{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4ZB3UEOYTJCHDKWIK6J47ARO6L","short_pith_number":"pith:4ZB3UEOY","schema_version":"1.0","canonical_sha256":"e643ba11d89a4471aac85793cf822ef2da8e5236cca2405f77588dea48db55ee","source":{"kind":"arxiv","id":"2608.03199","version":1},"attestation_state":"computed","paper":{"title":"SieveIVF: Threshold-Aware IVF Execution for Large-Scale Training Data Deduplication","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Chufeng Chen, Junjie Chen, Ke Xu, Ming-Chang Yang, Rui Chen, Yuxuan Li, Zhe Chen, Zhifang Li, Zhisheng Hu","submitted_at":"2026-08-04T06:41:14Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.03199","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-08-04T06:41:14Z","cross_cats_sorted":[],"title_canon_sha256":"689b43ad53004eace31435724617ff6bfe387c3cc78fe2d97f4fd0bdf26ff668","abstract_canon_sha256":"22b4b3f8893540524cd01e2f7ec4e45538b7e8df39d3dd66190d43c210a3a193"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T00:46:09.067487Z","signature_b64":"FuaMHpwZkBFNrKQqOYocn2+nfe1iHCPBONjYKUCN197zowUbWtKChM6KcJb1iVXtotfKdw3Y5IBr6YwmBr3RDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e643ba11d89a4471aac85793cf822ef2da8e5236cca2405f77588dea48db55ee","last_reissued_at":"2026-08-05T00:46:09.064995Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T00:46:09.064995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SieveIVF: Threshold-Aware IVF Execution for Large-Scale Training Data Deduplication","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Chufeng Chen, Junjie Chen, Ke Xu, Ming-Chang Yang, Rui Chen, Yuxuan Li, Zhe Chen, Zhifang Li, Zhisheng Hu","submitted_at":"2026-08-04T06:41:14Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03199","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/2608.03199/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.03199","created_at":"2026-08-05T00:46:09.065987+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03199v1","created_at":"2026-08-05T00:46:09.065987+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03199","created_at":"2026-08-05T00:46:09.065987+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ZB3UEOYTJCH","created_at":"2026-08-05T00:46:09.065987+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ZB3UEOYTJCHDKWI","created_at":"2026-08-05T00:46:09.065987+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ZB3UEOY","created_at":"2026-08-05T00:46:09.065987+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ZB3UEOYTJCHDKWIK6J47ARO6L","json":"https://pith.science/pith/4ZB3UEOYTJCHDKWIK6J47ARO6L.json","graph_json":"https://pith.science/api/pith-number/4ZB3UEOYTJCHDKWIK6J47ARO6L/graph.json","events_json":"https://pith.science/api/pith-number/4ZB3UEOYTJCHDKWIK6J47ARO6L/events.json","paper":"https://pith.science/paper/4ZB3UEOY"},"agent_actions":{"view_html":"https://pith.science/pith/4ZB3UEOYTJCHDKWIK6J47ARO6L","download_json":"https://pith.science/pith/4ZB3UEOYTJCHDKWIK6J47ARO6L.json","view_paper":"https://pith.science/paper/4ZB3UEOY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03199&json=true","fetch_graph":"https://pith.science/api/pith-number/4ZB3UEOYTJCHDKWIK6J47ARO6L/graph.json","fetch_events":"https://pith.science/api/pith-number/4ZB3UEOYTJCHDKWIK6J47ARO6L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ZB3UEOYTJCHDKWIK6J47ARO6L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ZB3UEOYTJCHDKWIK6J47ARO6L/action/storage_attestation","attest_author":"https://pith.science/pith/4ZB3UEOYTJCHDKWIK6J47ARO6L/action/author_attestation","sign_citation":"https://pith.science/pith/4ZB3UEOYTJCHDKWIK6J47ARO6L/action/citation_signature","submit_replication":"https://pith.science/pith/4ZB3UEOYTJCHDKWIK6J47ARO6L/action/replication_record"}},"created_at":"2026-08-05T00:46:09.065987+00:00","updated_at":"2026-08-05T00:46:09.065987+00:00"}