{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3YTX4TE4W5Q4YDIITZMXQ2LXM5","short_pith_number":"pith:3YTX4TE4","schema_version":"1.0","canonical_sha256":"de277e4c9cb761cc0d089e5978697767610a78c1281b24f7a64f7ca93f2d0d37","source":{"kind":"arxiv","id":"2502.13336","version":1},"attestation_state":"computed","paper":{"title":"Graph-Based Algorithms for Diverse Similarity Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Haike Xu, Kirankumar Shiragur, Piotr Indyk, Piyush Anand, Ravishankar Krishnaswamy, Sepideh Mahabadi, Vikas C. Raykar","submitted_at":"2025-02-18T23:31:37Z","abstract_excerpt":"Nearest neighbor search is a fundamental data structure problem with many applications in machine learning, computer vision, recommendation systems and other fields. Although the main objective of the data structure is to quickly report data points that are closest to a given query, it has long been noted (Carbonell and Goldstein, 1998) that without additional constraints the reported answers can be redundant and/or duplicative. This issue is typically addressed in two stages: in the first stage, the algorithm retrieves a (large) number $r$ of points closest to the query, while in the second s"},"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":"2502.13336","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2025-02-18T23:31:37Z","cross_cats_sorted":[],"title_canon_sha256":"f21acc119d2bb983d0a5fc84a3e66a10c8a055535ee9e7cf18093a21416ea16b","abstract_canon_sha256":"65b54b3c080602932c31f5950cfa567e57efca1bd45eadf121801bafc4489e99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:45.585215Z","signature_b64":"Y+WnpLsRW7nna1a8N5C6V+LejQCwPGyPWfC0JI/5CYqsY6AGtNaqzRkcxCTJg0EDbKQeoKpWy7Cpa6UgMUBuBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de277e4c9cb761cc0d089e5978697767610a78c1281b24f7a64f7ca93f2d0d37","last_reissued_at":"2026-07-05T10:16:45.584764Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:45.584764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph-Based Algorithms for Diverse Similarity Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Haike Xu, Kirankumar Shiragur, Piotr Indyk, Piyush Anand, Ravishankar Krishnaswamy, Sepideh Mahabadi, Vikas C. Raykar","submitted_at":"2025-02-18T23:31:37Z","abstract_excerpt":"Nearest neighbor search is a fundamental data structure problem with many applications in machine learning, computer vision, recommendation systems and other fields. Although the main objective of the data structure is to quickly report data points that are closest to a given query, it has long been noted (Carbonell and Goldstein, 1998) that without additional constraints the reported answers can be redundant and/or duplicative. This issue is typically addressed in two stages: in the first stage, the algorithm retrieves a (large) number $r$ of points closest to the query, while in the second s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13336","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/2502.13336/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":"2502.13336","created_at":"2026-07-05T10:16:45.584816+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.13336v1","created_at":"2026-07-05T10:16:45.584816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13336","created_at":"2026-07-05T10:16:45.584816+00:00"},{"alias_kind":"pith_short_12","alias_value":"3YTX4TE4W5Q4","created_at":"2026-07-05T10:16:45.584816+00:00"},{"alias_kind":"pith_short_16","alias_value":"3YTX4TE4W5Q4YDII","created_at":"2026-07-05T10:16:45.584816+00:00"},{"alias_kind":"pith_short_8","alias_value":"3YTX4TE4","created_at":"2026-07-05T10:16:45.584816+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18623","citing_title":"An Approximation Algorithm for Graph Label Selection","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3YTX4TE4W5Q4YDIITZMXQ2LXM5","json":"https://pith.science/pith/3YTX4TE4W5Q4YDIITZMXQ2LXM5.json","graph_json":"https://pith.science/api/pith-number/3YTX4TE4W5Q4YDIITZMXQ2LXM5/graph.json","events_json":"https://pith.science/api/pith-number/3YTX4TE4W5Q4YDIITZMXQ2LXM5/events.json","paper":"https://pith.science/paper/3YTX4TE4"},"agent_actions":{"view_html":"https://pith.science/pith/3YTX4TE4W5Q4YDIITZMXQ2LXM5","download_json":"https://pith.science/pith/3YTX4TE4W5Q4YDIITZMXQ2LXM5.json","view_paper":"https://pith.science/paper/3YTX4TE4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.13336&json=true","fetch_graph":"https://pith.science/api/pith-number/3YTX4TE4W5Q4YDIITZMXQ2LXM5/graph.json","fetch_events":"https://pith.science/api/pith-number/3YTX4TE4W5Q4YDIITZMXQ2LXM5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3YTX4TE4W5Q4YDIITZMXQ2LXM5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3YTX4TE4W5Q4YDIITZMXQ2LXM5/action/storage_attestation","attest_author":"https://pith.science/pith/3YTX4TE4W5Q4YDIITZMXQ2LXM5/action/author_attestation","sign_citation":"https://pith.science/pith/3YTX4TE4W5Q4YDIITZMXQ2LXM5/action/citation_signature","submit_replication":"https://pith.science/pith/3YTX4TE4W5Q4YDIITZMXQ2LXM5/action/replication_record"}},"created_at":"2026-07-05T10:16:45.584816+00:00","updated_at":"2026-07-05T10:16:45.584816+00:00"}