{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JT77CAYKH3OLFHGYQ24WA5OJCF","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":"f8610a5af4ff2ea01717dc5b0c3ff4ff8e9a0aafa0da5b022e0f8d631923c3cb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-15T14:37:18Z","title_canon_sha256":"78bca298d79182165e73061ecf3f8d5e3449c4ba09a71f0dd81ec1f117cfcbfa"},"schema_version":"1.0","source":{"id":"2605.16007","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16007","created_at":"2026-05-20T00:01:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16007v1","created_at":"2026-05-20T00:01:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16007","created_at":"2026-05-20T00:01:48Z"},{"alias_kind":"pith_short_12","alias_value":"JT77CAYKH3OL","created_at":"2026-05-20T00:01:48Z"},{"alias_kind":"pith_short_16","alias_value":"JT77CAYKH3OLFHGY","created_at":"2026-05-20T00:01:48Z"},{"alias_kind":"pith_short_8","alias_value":"JT77CAYK","created_at":"2026-05-20T00:01:48Z"}],"graph_snapshots":[{"event_id":"sha256:6b470b01ce3fcdb33fe47e2c497d7938c3ef0477aec6fa2b2fc2f054be719f6e","target":"graph","created_at":"2026-05-20T00:01:48Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Ascend-RaBitQ achieves 3.0* to 62.8* faster index construction than the CPU baseline, up to 4.6* throughput improvement over the fastest CPU IVF-RaBitQ implementation, and over 100* over the mathematically equivalent CPU baseline, while demonstrating encouraging scalability on distributed multi-NPU systems."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that the three-stage heterogeneous pipeline (NPU coarse ranking on 1-bit vectors, on-device AI CPU Top-k, host CPU fine re-ranking) preserves accuracy without post-hoc adjustments while the four NPU-native optimizations (fused AIC-AIV operators, computation restructuring, block-level load balancing, intra-NPU pipeline) deliver the reported speedups on real hardware."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Ascend-RaBitQ is the first heterogeneous NPU-CPU optimized IVF-RaBitQ system for billion-scale vector search that decouples coarse ranking on NPU from fine ranking on CPU to leverage optimal hardware per stage."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Decoupling NPU coarse ranking on 1-bit vectors from CPU fine re-ranking accelerates billion-scale vector similarity search by up to 100 times."}],"snapshot_sha256":"b6bcd0503e28f950b85d9b7a4141b775a59bc2073a36e519615cfecd6fb46fdb"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T22:31:19.639528Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T22:21:49.698988Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:42.169688Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T17:01:55.650407Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.16007/integrity.json","findings":[],"snapshot_sha256":"dd7a0c392cf7e15bec0243e2e26d2d97bc438ee91630c855bd2aaba70a1826fb","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vector similarity search is a critical component of modern AI systems, but traditional CPU-based implementations face fundamental scalability bottlenecks for billion-scale corpora due to prohibitive computational overhead and memory bandwidth limitations. While Neural Processing Units (NPUs) offer orders-of-magnitude higher compute density, existing CPU/GPU-optimized 1-bit RaBitQ quantization implementations cannot be directly ported to NPU architectures due to fundamental hardware mismatches, and homogeneous design paradigms struggle to simultaneously balance accuracy, memory footprint, and p","authors_text":"Baolong Cui, Chao Zhan, Chuyue Ye, Fujun He, Hao Yi, Huaxiang Cai, Jie Xiang, Pengfei Zheng, Wenru Yan, Xiabing Li, Yuhang Gai, Yunfei Du, Zetao Lv, Zigang Zhang, Ziyang Zhang","cross_cats":[],"headline":"Decoupling NPU coarse ranking on 1-bit vectors from CPU fine re-ranking accelerates billion-scale vector similarity search by up to 100 times.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-15T14:37:18Z","title":"Ascend-RaBitQ: Heterogeneous NPU-CPU Acceleration of Billion-Scale Similarity Search with 1-bit Quantization"},"references":{"count":49,"internal_anchors":1,"resolved_work":49,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Philip Adams, Menghao Li, Shi Zhang, Li Tan, Qi Chen, Mingqin Li, Zengzhong Li, Knut Risvik, and Harsha Vardhan Simhadri. 2025. Distributedann: Efficient scaling of a single diskann graph across thous","work_id":"01324ea7-dad2-4eae-852f-6d5befeec0fd","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Fabien André, Anne-Marie Kermarrec, and Nicolas Le Scouarnec. 2016. Cache locality is not enough: High-performance nearest neighbor search with product quantization fast scan. In42nd International Con","work_id":"6e0ab3b1-c24e-4284-959d-5c6b30f23f11","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Fabien André, Anne-Marie Kermarrec, and Nicolas Le Scouarnec. 2017. Acceler- ated nearest neighbor search with quick adc. InProceedings of the 2017 ACM on International Conference on Multimedia Retrie","work_id":"222fb1af-85e4-4038-909a-1b8e5f0e7a2e","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Artem Babenko and Victor Lempitsky. 2014. The inverted multi-index.IEEE transactions on pattern analysis and machine intelligence37, 6 (2014), 1247–1260","work_id":"7d34e2a5-27d5-4d1e-a6ae-8de3c72269b7","year":2014},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Oren Barkan and Noam Koenigstein. 2016. Item2vec: neural item embedding for collaborative filtering. In2016 IEEE 26th international workshop on machine learning for signal processing (MLSP). IEEE, 1–6","work_id":"b0f01f13-a02a-42a8-91ff-e85f526dfcfd","year":2016}],"snapshot_sha256":"33142013c7909c66f7a7da786cd3160a7c80e9aa004d15f4049d87bb394210df"},"source":{"id":"2605.16007","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T22:07:24.045111Z","id":"eb4be89f-042f-4f10-977c-c3982b507bc3","model_set":{"reader":"grok-4.3"},"one_line_summary":"Ascend-RaBitQ is the first heterogeneous NPU-CPU optimized IVF-RaBitQ system for billion-scale vector search that decouples coarse ranking on NPU from fine ranking on CPU to leverage optimal hardware per stage.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Decoupling NPU coarse ranking on 1-bit vectors from CPU fine re-ranking accelerates billion-scale vector similarity search by up to 100 times.","strongest_claim":"Ascend-RaBitQ achieves 3.0* to 62.8* faster index construction than the CPU baseline, up to 4.6* throughput improvement over the fastest CPU IVF-RaBitQ implementation, and over 100* over the mathematically equivalent CPU baseline, while demonstrating encouraging scalability on distributed multi-NPU systems.","weakest_assumption":"The assumption that the three-stage heterogeneous pipeline (NPU coarse ranking on 1-bit vectors, on-device AI CPU Top-k, host CPU fine re-ranking) preserves accuracy without post-hoc adjustments while the four NPU-native optimizations (fused AIC-AIV operators, computation restructuring, block-level load balancing, intra-NPU pipeline) deliver the reported speedups on real hardware."}},"verdict_id":"eb4be89f-042f-4f10-977c-c3982b507bc3"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4d2dc72bc0fa4acd1152c15ab9bd2bb94c644854ef713e8aeef1f5179e20da58","target":"record","created_at":"2026-05-20T00:01:48Z","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":"f8610a5af4ff2ea01717dc5b0c3ff4ff8e9a0aafa0da5b022e0f8d631923c3cb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-15T14:37:18Z","title_canon_sha256":"78bca298d79182165e73061ecf3f8d5e3449c4ba09a71f0dd81ec1f117cfcbfa"},"schema_version":"1.0","source":{"id":"2605.16007","kind":"arxiv","version":1}},"canonical_sha256":"4cfff1030a3edcb29cd886b96075c91154c57a01ef77386810c207b6ee934582","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4cfff1030a3edcb29cd886b96075c91154c57a01ef77386810c207b6ee934582","first_computed_at":"2026-05-20T00:01:48.745612Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:48.745612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vL1fCT3DDJY9bcuqJGxfLQNYl2WTQJwiIjYMH4ujhrc4v4JDxS6V4GUFuyf0efMbM1mMEEW7VVd9y+eVbTBEAQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:48.746509Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16007","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4d2dc72bc0fa4acd1152c15ab9bd2bb94c644854ef713e8aeef1f5179e20da58","sha256:6b470b01ce3fcdb33fe47e2c497d7938c3ef0477aec6fa2b2fc2f054be719f6e"],"state_sha256":"345f81a1527b8ce2478bc0d7de0061a42d6680bcb3952467e83aa238b3ebda4a"}