{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:STCNMKF73VK7HRMLDDRNEXKQYQ","short_pith_number":"pith:STCNMKF7","schema_version":"1.0","canonical_sha256":"94c4d628bfdd55f3c58b18e2d25d50c4205d0587e8c442b454469fcf725b508d","source":{"kind":"arxiv","id":"2404.02805","version":1},"attestation_state":"computed","paper":{"title":"Efficient Multi-Vector Dense Retrieval Using Bit Vectors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Cosimo Rulli, Franco Maria Nardini, Rossano Venturini","submitted_at":"2024-04-03T15:20:24Z","abstract_excerpt":"Dense retrieval techniques employ pre-trained large language models to build a high-dimensional representation of queries and passages. These representations compute the relevance of a passage w.r.t. to a query using efficient similarity measures. In this line, multi-vector representations show improved effectiveness at the expense of a one-order-of-magnitude increase in memory footprint and query latency by encoding queries and documents on a per-token level. Recently, PLAID has tackled these problems by introducing a centroid-based term representation to reduce the memory impact of multi-vec"},"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":"2404.02805","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-04-03T15:20:24Z","cross_cats_sorted":[],"title_canon_sha256":"c800f0e0eda73e6ebe09118a1a3665f491dea6e83459b5806c0638242a1710c9","abstract_canon_sha256":"9033820db880cb5183393cd474a25d0facc4f343aa360cbbb2bfc391601ad129"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:01.364070Z","signature_b64":"EC5L+yGtu82NqrZ5iFuIxUOtaIaL29Z8jUpI2tQ4RmotcJJhSXo7I2izF2GxhKl1iB4OPl5DWO0ZjMKsSP0ZBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94c4d628bfdd55f3c58b18e2d25d50c4205d0587e8c442b454469fcf725b508d","last_reissued_at":"2026-07-05T08:04:01.363670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:01.363670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Multi-Vector Dense Retrieval Using Bit Vectors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Cosimo Rulli, Franco Maria Nardini, Rossano Venturini","submitted_at":"2024-04-03T15:20:24Z","abstract_excerpt":"Dense retrieval techniques employ pre-trained large language models to build a high-dimensional representation of queries and passages. These representations compute the relevance of a passage w.r.t. to a query using efficient similarity measures. In this line, multi-vector representations show improved effectiveness at the expense of a one-order-of-magnitude increase in memory footprint and query latency by encoding queries and documents on a per-token level. Recently, PLAID has tackled these problems by introducing a centroid-based term representation to reduce the memory impact of multi-vec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02805","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/2404.02805/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":"2404.02805","created_at":"2026-07-05T08:04:01.363725+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.02805v1","created_at":"2026-07-05T08:04:01.363725+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02805","created_at":"2026-07-05T08:04:01.363725+00:00"},{"alias_kind":"pith_short_12","alias_value":"STCNMKF73VK7","created_at":"2026-07-05T08:04:01.363725+00:00"},{"alias_kind":"pith_short_16","alias_value":"STCNMKF73VK7HRML","created_at":"2026-07-05T08:04:01.363725+00:00"},{"alias_kind":"pith_short_8","alias_value":"STCNMKF7","created_at":"2026-07-05T08:04:01.363725+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23475","citing_title":"Multi-Vector Embeddings are Provably More Expressive than Single Vector Embeddings","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/STCNMKF73VK7HRMLDDRNEXKQYQ","json":"https://pith.science/pith/STCNMKF73VK7HRMLDDRNEXKQYQ.json","graph_json":"https://pith.science/api/pith-number/STCNMKF73VK7HRMLDDRNEXKQYQ/graph.json","events_json":"https://pith.science/api/pith-number/STCNMKF73VK7HRMLDDRNEXKQYQ/events.json","paper":"https://pith.science/paper/STCNMKF7"},"agent_actions":{"view_html":"https://pith.science/pith/STCNMKF73VK7HRMLDDRNEXKQYQ","download_json":"https://pith.science/pith/STCNMKF73VK7HRMLDDRNEXKQYQ.json","view_paper":"https://pith.science/paper/STCNMKF7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.02805&json=true","fetch_graph":"https://pith.science/api/pith-number/STCNMKF73VK7HRMLDDRNEXKQYQ/graph.json","fetch_events":"https://pith.science/api/pith-number/STCNMKF73VK7HRMLDDRNEXKQYQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/STCNMKF73VK7HRMLDDRNEXKQYQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/STCNMKF73VK7HRMLDDRNEXKQYQ/action/storage_attestation","attest_author":"https://pith.science/pith/STCNMKF73VK7HRMLDDRNEXKQYQ/action/author_attestation","sign_citation":"https://pith.science/pith/STCNMKF73VK7HRMLDDRNEXKQYQ/action/citation_signature","submit_replication":"https://pith.science/pith/STCNMKF73VK7HRMLDDRNEXKQYQ/action/replication_record"}},"created_at":"2026-07-05T08:04:01.363725+00:00","updated_at":"2026-07-05T08:04:01.363725+00:00"}