{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4ZB3UEOYTJCHDKWIK6J47ARO6L","short_pith_number":"pith:4ZB3UEOY","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"},"canonical_sha256":"e643ba11d89a4471aac85793cf822ef2da8e5236cca2405f77588dea48db55ee","source":{"kind":"arxiv","id":"2608.03199","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4ZB3UEOYTJCHDKWIK6J47ARO6L","target":"record","payload":{"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"},"canonical_sha256":"e643ba11d89a4471aac85793cf822ef2da8e5236cca2405f77588dea48db55ee","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"},"source_kind":"arxiv","source_id":"2608.03199","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":"2026-08-05T00:46:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NGRVhborIL8erU5VprJBpFOkE7yyLbZXEw4/Qv7yW1qhayVWtzxrLhMltL5yg9Ddckz2KKM92zh7YOS8UeXVDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T14:29:43.873827Z"},"content_sha256":"3d1119cb41f51f70c7ceafbb72c4ed8c706821657a20db27f6cbbefa1bb610fc","schema_version":"1.0","event_id":"sha256:3d1119cb41f51f70c7ceafbb72c4ed8c706821657a20db27f6cbbefa1bb610fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4ZB3UEOYTJCHDKWIK6J47ARO6L","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-05T00:46:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vInySyR52j0MLB/gl2mErSiCWlCtjz67qKE2Rzwi1OUlCAjSKYWgv1aYfDQQU7zAhE7lcW5+Z7iDoUrtLSijBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T14:29:43.874725Z"},"content_sha256":"ee5e0e65bf5245b66d2902e74f0002b5d0c2a4d58b038769a6ff712cf46b89ff","schema_version":"1.0","event_id":"sha256:ee5e0e65bf5245b66d2902e74f0002b5d0c2a4d58b038769a6ff712cf46b89ff"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:4ZB3UEOYTJCHDKWIK6J47ARO6L","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1109/CVPR.2016.226) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Artem Babenko Yandex and Victor Lempitsky. 2016. Efficient Indexing of Billion- Scale Datasets of Deep Descriptors. In2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2055–2063. https://doi.org/10.1109/CVPR.2016. 226","arxiv_id":"2608.03199","detector":"doi_compliance","evidence":{"ref_index":24,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.1109/cvpr.2016","reconstructed_doi":"10.1109/CVPR.2016.226"},"severity":"advisory","ref_index":24,"audited_at":"2026-08-05T23:58:22.311940Z","event_type":"pith.integrity.v1","detected_doi":"10.1109/CVPR.2016.226","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"0041fa083e8bbb99d2e0d701b99aab466f657e5bdd2c4aed2ae0348a91c711e4","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":18167,"payload_sha256":"2c3a30834317d52247e2ddd0829c9cb58b3a5a7d4c3b9c0073a19085126fdcc3","signature_b64":"1REh7NZbn/tEE4NVEMHLx7iFKfxh3TF6/U3DSZyENr85ThXTHfsbqRZejazLYjEh+Na0ndA1tIrNRxdp16+ACg==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-05T23:58:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jHesKtDdzG8OmfDKOwHX3Cg2JE/nXYZELVHw/sAg98xWOsCyOQoGtLhtxUSsKeqS2/LXoC+wgf6nFoRFvBuMCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T14:29:43.879381Z"},"content_sha256":"98199f0897885071a6b400a3d1e44a1d6813026830db5c31948d7f287e1e2abb","schema_version":"1.0","event_id":"sha256:98199f0897885071a6b400a3d1e44a1d6813026830db5c31948d7f287e1e2abb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4ZB3UEOYTJCHDKWIK6J47ARO6L/bundle.json","state_url":"https://pith.science/pith/4ZB3UEOYTJCHDKWIK6J47ARO6L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4ZB3UEOYTJCHDKWIK6J47ARO6L/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":"2026-08-14T14:29:43Z","links":{"resolver":"https://pith.science/pith/4ZB3UEOYTJCHDKWIK6J47ARO6L","bundle":"https://pith.science/pith/4ZB3UEOYTJCHDKWIK6J47ARO6L/bundle.json","state":"https://pith.science/pith/4ZB3UEOYTJCHDKWIK6J47ARO6L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4ZB3UEOYTJCHDKWIK6J47ARO6L/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kmARAwmJhpoMFCyVHupMLsucyQwAUlxKWmnaTjRI1SGpL1EKd3Zc1NMWkHZ7FAE7VXM8BDCnMINTR3FZRMZwDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T14:29:43.883214Z","bundle_sha256":"fce3aafef355be7bc54a70e3bb15f26a030794eb822743ded9d95a11714e7370"}}