{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:FIBBUVMMVJDFVVB27EY3PQ7KMY","short_pith_number":"pith:FIBBUVMM","schema_version":"1.0","canonical_sha256":"2a021a558caa465ad43af931b7c3ea6618ba9f573d030a26a806dbcdeed0b93e","source":{"kind":"arxiv","id":"1409.3867","version":1},"attestation_state":"computed","paper":{"title":"Nearest Keyword Set Search in Multi-dimensional Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.DB","authors_text":"Ambuj K. Singh, Vishwakarma Singh","submitted_at":"2014-09-12T21:12:16Z","abstract_excerpt":"Keyword-based search in text-rich multi-dimensional datasets facilitates many novel applications and tools. In this paper, we consider objects that are tagged with keywords and are embedded in a vector space. For these datasets, we study queries that ask for the tightest groups of points satisfying a given set of keywords. We propose a novel method called ProMiSH (Projection and Multi Scale Hashing) that uses random projection and hash-based index structures, and achieves high scalability and speedup. We present an exact and an approximate version of the algorithm. Our empirical studies, both "},"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":"1409.3867","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2014-09-12T21:12:16Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"44148ac396e7c4a240a2d435d24c8b08fafd823d087dbc56d7a402901e641e96","abstract_canon_sha256":"c8c0605584ffd56c19d5d1787e377c79ba6b060a8fdfa58b1a8de43cde066097"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:42:53.470061Z","signature_b64":"kr0kVy0bv8p3gbhKdtiUBJ9/3pu79o3rIL3fyfkAtUDZmK8YHrtQGFE4Tw80khdmwhP1yNSGm9pp5XkJCbvNAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a021a558caa465ad43af931b7c3ea6618ba9f573d030a26a806dbcdeed0b93e","last_reissued_at":"2026-05-18T02:42:53.469688Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:42:53.469688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nearest Keyword Set Search in Multi-dimensional Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.DB","authors_text":"Ambuj K. Singh, Vishwakarma Singh","submitted_at":"2014-09-12T21:12:16Z","abstract_excerpt":"Keyword-based search in text-rich multi-dimensional datasets facilitates many novel applications and tools. In this paper, we consider objects that are tagged with keywords and are embedded in a vector space. For these datasets, we study queries that ask for the tightest groups of points satisfying a given set of keywords. We propose a novel method called ProMiSH (Projection and Multi Scale Hashing) that uses random projection and hash-based index structures, and achieves high scalability and speedup. We present an exact and an approximate version of the algorithm. Our empirical studies, both "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1409.3867","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":"1409.3867","created_at":"2026-05-18T02:42:53.469752+00:00"},{"alias_kind":"arxiv_version","alias_value":"1409.3867v1","created_at":"2026-05-18T02:42:53.469752+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1409.3867","created_at":"2026-05-18T02:42:53.469752+00:00"},{"alias_kind":"pith_short_12","alias_value":"FIBBUVMMVJDF","created_at":"2026-05-18T12:28:28.263976+00:00"},{"alias_kind":"pith_short_16","alias_value":"FIBBUVMMVJDFVVB2","created_at":"2026-05-18T12:28:28.263976+00:00"},{"alias_kind":"pith_short_8","alias_value":"FIBBUVMM","created_at":"2026-05-18T12:28:28.263976+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FIBBUVMMVJDFVVB27EY3PQ7KMY","json":"https://pith.science/pith/FIBBUVMMVJDFVVB27EY3PQ7KMY.json","graph_json":"https://pith.science/api/pith-number/FIBBUVMMVJDFVVB27EY3PQ7KMY/graph.json","events_json":"https://pith.science/api/pith-number/FIBBUVMMVJDFVVB27EY3PQ7KMY/events.json","paper":"https://pith.science/paper/FIBBUVMM"},"agent_actions":{"view_html":"https://pith.science/pith/FIBBUVMMVJDFVVB27EY3PQ7KMY","download_json":"https://pith.science/pith/FIBBUVMMVJDFVVB27EY3PQ7KMY.json","view_paper":"https://pith.science/paper/FIBBUVMM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1409.3867&json=true","fetch_graph":"https://pith.science/api/pith-number/FIBBUVMMVJDFVVB27EY3PQ7KMY/graph.json","fetch_events":"https://pith.science/api/pith-number/FIBBUVMMVJDFVVB27EY3PQ7KMY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FIBBUVMMVJDFVVB27EY3PQ7KMY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FIBBUVMMVJDFVVB27EY3PQ7KMY/action/storage_attestation","attest_author":"https://pith.science/pith/FIBBUVMMVJDFVVB27EY3PQ7KMY/action/author_attestation","sign_citation":"https://pith.science/pith/FIBBUVMMVJDFVVB27EY3PQ7KMY/action/citation_signature","submit_replication":"https://pith.science/pith/FIBBUVMMVJDFVVB27EY3PQ7KMY/action/replication_record"}},"created_at":"2026-05-18T02:42:53.469752+00:00","updated_at":"2026-05-18T02:42:53.469752+00:00"}