{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:LP4OG43AFEQYC7M5FMNDBMR2KE","short_pith_number":"pith:LP4OG43A","schema_version":"1.0","canonical_sha256":"5bf8e373602921817d9d2b1a30b23a5101911cf93df83a7fe5a31eb187f326a8","source":{"kind":"arxiv","id":"1702.08734","version":1},"attestation_state":"computed","paper":{"title":"Billion-scale similarity search with GPUs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.DS","cs.IR"],"primary_cat":"cs.CV","authors_text":"Herv\\'e J\\'egou, Jeff Johnson, Matthijs Douze","submitted_at":"2017-02-28T10:42:31Z","abstract_excerpt":"Similarity search finds application in specialized database systems handling complex data such as images or videos, which are typically represented by high-dimensional features and require specific indexing structures. This paper tackles the problem of better utilizing GPUs for this task. While GPUs excel at data-parallel tasks, prior approaches are bottlenecked by algorithms that expose less parallelism, such as k-min selection, or make poor use of the memory hierarchy.\n  We propose a design for k-selection that operates at up to 55% of theoretical peak performance, enabling a nearest neighbo"},"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":"1702.08734","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-28T10:42:31Z","cross_cats_sorted":["cs.DB","cs.DS","cs.IR"],"title_canon_sha256":"cf53b217a6dc21ef54640a57cdaa92c8edc0ccedecda61c47f9b55c4d25df8d9","abstract_canon_sha256":"2084f80738fae66a544f2341eed408f5a000bb29f4669b2170753bcdc65be0fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:06.893018Z","signature_b64":"UL7cOocDdJz0iDWLY0ihbLu3u5BTgtQ7wRKtr73jgV1axe7L5dO54AAC/bgi1Q+wUJyu0XWfdR/gUmvcZ8LKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bf8e373602921817d9d2b1a30b23a5101911cf93df83a7fe5a31eb187f326a8","last_reissued_at":"2026-05-18T00:14:06.892518Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:06.892518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Billion-scale similarity search with GPUs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.DS","cs.IR"],"primary_cat":"cs.CV","authors_text":"Herv\\'e J\\'egou, Jeff Johnson, Matthijs Douze","submitted_at":"2017-02-28T10:42:31Z","abstract_excerpt":"Similarity search finds application in specialized database systems handling complex data such as images or videos, which are typically represented by high-dimensional features and require specific indexing structures. This paper tackles the problem of better utilizing GPUs for this task. While GPUs excel at data-parallel tasks, prior approaches are bottlenecked by algorithms that expose less parallelism, such as k-min selection, or make poor use of the memory hierarchy.\n  We propose a design for k-selection that operates at up to 55% of theoretical peak performance, enabling a nearest neighbo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.08734","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":""},"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":"1702.08734","created_at":"2026-05-18T00:14:06.892597+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.08734v1","created_at":"2026-05-18T00:14:06.892597+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.08734","created_at":"2026-05-18T00:14:06.892597+00:00"},{"alias_kind":"pith_short_12","alias_value":"LP4OG43AFEQY","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"LP4OG43AFEQYC7M5","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"LP4OG43A","created_at":"2026-05-18T12:31:28.150371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":36,"internal_anchor_count":25,"sample":[{"citing_arxiv_id":"2605.30295","citing_title":"MedCase-Structured: A Text-to-FHIR Dataset for Benchmarking Diagnostic Reasoning in Clinically Realistic EHR Settings","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2607.02266","citing_title":"HERMES: A Multi-Granularity Labeling Substrate for Pre-training Data Mixtures","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2606.12215","citing_title":"MLT-Dedup: Efficient Large-Scale Online Video Deduplication via Multi-Level Representations and Spatial-Temporal Matching","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2606.08151","citing_title":"Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2606.06566","citing_title":"NTILC: Neural Tool Invocation via Learned Compression","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2606.31272","citing_title":"The Decomposition Is the Fingerprint: Per-Component Identity for Agent Skills","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20608","citing_title":"CourseBlueprint: A Structured Pipeline for Adaptive Pedagogical Video Generation Grounded in Course Corpora","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.24307","citing_title":"Modernizing User Privacy Preference Measurement through GPPI: A GDPR-aligned Privacy Preference Item Bank","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2605.30295","citing_title":"MedCase-Structured: A Text-to-FHIR Dataset for Benchmarking Diagnostic Reasoning in Clinically Realistic EHR Settings","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.30295","citing_title":"MedCase-Structured: A Text-to-FHIR Dataset for Benchmarking Diagnostic Reasoning in Clinically Realistic EHR Settings","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24894","citing_title":"RWGBench: Evaluating Scholarly Positioning in Related Work Generation","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2606.08950","citing_title":"When More Cores Hurts: The Vector Database Scaling Paradox in HPC","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"1906.10095","citing_title":"An Empirical Comparison of FAISS and FENSHSES for Nearest Neighbor Search in Hamming Space","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"1906.10602","citing_title":"Pyramid: A General Framework for Distributed Similarity Search","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"1907.00544","citing_title":"Unsupervised Adversarial Graph Alignment with Graph Embedding","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"1907.07387","citing_title":"The Role of Local Intrinsic Dimensionality in Benchmarking Nearest Neighbor Search","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2502.11336","citing_title":"ExaGPT: Example-Based Machine-Generated Text Detection for Human Interpretability","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2504.09775","citing_title":"MIST: A Co-Design Framework for Heterogeneous, Multi-Stage LLM Inference","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22203","citing_title":"Evaluation of Chunking Strategies for Effective Text Embedding in Low-Resource Language on Agricultural Documents","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17366","citing_title":"Text-Guided Visual Representation Learning for Robust Multimodal E-Commerce Recommendation","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2506.03374","citing_title":"Product Quantization for Surface Soil Similarity","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2406.11794","citing_title":"DataComp-LM: In search of the next generation of training sets for language models","ref_index":92,"is_internal_anchor":true},{"citing_arxiv_id":"2004.04906","citing_title":"Dense Passage Retrieval for Open-Domain Question Answering","ref_index":83,"is_internal_anchor":true},{"citing_arxiv_id":"2401.18059","citing_title":"RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19779","citing_title":"ESGLens: An LLM-Based RAG Framework for Interactive ESG Report Analysis and Score Prediction","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LP4OG43AFEQYC7M5FMNDBMR2KE","json":"https://pith.science/pith/LP4OG43AFEQYC7M5FMNDBMR2KE.json","graph_json":"https://pith.science/api/pith-number/LP4OG43AFEQYC7M5FMNDBMR2KE/graph.json","events_json":"https://pith.science/api/pith-number/LP4OG43AFEQYC7M5FMNDBMR2KE/events.json","paper":"https://pith.science/paper/LP4OG43A"},"agent_actions":{"view_html":"https://pith.science/pith/LP4OG43AFEQYC7M5FMNDBMR2KE","download_json":"https://pith.science/pith/LP4OG43AFEQYC7M5FMNDBMR2KE.json","view_paper":"https://pith.science/paper/LP4OG43A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.08734&json=true","fetch_graph":"https://pith.science/api/pith-number/LP4OG43AFEQYC7M5FMNDBMR2KE/graph.json","fetch_events":"https://pith.science/api/pith-number/LP4OG43AFEQYC7M5FMNDBMR2KE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LP4OG43AFEQYC7M5FMNDBMR2KE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LP4OG43AFEQYC7M5FMNDBMR2KE/action/storage_attestation","attest_author":"https://pith.science/pith/LP4OG43AFEQYC7M5FMNDBMR2KE/action/author_attestation","sign_citation":"https://pith.science/pith/LP4OG43AFEQYC7M5FMNDBMR2KE/action/citation_signature","submit_replication":"https://pith.science/pith/LP4OG43AFEQYC7M5FMNDBMR2KE/action/replication_record"}},"created_at":"2026-05-18T00:14:06.892597+00:00","updated_at":"2026-05-18T00:14:06.892597+00:00"}