{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WH5RFSJXDDC5TRGEYI7ZQQ6XKP","short_pith_number":"pith:WH5RFSJX","canonical_record":{"source":{"id":"2405.03267","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-05-06T08:38:14Z","cross_cats_sorted":["cs.DB","cs.IR"],"title_canon_sha256":"1f8d46dad47f5bc2e3ae03eed1633f3d53714370f41837a6047e018a2106980f","abstract_canon_sha256":"98faef1f98ef9f06e46b3c37e4246b4bd84990fe63fbdd375e01906d6b817dda"},"schema_version":"1.0"},"canonical_sha256":"b1fb12c93718c5d9c4c4c23f9843d753c08bcd561b70112d439a77980ccc5589","source":{"kind":"arxiv","id":"2405.03267","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.03267","created_at":"2026-07-05T08:16:29Z"},{"alias_kind":"arxiv_version","alias_value":"2405.03267v2","created_at":"2026-07-05T08:16:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03267","created_at":"2026-07-05T08:16:29Z"},{"alias_kind":"pith_short_12","alias_value":"WH5RFSJXDDC5","created_at":"2026-07-05T08:16:29Z"},{"alias_kind":"pith_short_16","alias_value":"WH5RFSJXDDC5TRGE","created_at":"2026-07-05T08:16:29Z"},{"alias_kind":"pith_short_8","alias_value":"WH5RFSJX","created_at":"2026-07-05T08:16:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WH5RFSJXDDC5TRGEYI7ZQQ6XKP","target":"record","payload":{"canonical_record":{"source":{"id":"2405.03267","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-05-06T08:38:14Z","cross_cats_sorted":["cs.DB","cs.IR"],"title_canon_sha256":"1f8d46dad47f5bc2e3ae03eed1633f3d53714370f41837a6047e018a2106980f","abstract_canon_sha256":"98faef1f98ef9f06e46b3c37e4246b4bd84990fe63fbdd375e01906d6b817dda"},"schema_version":"1.0"},"canonical_sha256":"b1fb12c93718c5d9c4c4c23f9843d753c08bcd561b70112d439a77980ccc5589","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:29.037930Z","signature_b64":"NVZcaZLE40e/zkuKz3Pl/92O8qT3p3LOv47g1CG2pXcKymXhb+U8lvOKmKfrt10HF5/zIAED384Q2FU4OdymBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1fb12c93718c5d9c4c4c23f9843d753c08bcd561b70112d439a77980ccc5589","last_reissued_at":"2026-07-05T08:16:29.037427Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:29.037427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.03267","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:16:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wdqpieHlsu0GuBqjq9GeSh3gzvhYlX+w7obxMAuCy5aW/XRxlgJlEOu3eapHeusCVsiEM04r0N4/XOFaGIypBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:32:02.514266Z"},"content_sha256":"f6e513dcb6638992ab8fea7e18a7141e0cf78f8839359a7b822f8ebe715c472b","schema_version":"1.0","event_id":"sha256:f6e513dcb6638992ab8fea7e18a7141e0cf78f8839359a7b822f8ebe715c472b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WH5RFSJXDDC5TRGEYI7ZQQ6XKP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Characterizing the Dilemma of Performance and Index Size in Billion-Scale Vector Search and Breaking It with Second-Tier Memory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB","cs.IR"],"primary_cat":"cs.DC","authors_text":"Haibo Chen, Hongrui Xie, Rong chen, Rongxin Cheng, Sijie Shen, Xingda Wei, Yifan Peng","submitted_at":"2024-05-06T08:38:14Z","abstract_excerpt":"Vector searches on large-scale datasets are critical to modern online services like web search and RAG, which necessity storing the datasets and their index on the secondary storage like SSD. In this paper, we are the first to characterize the trade-off of performance and index size in existing SSD-based graph and cluster indexes: to improve throughput by 5.7$\\times$ and 1.7$\\times$, these indexes have to pay a 5.8$\\times$ storage amplification and 7.7$\\times$ with respect to the dataset size, respectively. The root cause is that the coarse-grained access of SSD mismatches the fine-grained ran"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03267","kind":"arxiv","version":2},"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/2405.03267/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":"2026-07-05T08:16:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tbd/2NwmGiFqbe3Yv0kMnaJFnx7aabRzRMbFGBWEKuQRZGbhJw1hJc+Ps0Px4rBlOpuuU58lfNGjFGQhZJFiDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:32:02.515233Z"},"content_sha256":"a6d02a26f3e75e5306de9925841a7d245381e73e057649161ad93bf06bfb423e","schema_version":"1.0","event_id":"sha256:a6d02a26f3e75e5306de9925841a7d245381e73e057649161ad93bf06bfb423e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WH5RFSJXDDC5TRGEYI7ZQQ6XKP/bundle.json","state_url":"https://pith.science/pith/WH5RFSJXDDC5TRGEYI7ZQQ6XKP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WH5RFSJXDDC5TRGEYI7ZQQ6XKP/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":"2026-08-10T09:32:02Z","links":{"resolver":"https://pith.science/pith/WH5RFSJXDDC5TRGEYI7ZQQ6XKP","bundle":"https://pith.science/pith/WH5RFSJXDDC5TRGEYI7ZQQ6XKP/bundle.json","state":"https://pith.science/pith/WH5RFSJXDDC5TRGEYI7ZQQ6XKP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WH5RFSJXDDC5TRGEYI7ZQQ6XKP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WH5RFSJXDDC5TRGEYI7ZQQ6XKP","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":"98faef1f98ef9f06e46b3c37e4246b4bd84990fe63fbdd375e01906d6b817dda","cross_cats_sorted":["cs.DB","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-05-06T08:38:14Z","title_canon_sha256":"1f8d46dad47f5bc2e3ae03eed1633f3d53714370f41837a6047e018a2106980f"},"schema_version":"1.0","source":{"id":"2405.03267","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.03267","created_at":"2026-07-05T08:16:29Z"},{"alias_kind":"arxiv_version","alias_value":"2405.03267v2","created_at":"2026-07-05T08:16:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03267","created_at":"2026-07-05T08:16:29Z"},{"alias_kind":"pith_short_12","alias_value":"WH5RFSJXDDC5","created_at":"2026-07-05T08:16:29Z"},{"alias_kind":"pith_short_16","alias_value":"WH5RFSJXDDC5TRGE","created_at":"2026-07-05T08:16:29Z"},{"alias_kind":"pith_short_8","alias_value":"WH5RFSJX","created_at":"2026-07-05T08:16:29Z"}],"graph_snapshots":[{"event_id":"sha256:a6d02a26f3e75e5306de9925841a7d245381e73e057649161ad93bf06bfb423e","target":"graph","created_at":"2026-07-05T08:16:29Z","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/2405.03267/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vector searches on large-scale datasets are critical to modern online services like web search and RAG, which necessity storing the datasets and their index on the secondary storage like SSD. In this paper, we are the first to characterize the trade-off of performance and index size in existing SSD-based graph and cluster indexes: to improve throughput by 5.7$\\times$ and 1.7$\\times$, these indexes have to pay a 5.8$\\times$ storage amplification and 7.7$\\times$ with respect to the dataset size, respectively. The root cause is that the coarse-grained access of SSD mismatches the fine-grained ran","authors_text":"Haibo Chen, Hongrui Xie, Rong chen, Rongxin Cheng, Sijie Shen, Xingda Wei, Yifan Peng","cross_cats":["cs.DB","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-05-06T08:38:14Z","title":"Characterizing the Dilemma of Performance and Index Size in Billion-Scale Vector Search and Breaking It with Second-Tier Memory"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03267","kind":"arxiv","version":2},"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:f6e513dcb6638992ab8fea7e18a7141e0cf78f8839359a7b822f8ebe715c472b","target":"record","created_at":"2026-07-05T08:16:29Z","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":"98faef1f98ef9f06e46b3c37e4246b4bd84990fe63fbdd375e01906d6b817dda","cross_cats_sorted":["cs.DB","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-05-06T08:38:14Z","title_canon_sha256":"1f8d46dad47f5bc2e3ae03eed1633f3d53714370f41837a6047e018a2106980f"},"schema_version":"1.0","source":{"id":"2405.03267","kind":"arxiv","version":2}},"canonical_sha256":"b1fb12c93718c5d9c4c4c23f9843d753c08bcd561b70112d439a77980ccc5589","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1fb12c93718c5d9c4c4c23f9843d753c08bcd561b70112d439a77980ccc5589","first_computed_at":"2026-07-05T08:16:29.037427Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:16:29.037427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NVZcaZLE40e/zkuKz3Pl/92O8qT3p3LOv47g1CG2pXcKymXhb+U8lvOKmKfrt10HF5/zIAED384Q2FU4OdymBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:16:29.037930Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.03267","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6e513dcb6638992ab8fea7e18a7141e0cf78f8839359a7b822f8ebe715c472b","sha256:a6d02a26f3e75e5306de9925841a7d245381e73e057649161ad93bf06bfb423e"],"state_sha256":"02192678feba924a4b39f187fc90edc856c5c7891806e74c3bdac610ea548f4d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/xzXKroARHJqxuen5ZzL7qKRXzLhW8QYKiC7qlhmo6/ubIexfbIENfRn0uYMW3wrbCbgQjmSCRK3X9TGlK2CBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T09:32:02.520034Z","bundle_sha256":"9e6d9e83183f811771581c69ffee306a9094e39ac781d312629d648835a4c7b3"}}