{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HICDTAHDP3REHPO5ITOZISDICJ","short_pith_number":"pith:HICDTAHD","schema_version":"1.0","canonical_sha256":"3a043980e37ee243bddd44dd94486812451eff8086e2a359b721078fce1e7a5a","source":{"kind":"arxiv","id":"2505.19189","version":2},"attestation_state":"computed","paper":{"title":"POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.IR","authors_text":"Junlin Li, YaoYang Liu, Yinjun Wu, Zhen Chen","submitted_at":"2025-05-25T15:31:52Z","abstract_excerpt":"Although Multi-Vector Retrieval (MVR) has achieved the state of the art on many information retrieval (IR) tasks, its performance highly depends on how to decompose queries into smaller pieces, say phrases or tokens. However, optimizing query decomposition for MVR performance is not end-to-end differentiable. Even worse, jointly solving this problem and training the downstream retrieval-based systems, say RAG systems could be highly inefficient. To overcome these challenges, we propose Performance-Oriented Query Decomposer (POQD), a novel query decomposition framework for MVR. POQD leverages o"},"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":"2505.19189","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-25T15:31:52Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"78e740b7e2bc016a2a19eef382190432ad80dd04f8e0656fa77d18e54efd1899","abstract_canon_sha256":"3ab90b23dfce9e1e9b3f98cd5ca6f0c560b2729a8ae70d304771ad884946fba9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:26.814369Z","signature_b64":"EQQ/bukP5nQR3nX00GyUOhdM8FuEc08IkKuD12G8gTvAgSBYwBMoRnK9KHaYb0mxWadsCDf03/LOOWTkeh04Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a043980e37ee243bddd44dd94486812451eff8086e2a359b721078fce1e7a5a","last_reissued_at":"2026-07-05T11:13:26.813882Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:26.813882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.IR","authors_text":"Junlin Li, YaoYang Liu, Yinjun Wu, Zhen Chen","submitted_at":"2025-05-25T15:31:52Z","abstract_excerpt":"Although Multi-Vector Retrieval (MVR) has achieved the state of the art on many information retrieval (IR) tasks, its performance highly depends on how to decompose queries into smaller pieces, say phrases or tokens. However, optimizing query decomposition for MVR performance is not end-to-end differentiable. Even worse, jointly solving this problem and training the downstream retrieval-based systems, say RAG systems could be highly inefficient. To overcome these challenges, we propose Performance-Oriented Query Decomposer (POQD), a novel query decomposition framework for MVR. POQD leverages o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19189","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/2505.19189/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":"2505.19189","created_at":"2026-07-05T11:13:26.813939+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19189v2","created_at":"2026-07-05T11:13:26.813939+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19189","created_at":"2026-07-05T11:13:26.813939+00:00"},{"alias_kind":"pith_short_12","alias_value":"HICDTAHDP3RE","created_at":"2026-07-05T11:13:26.813939+00:00"},{"alias_kind":"pith_short_16","alias_value":"HICDTAHDP3REHPO5","created_at":"2026-07-05T11:13:26.813939+00:00"},{"alias_kind":"pith_short_8","alias_value":"HICDTAHD","created_at":"2026-07-05T11:13:26.813939+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10389","citing_title":"BLUEmed: Retrieval-Augmented Multi-Agent Debate for Clinical Error Detection","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HICDTAHDP3REHPO5ITOZISDICJ","json":"https://pith.science/pith/HICDTAHDP3REHPO5ITOZISDICJ.json","graph_json":"https://pith.science/api/pith-number/HICDTAHDP3REHPO5ITOZISDICJ/graph.json","events_json":"https://pith.science/api/pith-number/HICDTAHDP3REHPO5ITOZISDICJ/events.json","paper":"https://pith.science/paper/HICDTAHD"},"agent_actions":{"view_html":"https://pith.science/pith/HICDTAHDP3REHPO5ITOZISDICJ","download_json":"https://pith.science/pith/HICDTAHDP3REHPO5ITOZISDICJ.json","view_paper":"https://pith.science/paper/HICDTAHD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19189&json=true","fetch_graph":"https://pith.science/api/pith-number/HICDTAHDP3REHPO5ITOZISDICJ/graph.json","fetch_events":"https://pith.science/api/pith-number/HICDTAHDP3REHPO5ITOZISDICJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HICDTAHDP3REHPO5ITOZISDICJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HICDTAHDP3REHPO5ITOZISDICJ/action/storage_attestation","attest_author":"https://pith.science/pith/HICDTAHDP3REHPO5ITOZISDICJ/action/author_attestation","sign_citation":"https://pith.science/pith/HICDTAHDP3REHPO5ITOZISDICJ/action/citation_signature","submit_replication":"https://pith.science/pith/HICDTAHDP3REHPO5ITOZISDICJ/action/replication_record"}},"created_at":"2026-07-05T11:13:26.813939+00:00","updated_at":"2026-07-05T11:13:26.813939+00:00"}