{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:FIBBUVMMVJDFVVB27EY3PQ7KMY","short_pith_number":"pith:FIBBUVMM","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"},"canonical_sha256":"2a021a558caa465ad43af931b7c3ea6618ba9f573d030a26a806dbcdeed0b93e","source":{"kind":"arxiv","id":"1409.3867","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1409.3867","created_at":"2026-05-18T02:42:53Z"},{"alias_kind":"arxiv_version","alias_value":"1409.3867v1","created_at":"2026-05-18T02:42:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1409.3867","created_at":"2026-05-18T02:42:53Z"},{"alias_kind":"pith_short_12","alias_value":"FIBBUVMMVJDF","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"FIBBUVMMVJDFVVB2","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"FIBBUVMM","created_at":"2026-05-18T12:28:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:FIBBUVMMVJDFVVB27EY3PQ7KMY","target":"record","payload":{"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"},"canonical_sha256":"2a021a558caa465ad43af931b7c3ea6618ba9f573d030a26a806dbcdeed0b93e","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"},"source_kind":"arxiv","source_id":"1409.3867","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:42:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rynCy2aPi6nHYh2Pt+Bn+g9BsYwpjRRwQbBHj1vlS44l9tIbB3c1p4DCvon/fM3RkjBsjuGWEPk/tzfRXpOGBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T18:09:51.588389Z"},"content_sha256":"a90821b1d8284bbbbb01e58f91d558827b410426f5905da281f0e4cbd69138bf","schema_version":"1.0","event_id":"sha256:a90821b1d8284bbbbb01e58f91d558827b410426f5905da281f0e4cbd69138bf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:FIBBUVMMVJDFVVB27EY3PQ7KMY","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:42:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yu+GYFL+W9ZC1W/c6lmIcaHDT6KaYLXHv0wLDS9nWactXqxD/Peo/B96S0TzSLRkFn4V4YDi4E2e0F/3I9HmCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T18:09:51.589065Z"},"content_sha256":"c9bafce3495b54fc6a0ee3774cb6888d8e0d04796067c0d2a6432be3ac4f0f33","schema_version":"1.0","event_id":"sha256:c9bafce3495b54fc6a0ee3774cb6888d8e0d04796067c0d2a6432be3ac4f0f33"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FIBBUVMMVJDFVVB27EY3PQ7KMY/bundle.json","state_url":"https://pith.science/pith/FIBBUVMMVJDFVVB27EY3PQ7KMY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FIBBUVMMVJDFVVB27EY3PQ7KMY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-31T18:09:51Z","links":{"resolver":"https://pith.science/pith/FIBBUVMMVJDFVVB27EY3PQ7KMY","bundle":"https://pith.science/pith/FIBBUVMMVJDFVVB27EY3PQ7KMY/bundle.json","state":"https://pith.science/pith/FIBBUVMMVJDFVVB27EY3PQ7KMY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FIBBUVMMVJDFVVB27EY3PQ7KMY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:FIBBUVMMVJDFVVB27EY3PQ7KMY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c8c0605584ffd56c19d5d1787e377c79ba6b060a8fdfa58b1a8de43cde066097","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2014-09-12T21:12:16Z","title_canon_sha256":"44148ac396e7c4a240a2d435d24c8b08fafd823d087dbc56d7a402901e641e96"},"schema_version":"1.0","source":{"id":"1409.3867","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1409.3867","created_at":"2026-05-18T02:42:53Z"},{"alias_kind":"arxiv_version","alias_value":"1409.3867v1","created_at":"2026-05-18T02:42:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1409.3867","created_at":"2026-05-18T02:42:53Z"},{"alias_kind":"pith_short_12","alias_value":"FIBBUVMMVJDF","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"FIBBUVMMVJDFVVB2","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"FIBBUVMM","created_at":"2026-05-18T12:28:28Z"}],"graph_snapshots":[{"event_id":"sha256:c9bafce3495b54fc6a0ee3774cb6888d8e0d04796067c0d2a6432be3ac4f0f33","target":"graph","created_at":"2026-05-18T02:42:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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 ","authors_text":"Ambuj K. Singh, Vishwakarma Singh","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2014-09-12T21:12:16Z","title":"Nearest Keyword Set Search in Multi-dimensional Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1409.3867","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a90821b1d8284bbbbb01e58f91d558827b410426f5905da281f0e4cbd69138bf","target":"record","created_at":"2026-05-18T02:42:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c8c0605584ffd56c19d5d1787e377c79ba6b060a8fdfa58b1a8de43cde066097","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2014-09-12T21:12:16Z","title_canon_sha256":"44148ac396e7c4a240a2d435d24c8b08fafd823d087dbc56d7a402901e641e96"},"schema_version":"1.0","source":{"id":"1409.3867","kind":"arxiv","version":1}},"canonical_sha256":"2a021a558caa465ad43af931b7c3ea6618ba9f573d030a26a806dbcdeed0b93e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a021a558caa465ad43af931b7c3ea6618ba9f573d030a26a806dbcdeed0b93e","first_computed_at":"2026-05-18T02:42:53.469688Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:42:53.469688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kr0kVy0bv8p3gbhKdtiUBJ9/3pu79o3rIL3fyfkAtUDZmK8YHrtQGFE4Tw80khdmwhP1yNSGm9pp5XkJCbvNAA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:42:53.470061Z","signed_message":"canonical_sha256_bytes"},"source_id":"1409.3867","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a90821b1d8284bbbbb01e58f91d558827b410426f5905da281f0e4cbd69138bf","sha256:c9bafce3495b54fc6a0ee3774cb6888d8e0d04796067c0d2a6432be3ac4f0f33"],"state_sha256":"040507de74b2d369c7bff86761e8e5f6e471d7fd91d85b1c15f4552f0e19ca41"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+8vIfE3Olmsodz7m1Xbt8PYUPUE5ptEfPrXaBVZlWN5jFNI4HH7VDEB8lIB092kNRkkVM9fdw+2x1S2T8uoXCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T18:09:51.592893Z","bundle_sha256":"016903d949554164976cf09073ca2b5a302e7e17714b2e83f8c32091695de341"}}