{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4ZB3UEOYTJCHDKWIK6J47ARO6L","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"22b4b3f8893540524cd01e2f7ec4e45538b7e8df39d3dd66190d43c210a3a193","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-08-04T06:41:14Z","title_canon_sha256":"689b43ad53004eace31435724617ff6bfe387c3cc78fe2d97f4fd0bdf26ff668"},"schema_version":"1.0","source":{"id":"2608.03199","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03199","created_at":"2026-08-05T00:46:09Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03199v1","created_at":"2026-08-05T00:46:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03199","created_at":"2026-08-05T00:46:09Z"},{"alias_kind":"pith_short_12","alias_value":"4ZB3UEOYTJCH","created_at":"2026-08-05T00:46:09Z"},{"alias_kind":"pith_short_16","alias_value":"4ZB3UEOYTJCHDKWI","created_at":"2026-08-05T00:46:09Z"},{"alias_kind":"pith_short_8","alias_value":"4ZB3UEOY","created_at":"2026-08-05T00:46:09Z"}],"graph_snapshots":[{"event_id":"sha256:ee5e0e65bf5245b66d2902e74f0002b5d0c2a4d58b038769a6ff712cf46b89ff","target":"graph","created_at":"2026-08-05T00:46:09Z","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/2608.03199/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Embedding-based training data deduplication retrieves candidate duplicate edges above an application similarity threshold, but fixed-probe inverted-file (IVF) search ignores this predicate when giving every query the same partition budget. Across four Hunyuan workloads, qualifying neighbors appear early despite sharply varying search depths. We present SieveIVF, a threshold-aware IVF executor that stops after $W$ consecutive searches find no qualifying candidate. The systems challenge is to preserve partition-major batching when each query's remaining work depends on prior results. Continuous ","authors_text":"Chufeng Chen, Junjie Chen, Ke Xu, Ming-Chang Yang, Rui Chen, Yuxuan Li, Zhe Chen, Zhifang Li, Zhisheng Hu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-08-04T06:41:14Z","title":"SieveIVF: Threshold-Aware IVF Execution for Large-Scale Training Data Deduplication"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03199","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":"sha256:3d1119cb41f51f70c7ceafbb72c4ed8c706821657a20db27f6cbbefa1bb610fc","target":"record","created_at":"2026-08-05T00:46:09Z","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":"22b4b3f8893540524cd01e2f7ec4e45538b7e8df39d3dd66190d43c210a3a193","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-08-04T06:41:14Z","title_canon_sha256":"689b43ad53004eace31435724617ff6bfe387c3cc78fe2d97f4fd0bdf26ff668"},"schema_version":"1.0","source":{"id":"2608.03199","kind":"arxiv","version":1}},"canonical_sha256":"e643ba11d89a4471aac85793cf822ef2da8e5236cca2405f77588dea48db55ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e643ba11d89a4471aac85793cf822ef2da8e5236cca2405f77588dea48db55ee","first_computed_at":"2026-08-05T00:46:09.064995Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T00:46:09.064995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FuaMHpwZkBFNrKQqOYocn2+nfe1iHCPBONjYKUCN197zowUbWtKChM6KcJb1iVXtotfKdw3Y5IBr6YwmBr3RDw==","signature_status":"signed_v1","signed_at":"2026-08-05T00:46:09.067487Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03199","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d1119cb41f51f70c7ceafbb72c4ed8c706821657a20db27f6cbbefa1bb610fc","sha256:ee5e0e65bf5245b66d2902e74f0002b5d0c2a4d58b038769a6ff712cf46b89ff","sha256:98199f0897885071a6b400a3d1e44a1d6813026830db5c31948d7f287e1e2abb"],"state_sha256":"bbaa6d4d7bf65442e0cfd3af0818b1e7eb13346c1497880e2b9ce95b65a885a6"}