{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:QAXJYYUCIHDFEN44HO6XQ554NN","short_pith_number":"pith:QAXJYYUC","schema_version":"1.0","canonical_sha256":"802e9c628241c652379c3bbd7877bc6b7a9947f1364ed3b0ddca4c072ac7bbfa","source":{"kind":"arxiv","id":"1605.06693","version":1},"attestation_state":"computed","paper":{"title":"Efficient Document Indexing Using Pivot Tree","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Benjamin Piwowarski, Gaurav Singh","submitted_at":"2016-05-21T19:55:03Z","abstract_excerpt":"We present a novel method for efficiently searching top-k neighbors for documents represented in high dimensional space of terms based on the cosine similarity. Mostly, documents are stored as bag-of-words tf-idf representation. One of the most used ways of computing similarity between a pair of documents is cosine similarity between the vector representations, but cosine similarity is not a metric distance measure as it doesn't follow triangle inequality, therefore most metric searching methods can not be applied directly. We propose an efficient method for indexing documents using a pivot tr"},"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":"1605.06693","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-05-21T19:55:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fd08cf119df1588ef5e5a531463dac3a7ebcd3b93c9b44b5aa8658cfdcf54026","abstract_canon_sha256":"fdd4284117d326a313b17d51fbed443051b2644d2abdf1a6eab49860b6f5b90c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:14:11.502279Z","signature_b64":"fUKCf2C9j8KDDfLHS5ZjEfctm/V+BJkOGeE5Tkc8sLC4fUwlYfsKICsT5cLXI/hag2E+kNQmbjhaZNLDNH3qAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"802e9c628241c652379c3bbd7877bc6b7a9947f1364ed3b0ddca4c072ac7bbfa","last_reissued_at":"2026-05-18T01:14:11.501550Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:14:11.501550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Document Indexing Using Pivot Tree","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Benjamin Piwowarski, Gaurav Singh","submitted_at":"2016-05-21T19:55:03Z","abstract_excerpt":"We present a novel method for efficiently searching top-k neighbors for documents represented in high dimensional space of terms based on the cosine similarity. Mostly, documents are stored as bag-of-words tf-idf representation. One of the most used ways of computing similarity between a pair of documents is cosine similarity between the vector representations, but cosine similarity is not a metric distance measure as it doesn't follow triangle inequality, therefore most metric searching methods can not be applied directly. We propose an efficient method for indexing documents using a pivot tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.06693","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":"1605.06693","created_at":"2026-05-18T01:14:11.501672+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.06693v1","created_at":"2026-05-18T01:14:11.501672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.06693","created_at":"2026-05-18T01:14:11.501672+00:00"},{"alias_kind":"pith_short_12","alias_value":"QAXJYYUCIHDF","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_16","alias_value":"QAXJYYUCIHDFEN44","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_8","alias_value":"QAXJYYUC","created_at":"2026-05-18T12:30:39.010887+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/QAXJYYUCIHDFEN44HO6XQ554NN","json":"https://pith.science/pith/QAXJYYUCIHDFEN44HO6XQ554NN.json","graph_json":"https://pith.science/api/pith-number/QAXJYYUCIHDFEN44HO6XQ554NN/graph.json","events_json":"https://pith.science/api/pith-number/QAXJYYUCIHDFEN44HO6XQ554NN/events.json","paper":"https://pith.science/paper/QAXJYYUC"},"agent_actions":{"view_html":"https://pith.science/pith/QAXJYYUCIHDFEN44HO6XQ554NN","download_json":"https://pith.science/pith/QAXJYYUCIHDFEN44HO6XQ554NN.json","view_paper":"https://pith.science/paper/QAXJYYUC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.06693&json=true","fetch_graph":"https://pith.science/api/pith-number/QAXJYYUCIHDFEN44HO6XQ554NN/graph.json","fetch_events":"https://pith.science/api/pith-number/QAXJYYUCIHDFEN44HO6XQ554NN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QAXJYYUCIHDFEN44HO6XQ554NN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QAXJYYUCIHDFEN44HO6XQ554NN/action/storage_attestation","attest_author":"https://pith.science/pith/QAXJYYUCIHDFEN44HO6XQ554NN/action/author_attestation","sign_citation":"https://pith.science/pith/QAXJYYUCIHDFEN44HO6XQ554NN/action/citation_signature","submit_replication":"https://pith.science/pith/QAXJYYUCIHDFEN44HO6XQ554NN/action/replication_record"}},"created_at":"2026-05-18T01:14:11.501672+00:00","updated_at":"2026-05-18T01:14:11.501672+00:00"}