{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:PPQJ5MULANBT3KILHMEXT7VFNB","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":"e843f78822732d896488764dea4f39860a85e01af484b64d485d577da76df5c6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-08-05T14:11:14Z","title_canon_sha256":"b6a87ec91610bbe13ebf89a812ac9cfc486171c438a33213519cf0c17d85324d"},"schema_version":"1.0","source":{"id":"1808.01621","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.01621","created_at":"2026-05-18T00:08:52Z"},{"alias_kind":"arxiv_version","alias_value":"1808.01621v1","created_at":"2026-05-18T00:08:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.01621","created_at":"2026-05-18T00:08:52Z"},{"alias_kind":"pith_short_12","alias_value":"PPQJ5MULANBT","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"PPQJ5MULANBT3KIL","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"PPQJ5MUL","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:47fd3d5555f81f6197f2035af64bdb1787dab05f76c7dd13a6b6b6fc53be1435","target":"graph","created_at":"2026-05-18T00:08:52Z","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":"Current conditional functional dependencies (CFDs) discovery algorithms always need a well-prepared training data set. This makes them difficult to be applied on large datasets which are always in low-quality. To handle the volume issue of big data, we develop the sampling algorithms to obtain a small representative training set. For the low-quality issue of big data, we then design the fault-tolerant rule discovery algorithm and the conflict resolution algorithm. We also propose parameter selection strategy for CFD discovery algorithm to ensure its effectiveness. Experimental results demonstr","authors_text":"Hong Gao, Hongzhi Wang, Jianzhong Li, Jiawei Zhao, Mingda Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-08-05T14:11:14Z","title":"Mining CFD Rules on Big Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.01621","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":"sha256:8f46a0f1151d33eb649a7c8a73e75306c46d92b4c8afa9dfc61e5061ab1f5cc3","target":"record","created_at":"2026-05-18T00:08:52Z","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":"e843f78822732d896488764dea4f39860a85e01af484b64d485d577da76df5c6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-08-05T14:11:14Z","title_canon_sha256":"b6a87ec91610bbe13ebf89a812ac9cfc486171c438a33213519cf0c17d85324d"},"schema_version":"1.0","source":{"id":"1808.01621","kind":"arxiv","version":1}},"canonical_sha256":"7be09eb28b03433da90b3b0979fea568749d2bc9f6c7f1a5c18347e2d1d568e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7be09eb28b03433da90b3b0979fea568749d2bc9f6c7f1a5c18347e2d1d568e7","first_computed_at":"2026-05-18T00:08:52.395260Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:08:52.395260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xoYTAJVr2QjEWpszbe+BcZPNGrdZsD4U5z051Mo1Fz9simQP1tv2BQU5rwW3NvtnyJXygTmGARhwYowxVBkXCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:08:52.395980Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.01621","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f46a0f1151d33eb649a7c8a73e75306c46d92b4c8afa9dfc61e5061ab1f5cc3","sha256:47fd3d5555f81f6197f2035af64bdb1787dab05f76c7dd13a6b6b6fc53be1435"],"state_sha256":"1a18da0ee9c830eb916e8a2c98f7d1a95a86080a504547cc849526a2a1a0d4fb"}