5TFBNJHUGRRGS","target":"record","payload":{"canonical_record":{"source":{"id":"2412.05240","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-12-06T18:18:26Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"9aefbef81fd8331315addebc02b21358902c7a9e363c4b876b5c082a980341ed","abstract_canon_sha256":"20987555ea96e50bb571fb906c6059df05d0a21bc363250ba0151b3a4ebf5405"},"schema_version":"1.0"},"canonical_sha256":"779c23a7a96dfe27f6650b527a1a3134b689507e8964f443abbfc6488a230e8c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:30.601901Z","signature_b64":"NI5iNlcRSfOxhdaLylqjUBuoVfKtiZ+XpNcfrW31EmYeiG3FEpmSSdvs9Y13Q4Casjg5srXutnZCRBeoelV/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"779c23a7a96dfe27f6650b527a1a3134b689507e8964f443abbfc6488a230e8c","last_reissued_at":"2026-07-05T09:45:30.601361Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:30.601361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.05240","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":"2026-07-05T09:45:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3xze4fm+b1zeNHi2iD2UFWLveCW2VrjGSkO0mYBq5GLOdYNGhBm7eV61ZAZBoZG5g7Wh4v5UFIur1QyeAHgfBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:21:29.123960Z"},"content_sha256":"20bd97ab476be19109144d3c64d28f1999b7e6985187978bd3a0317fc07628b1","schema_version":"1.0","event_id":"sha256:20bd97ab476be19109144d3c64d28f1999b7e6985187978bd3a0317fc07628b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:O6OCHJ5JNX7CP5TFBNJHUGRRGS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automated, Unsupervised, and Auto-parameterized Inference of Data Patterns and Anomaly Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.SE","authors_text":"Ettore Merlo, Heng Li, Maxime Lamothe, Qiaolin Qin","submitted_at":"2024-12-06T18:18:26Z","abstract_excerpt":"With the advent of data-centric and machine learning (ML) systems, data quality is playing an increasingly critical role in ensuring the overall quality of software systems. Data preparation, an essential step towards high data quality, is known to be a highly effort-intensive process. Although prior studies have dealt with one of the most impacting issues, data pattern violations, these studies usually require data-specific configurations (i.e., parameterized) or use carefully curated data as learning examples (i.e., supervised), relying on domain knowledge and deep understanding of the data,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05240","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/2412.05240/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":"2026-07-05T09:45:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"17q/jYrRsMXr4t7Q709+DrTOhODiVva6tYp/GQRUsTDCfWJKG+/9OdX9bnNtGfoLc2XnZKuNf3rbnEDlRoJJCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:21:29.124455Z"},"content_sha256":"f0ede76047a113d6a5bfd8e35fb6f6b4adae2d1dd4a782950a8e612e842e02a2","schema_version":"1.0","event_id":"sha256:f0ede76047a113d6a5bfd8e35fb6f6b4adae2d1dd4a782950a8e612e842e02a2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O6OCHJ5JNX7CP5TFBNJHUGRRGS/bundle.json","state_url":"https://pith.science/pith/O6OCHJ5JNX7CP5TFBNJHUGRRGS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O6OCHJ5JNX7CP5TFBNJHUGRRGS/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":"2026-08-04T10:21:29Z","links":{"resolver":"https://pith.science/pith/O6OCHJ5JNX7CP5TFBNJHUGRRGS","bundle":"https://pith.science/pith/O6OCHJ5JNX7CP5TFBNJHUGRRGS/bundle.json","state":"https://pith.science/pith/O6OCHJ5JNX7CP5TFBNJHUGRRGS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O6OCHJ5JNX7CP5TFBNJHUGRRGS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:O6OCHJ5JNX7CP5TFBNJHUGRRGS","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":"20987555ea96e50bb571fb906c6059df05d0a21bc363250ba0151b3a4ebf5405","cross_cats_sorted":["cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-12-06T18:18:26Z","title_canon_sha256":"9aefbef81fd8331315addebc02b21358902c7a9e363c4b876b5c082a980341ed"},"schema_version":"1.0","source":{"id":"2412.05240","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.05240","created_at":"2026-07-05T09:45:30Z"},{"alias_kind":"arxiv_version","alias_value":"2412.05240v1","created_at":"2026-07-05T09:45:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05240","created_at":"2026-07-05T09:45:30Z"},{"alias_kind":"pith_short_12","alias_value":"O6OCHJ5JNX7C","created_at":"2026-07-05T09:45:30Z"},{"alias_kind":"pith_short_16","alias_value":"O6OCHJ5JNX7CP5TF","created_at":"2026-07-05T09:45:30Z"},{"alias_kind":"pith_short_8","alias_value":"O6OCHJ5J","created_at":"2026-07-05T09:45:30Z"}],"graph_snapshots":[{"event_id":"sha256:f0ede76047a113d6a5bfd8e35fb6f6b4adae2d1dd4a782950a8e612e842e02a2","target":"graph","created_at":"2026-07-05T09:45:30Z","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/2412.05240/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the advent of data-centric and machine learning (ML) systems, data quality is playing an increasingly critical role in ensuring the overall quality of software systems. Data preparation, an essential step towards high data quality, is known to be a highly effort-intensive process. Although prior studies have dealt with one of the most impacting issues, data pattern violations, these studies usually require data-specific configurations (i.e., parameterized) or use carefully curated data as learning examples (i.e., supervised), relying on domain knowledge and deep understanding of the data,","authors_text":"Ettore Merlo, Heng Li, Maxime Lamothe, Qiaolin Qin","cross_cats":["cs.DB"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-12-06T18:18:26Z","title":"Automated, Unsupervised, and Auto-parameterized Inference of Data Patterns and Anomaly Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05240","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":"sha256:20bd97ab476be19109144d3c64d28f1999b7e6985187978bd3a0317fc07628b1","target":"record","created_at":"2026-07-05T09:45:30Z","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":"20987555ea96e50bb571fb906c6059df05d0a21bc363250ba0151b3a4ebf5405","cross_cats_sorted":["cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-12-06T18:18:26Z","title_canon_sha256":"9aefbef81fd8331315addebc02b21358902c7a9e363c4b876b5c082a980341ed"},"schema_version":"1.0","source":{"id":"2412.05240","kind":"arxiv","version":1}},"canonical_sha256":"779c23a7a96dfe27f6650b527a1a3134b689507e8964f443abbfc6488a230e8c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"779c23a7a96dfe27f6650b527a1a3134b689507e8964f443abbfc6488a230e8c","first_computed_at":"2026-07-05T09:45:30.601361Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:30.601361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NI5iNlcRSfOxhdaLylqjUBuoVfKtiZ+XpNcfrW31EmYeiG3FEpmSSdvs9Y13Q4Casjg5srXutnZCRBeoelV/Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:30.601901Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.05240","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20bd97ab476be19109144d3c64d28f1999b7e6985187978bd3a0317fc07628b1","sha256:f0ede76047a113d6a5bfd8e35fb6f6b4adae2d1dd4a782950a8e612e842e02a2"],"state_sha256":"6a9f7f2e6c4d2e22bae6808bdf0b2ad9f9c379f08509fe372f255e475ae952c7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1LAUeT+wm8esSnupcOxvsUzOfPXcyd1jGupiiVKwrybnkRyRCP/dZfjCQcxOiAAiad0ABZpeExUBlgNBtxnrDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T10:21:29.128934Z","bundle_sha256":"2c2d912604962533867b757ba8ba7ae7b51df3b2db38b11b1796ecf44388073f"}}