{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FZVZXAHQTDKLPYVPUFPUXNG6IA","short_pith_number":"pith:FZVZXAHQ","schema_version":"1.0","canonical_sha256":"2e6b9b80f098d4b7e2afa15f4bb4de402ac4b454ebc0c24959978453402c9783","source":{"kind":"arxiv","id":"2505.11471","version":1},"attestation_state":"computed","paper":{"title":"CRISP: Clustering Multi-Vector Representations for Denoising and Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Daniel Cer, Gustavo Hern\\'andez \\'Abrego, Jinmeng Rao, Jo\\~ao Veneroso, Majid Hadian, Rajesh Jayaram","submitted_at":"2025-05-16T17:26:16Z","abstract_excerpt":"Multi-vector models, such as ColBERT, are a significant advancement in neural information retrieval (IR), delivering state-of-the-art performance by representing queries and documents by multiple contextualized token-level embeddings. However, this increased representation size introduces considerable storage and computational overheads which have hindered widespread adoption in practice. A common approach to mitigate this overhead is to cluster the model's frozen vectors, but this strategy's effectiveness is fundamentally limited by the intrinsic clusterability of these embeddings. In this wo"},"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":"2505.11471","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-16T17:26:16Z","cross_cats_sorted":[],"title_canon_sha256":"95e4c24d9a41b43a9120217dcefab7a1bf8f1347494600044aa0238a2fb05bd8","abstract_canon_sha256":"defb8e2a517dbc6b7ffedead18728a43507f15a5fd86005d868e27eb3a112c19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:16.826827Z","signature_b64":"irVmhVVIMAsNeLOgmsjL142clXVGV2i7DiH16zdHAXLu/+jDTl4eSPz443vlrEUwxmZzD2ereCwaoWwzE6qeCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e6b9b80f098d4b7e2afa15f4bb4de402ac4b454ebc0c24959978453402c9783","last_reissued_at":"2026-07-05T11:04:16.826348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:16.826348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CRISP: Clustering Multi-Vector Representations for Denoising and Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Daniel Cer, Gustavo Hern\\'andez \\'Abrego, Jinmeng Rao, Jo\\~ao Veneroso, Majid Hadian, Rajesh Jayaram","submitted_at":"2025-05-16T17:26:16Z","abstract_excerpt":"Multi-vector models, such as ColBERT, are a significant advancement in neural information retrieval (IR), delivering state-of-the-art performance by representing queries and documents by multiple contextualized token-level embeddings. However, this increased representation size introduces considerable storage and computational overheads which have hindered widespread adoption in practice. A common approach to mitigate this overhead is to cluster the model's frozen vectors, but this strategy's effectiveness is fundamentally limited by the intrinsic clusterability of these embeddings. In this wo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11471","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/2505.11471/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":"2505.11471","created_at":"2026-07-05T11:04:16.826412+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11471v1","created_at":"2026-07-05T11:04:16.826412+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11471","created_at":"2026-07-05T11:04:16.826412+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZVZXAHQTDKL","created_at":"2026-07-05T11:04:16.826412+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZVZXAHQTDKLPYVP","created_at":"2026-07-05T11:04:16.826412+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZVZXAHQ","created_at":"2026-07-05T11:04:16.826412+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.05803","citing_title":"Quantifying and Expanding the Theoretical Capacity of Late-Interaction Retrieval Models","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2607.06036","citing_title":"Learn to Pool: Lightweight Fine-Tuning for Flexible Multi-Vector Compression","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2601.21853","citing_title":"LEMUR: Learned Multi-Vector Retrieval","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2603.09933","citing_title":"A Voronoi Cell Formulation for Principled Token Pruning in Late-Interaction Retrieval Models","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10167","citing_title":"Visual Late Chunking: An Empirical Study of Contextual Chunking for Efficient Visual Document Retrieval","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FZVZXAHQTDKLPYVPUFPUXNG6IA","json":"https://pith.science/pith/FZVZXAHQTDKLPYVPUFPUXNG6IA.json","graph_json":"https://pith.science/api/pith-number/FZVZXAHQTDKLPYVPUFPUXNG6IA/graph.json","events_json":"https://pith.science/api/pith-number/FZVZXAHQTDKLPYVPUFPUXNG6IA/events.json","paper":"https://pith.science/paper/FZVZXAHQ"},"agent_actions":{"view_html":"https://pith.science/pith/FZVZXAHQTDKLPYVPUFPUXNG6IA","download_json":"https://pith.science/pith/FZVZXAHQTDKLPYVPUFPUXNG6IA.json","view_paper":"https://pith.science/paper/FZVZXAHQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11471&json=true","fetch_graph":"https://pith.science/api/pith-number/FZVZXAHQTDKLPYVPUFPUXNG6IA/graph.json","fetch_events":"https://pith.science/api/pith-number/FZVZXAHQTDKLPYVPUFPUXNG6IA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZVZXAHQTDKLPYVPUFPUXNG6IA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZVZXAHQTDKLPYVPUFPUXNG6IA/action/storage_attestation","attest_author":"https://pith.science/pith/FZVZXAHQTDKLPYVPUFPUXNG6IA/action/author_attestation","sign_citation":"https://pith.science/pith/FZVZXAHQTDKLPYVPUFPUXNG6IA/action/citation_signature","submit_replication":"https://pith.science/pith/FZVZXAHQTDKLPYVPUFPUXNG6IA/action/replication_record"}},"created_at":"2026-07-05T11:04:16.826412+00:00","updated_at":"2026-07-05T11:04:16.826412+00:00"}