{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MR4DJXRFGX2BATXDPF2JPT3FFK","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":"9b335d18414d19f57cdf63f6710b237cff406d4bd6978fc0c93a76e8a154829b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2023-01-14T19:14:51Z","title_canon_sha256":"187319fb3f07047334b6991a83a558d1f43d41a7a9df9e681509588fc542c2aa"},"schema_version":"1.0","source":{"id":"2301.05965","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.05965","created_at":"2026-07-05T05:33:26Z"},{"alias_kind":"arxiv_version","alias_value":"2301.05965v1","created_at":"2026-07-05T05:33:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.05965","created_at":"2026-07-05T05:33:26Z"},{"alias_kind":"pith_short_12","alias_value":"MR4DJXRFGX2B","created_at":"2026-07-05T05:33:26Z"},{"alias_kind":"pith_short_16","alias_value":"MR4DJXRFGX2BATXD","created_at":"2026-07-05T05:33:26Z"},{"alias_kind":"pith_short_8","alias_value":"MR4DJXRF","created_at":"2026-07-05T05:33:26Z"}],"graph_snapshots":[{"event_id":"sha256:aeec23c492b48646aa9fce5021665334a722988d5d8988941925a4d67c0cbc6a","target":"graph","created_at":"2026-07-05T05:33:26Z","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/2301.05965/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pioneering data profiling systems such as Metanome and OpenClean brought public attention to science-intensive data profiling. This type of profiling aims to extract complex patterns (primitives) such as functional dependencies, data constraints, association rules, and others. However, these tools are research prototypes rather than production-ready systems.\n  The following work presents Desbordante - a high-performance science-intensive data profiler with open source code. Unlike similar systems, it is built with emphasis on industrial application in a multi-user environment. It is efficient,","authors_text":"Alexander Smirnov, Alexey Shlyonskikh, Anna Rakhmukova, Anton Chernikov, Anton Chizhov, Arthur Saliou, Daniil Goncharov, Dmitrii Mandelshtam, Dmitriy Shcheka, Eduard Gaisin, George Chernishev, Ilia Barutkin, Ilya Shchuckin, Kirill Muraviev, Kirill Smirnov, Kirill Stupakov, Maxim Strutovsky, Michael Polyntsov, Mikhail Firsov, Mikhail Vyrodov, Nikita Bobrov, Stepan Manannikov, Vladislav Shalnev","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2023-01-14T19:14:51Z","title":"Desbordante: from benchmarking suite to high-performance science-intensive data profiler (preprint)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.05965","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":"sha256:172850cc27a1260722cfdb8c2e62ebfb9b87cb39acc73e1e6df69de3f61011d6","target":"record","created_at":"2026-07-05T05:33:26Z","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":"9b335d18414d19f57cdf63f6710b237cff406d4bd6978fc0c93a76e8a154829b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2023-01-14T19:14:51Z","title_canon_sha256":"187319fb3f07047334b6991a83a558d1f43d41a7a9df9e681509588fc542c2aa"},"schema_version":"1.0","source":{"id":"2301.05965","kind":"arxiv","version":1}},"canonical_sha256":"647834de2535f4104ee3797497cf652ab0f829f832572f192d12984a8e9b0707","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"647834de2535f4104ee3797497cf652ab0f829f832572f192d12984a8e9b0707","first_computed_at":"2026-07-05T05:33:26.132277Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:33:26.132277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"63NH86W2oaYcxhLRmPMyhhwuzyze3a+hjUOH+Ex6unI+xZZlq/heHAS1iOnzWwo3cJkxH548LfS0ip+S74zlCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:33:26.132737Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.05965","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:172850cc27a1260722cfdb8c2e62ebfb9b87cb39acc73e1e6df69de3f61011d6","sha256:aeec23c492b48646aa9fce5021665334a722988d5d8988941925a4d67c0cbc6a"],"state_sha256":"343524aff6fea0da73af8dca7775210fd2420c042d1b091f0f6e04b1e3e6307b"}