{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:LYCJ76XAFNEEO4CHLHAYMPSCNQ","short_pith_number":"pith:LYCJ76XA","schema_version":"1.0","canonical_sha256":"5e049ffae02b4847704759c1863e426c21ea89144976136abc7eab5e1f4ef15a","source":{"kind":"arxiv","id":"1208.1259","version":1},"attestation_state":"computed","paper":{"title":"One Permutation Hashing for Efficient Search and Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.IT","math.IT","stat.CO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Art Owen, Cun-Hui Zhang, Ping Li","submitted_at":"2012-08-06T12:28:06Z","abstract_excerpt":"Recently, the method of b-bit minwise hashing has been applied to large-scale linear learning and sublinear time near-neighbor search. The major drawback of minwise hashing is the expensive preprocessing cost, as the method requires applying (e.g.,) k=200 to 500 permutations on the data. The testing time can also be expensive if a new data point (e.g., a new document or image) has not been processed, which might be a significant issue in user-facing applications.\n  We develop a very simple solution based on one permutation hashing. Conceptually, given a massive binary data matrix, we permute t"},"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":"1208.1259","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-08-06T12:28:06Z","cross_cats_sorted":["cs.IR","cs.IT","math.IT","stat.CO","stat.ML"],"title_canon_sha256":"23467896f77f98e6a47a755521e47ac6782396d722206583642f925836a59fe6","abstract_canon_sha256":"a7a6aee06a1c3110b7ae46718b12451de0c246bfa9adec6f7ea703656fede71d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:49:19.449502Z","signature_b64":"+S7X/GQaHr9BKF0yWD5jqYL5H1jT7rw08jLi5W2c+bo9s7pIsC4Y24094oOTD1yDDjEM5tTnZJBufTzEit9yBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e049ffae02b4847704759c1863e426c21ea89144976136abc7eab5e1f4ef15a","last_reissued_at":"2026-05-18T03:49:19.448810Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:49:19.448810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One Permutation Hashing for Efficient Search and Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.IT","math.IT","stat.CO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Art Owen, Cun-Hui Zhang, Ping Li","submitted_at":"2012-08-06T12:28:06Z","abstract_excerpt":"Recently, the method of b-bit minwise hashing has been applied to large-scale linear learning and sublinear time near-neighbor search. The major drawback of minwise hashing is the expensive preprocessing cost, as the method requires applying (e.g.,) k=200 to 500 permutations on the data. The testing time can also be expensive if a new data point (e.g., a new document or image) has not been processed, which might be a significant issue in user-facing applications.\n  We develop a very simple solution based on one permutation hashing. Conceptually, given a massive binary data matrix, we permute t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1208.1259","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":"1208.1259","created_at":"2026-05-18T03:49:19.448917+00:00"},{"alias_kind":"arxiv_version","alias_value":"1208.1259v1","created_at":"2026-05-18T03:49:19.448917+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1208.1259","created_at":"2026-05-18T03:49:19.448917+00:00"},{"alias_kind":"pith_short_12","alias_value":"LYCJ76XAFNEE","created_at":"2026-05-18T12:27:14.488303+00:00"},{"alias_kind":"pith_short_16","alias_value":"LYCJ76XAFNEEO4CH","created_at":"2026-05-18T12:27:14.488303+00:00"},{"alias_kind":"pith_short_8","alias_value":"LYCJ76XA","created_at":"2026-05-18T12:27:14.488303+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/LYCJ76XAFNEEO4CHLHAYMPSCNQ","json":"https://pith.science/pith/LYCJ76XAFNEEO4CHLHAYMPSCNQ.json","graph_json":"https://pith.science/api/pith-number/LYCJ76XAFNEEO4CHLHAYMPSCNQ/graph.json","events_json":"https://pith.science/api/pith-number/LYCJ76XAFNEEO4CHLHAYMPSCNQ/events.json","paper":"https://pith.science/paper/LYCJ76XA"},"agent_actions":{"view_html":"https://pith.science/pith/LYCJ76XAFNEEO4CHLHAYMPSCNQ","download_json":"https://pith.science/pith/LYCJ76XAFNEEO4CHLHAYMPSCNQ.json","view_paper":"https://pith.science/paper/LYCJ76XA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1208.1259&json=true","fetch_graph":"https://pith.science/api/pith-number/LYCJ76XAFNEEO4CHLHAYMPSCNQ/graph.json","fetch_events":"https://pith.science/api/pith-number/LYCJ76XAFNEEO4CHLHAYMPSCNQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LYCJ76XAFNEEO4CHLHAYMPSCNQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LYCJ76XAFNEEO4CHLHAYMPSCNQ/action/storage_attestation","attest_author":"https://pith.science/pith/LYCJ76XAFNEEO4CHLHAYMPSCNQ/action/author_attestation","sign_citation":"https://pith.science/pith/LYCJ76XAFNEEO4CHLHAYMPSCNQ/action/citation_signature","submit_replication":"https://pith.science/pith/LYCJ76XAFNEEO4CHLHAYMPSCNQ/action/replication_record"}},"created_at":"2026-05-18T03:49:19.448917+00:00","updated_at":"2026-05-18T03:49:19.448917+00:00"}