{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ADV5M33ITKFYR3ITOUYAMGHWUB","short_pith_number":"pith:ADV5M33I","canonical_record":{"source":{"id":"2607.23636","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2026-07-26T13:01:48Z","cross_cats_sorted":["cs.AI","cs.CE","cs.LG"],"title_canon_sha256":"cccef1b8fb55d14e5ac1302dc0577646989ffaa86ad422281dd3f4d96288232f","abstract_canon_sha256":"5fb3d8e2f0f95c0f614a0bf69f0d9066c0ab5e0d02ddbbe4f588c44dae497528"},"schema_version":"1.0"},"canonical_sha256":"00ebd66f689a8b88ed1375300618f6a06fa7805bd08df371708bffa0797e207c","source":{"kind":"arxiv","id":"2607.23636","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23636","created_at":"2026-07-28T01:23:03Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23636v1","created_at":"2026-07-28T01:23:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23636","created_at":"2026-07-28T01:23:03Z"},{"alias_kind":"pith_short_12","alias_value":"ADV5M33ITKFY","created_at":"2026-07-28T01:23:03Z"},{"alias_kind":"pith_short_16","alias_value":"ADV5M33ITKFYR3IT","created_at":"2026-07-28T01:23:03Z"},{"alias_kind":"pith_short_8","alias_value":"ADV5M33I","created_at":"2026-07-28T01:23:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ADV5M33ITKFYR3ITOUYAMGHWUB","target":"record","payload":{"canonical_record":{"source":{"id":"2607.23636","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2026-07-26T13:01:48Z","cross_cats_sorted":["cs.AI","cs.CE","cs.LG"],"title_canon_sha256":"cccef1b8fb55d14e5ac1302dc0577646989ffaa86ad422281dd3f4d96288232f","abstract_canon_sha256":"5fb3d8e2f0f95c0f614a0bf69f0d9066c0ab5e0d02ddbbe4f588c44dae497528"},"schema_version":"1.0"},"canonical_sha256":"00ebd66f689a8b88ed1375300618f6a06fa7805bd08df371708bffa0797e207c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:23:03.006968Z","signature_b64":"wnhhw8FRq7yhLa15KcFCRaN+/9YcCwOCEsrBdyDD7f1ZksvzFMivU9JfPIjoQ8rI+kCDdQs0Dz/9j5T/U4gRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00ebd66f689a8b88ed1375300618f6a06fa7805bd08df371708bffa0797e207c","last_reissued_at":"2026-07-28T01:23:03.006164Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:23:03.006164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.23636","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":"2026-07-28T01:23:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dUV6hNJ9RtTthm3jKf/YcqVbOG3DJPSHuXfKcy6khrk5//pFO0aIx4wBNizaiBkrxGYNFdCWj1/zEigU5CyeBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:08:26.929357Z"},"content_sha256":"71867dd1c7fa564c127e89812559485703564bde97216e9033d56dc2e520753a","schema_version":"1.0","event_id":"sha256:71867dd1c7fa564c127e89812559485703564bde97216e9033d56dc2e520753a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ADV5M33ITKFYR3ITOUYAMGHWUB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Extending Desbordante with Probabilistic Functional Dependency Discovery Support","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.LG"],"primary_cat":"cs.DB","authors_text":"George Chernishev, Ilia Barutkin, Maxim Fofanov, Sergey Belokonny, Vladislav Makeev","submitted_at":"2026-07-26T13:01:48Z","abstract_excerpt":"Data profiling aims to extract complex patterns from data for further analysis and use that data in domains such as data cleaning, data deduplication, anomaly detection, and many more.\n  Functional dependencies (FDs) are one of the most well-known patterns. However, they are poorly suited for these tasks, as real data is usually dirty, and the rigid definition of FDs does not allow algorithms to locate them. For this reason, there are several formulations aimed at relaxing FDs to support dirty data, with approximate functional dependency (AFD) being the most popular one. Another formulation is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23636","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/2607.23636/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":"2026-07-28T01:23:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t7UMyf3Pi8fUBRUYrfxobVolFx1hf4umKfChmUFTlwNqtzxud6Se33n1gEiduj0tB188FqbJDnI3v5mWBARPAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:08:26.929867Z"},"content_sha256":"6cd465c19c0b7cb6ec47d06e7056eb453a2168c9325d67ef20945d523d03da29","schema_version":"1.0","event_id":"sha256:6cd465c19c0b7cb6ec47d06e7056eb453a2168c9325d67ef20945d523d03da29"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ADV5M33ITKFYR3ITOUYAMGHWUB/bundle.json","state_url":"https://pith.science/pith/ADV5M33ITKFYR3ITOUYAMGHWUB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ADV5M33ITKFYR3ITOUYAMGHWUB/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":"2026-08-09T11:08:26Z","links":{"resolver":"https://pith.science/pith/ADV5M33ITKFYR3ITOUYAMGHWUB","bundle":"https://pith.science/pith/ADV5M33ITKFYR3ITOUYAMGHWUB/bundle.json","state":"https://pith.science/pith/ADV5M33ITKFYR3ITOUYAMGHWUB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ADV5M33ITKFYR3ITOUYAMGHWUB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ADV5M33ITKFYR3ITOUYAMGHWUB","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":"5fb3d8e2f0f95c0f614a0bf69f0d9066c0ab5e0d02ddbbe4f588c44dae497528","cross_cats_sorted":["cs.AI","cs.CE","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2026-07-26T13:01:48Z","title_canon_sha256":"cccef1b8fb55d14e5ac1302dc0577646989ffaa86ad422281dd3f4d96288232f"},"schema_version":"1.0","source":{"id":"2607.23636","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23636","created_at":"2026-07-28T01:23:03Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23636v1","created_at":"2026-07-28T01:23:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23636","created_at":"2026-07-28T01:23:03Z"},{"alias_kind":"pith_short_12","alias_value":"ADV5M33ITKFY","created_at":"2026-07-28T01:23:03Z"},{"alias_kind":"pith_short_16","alias_value":"ADV5M33ITKFYR3IT","created_at":"2026-07-28T01:23:03Z"},{"alias_kind":"pith_short_8","alias_value":"ADV5M33I","created_at":"2026-07-28T01:23:03Z"}],"graph_snapshots":[{"event_id":"sha256:6cd465c19c0b7cb6ec47d06e7056eb453a2168c9325d67ef20945d523d03da29","target":"graph","created_at":"2026-07-28T01:23:03Z","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/2607.23636/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data profiling aims to extract complex patterns from data for further analysis and use that data in domains such as data cleaning, data deduplication, anomaly detection, and many more.\n  Functional dependencies (FDs) are one of the most well-known patterns. However, they are poorly suited for these tasks, as real data is usually dirty, and the rigid definition of FDs does not allow algorithms to locate them. For this reason, there are several formulations aimed at relaxing FDs to support dirty data, with approximate functional dependency (AFD) being the most popular one. Another formulation is","authors_text":"George Chernishev, Ilia Barutkin, Maxim Fofanov, Sergey Belokonny, Vladislav Makeev","cross_cats":["cs.AI","cs.CE","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2026-07-26T13:01:48Z","title":"Extending Desbordante with Probabilistic Functional Dependency Discovery Support"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23636","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":"sha256:71867dd1c7fa564c127e89812559485703564bde97216e9033d56dc2e520753a","target":"record","created_at":"2026-07-28T01:23:03Z","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":"5fb3d8e2f0f95c0f614a0bf69f0d9066c0ab5e0d02ddbbe4f588c44dae497528","cross_cats_sorted":["cs.AI","cs.CE","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2026-07-26T13:01:48Z","title_canon_sha256":"cccef1b8fb55d14e5ac1302dc0577646989ffaa86ad422281dd3f4d96288232f"},"schema_version":"1.0","source":{"id":"2607.23636","kind":"arxiv","version":1}},"canonical_sha256":"00ebd66f689a8b88ed1375300618f6a06fa7805bd08df371708bffa0797e207c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00ebd66f689a8b88ed1375300618f6a06fa7805bd08df371708bffa0797e207c","first_computed_at":"2026-07-28T01:23:03.006164Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:23:03.006164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wnhhw8FRq7yhLa15KcFCRaN+/9YcCwOCEsrBdyDD7f1ZksvzFMivU9JfPIjoQ8rI+kCDdQs0Dz/9j5T/U4gRCg==","signature_status":"signed_v1","signed_at":"2026-07-28T01:23:03.006968Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.23636","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71867dd1c7fa564c127e89812559485703564bde97216e9033d56dc2e520753a","sha256:6cd465c19c0b7cb6ec47d06e7056eb453a2168c9325d67ef20945d523d03da29"],"state_sha256":"0cfceeaa0cbed8db7af7789c3c20227a1eb9005ab7935c164a08d5fea51a7e80"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7/YpUtKLHeLN3oFcPf7GfpePg0VPC9Z0X82R/H7HFgah7YDnQ2Y4wSZ6WgJV478CmHAE06/2PPQYa5J3xG9jAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T11:08:26.934168Z","bundle_sha256":"2c1a62eedfdd8fb7c5b7b6edc7b4134937bed26424588c37d04e44a93e38ea52"}}