{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2010:2DUTW62HNN3Q7X3ICGAPRD5PLJ","short_pith_number":"pith:2DUTW62H","schema_version":"1.0","canonical_sha256":"d0e93b7b476b770fdf681180f88faf5a4ddb111e4a36ebf1f26858e637e415b2","source":{"kind":"arxiv","id":"1004.5370","version":1},"attestation_state":"computed","paper":{"title":"Self-Taught Hashing for Fast Similarity Search","license":"http://creativecommons.org/licenses/by/3.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Dell Zhang, Deng Cai, Jinsong Lu, Jun Wang","submitted_at":"2010-04-29T19:25:17Z","abstract_excerpt":"The ability of fast similarity search at large scale is of great importance to many Information Retrieval (IR) applications. A promising way to accelerate similarity search is semantic hashing which designs compact binary codes for a large number of documents so that semantically similar documents are mapped to similar codes (within a short Hamming distance). Although some recently proposed techniques are able to generate high-quality codes for documents known in advance, obtaining the codes for previously unseen documents remains to be a very challenging problem. In this paper, we emphasise 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":"1004.5370","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/3.0/","primary_cat":"cs.IR","submitted_at":"2010-04-29T19:25:17Z","cross_cats_sorted":[],"title_canon_sha256":"12aab813bfa8cb8fd3321e900a3e0d07444271ef39bbf6cbaf67af2c3f4908b8","abstract_canon_sha256":"ebdf20e70c3981ff4b027e0e710ab32569e1e833118a3c23376160b9e9a67f67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T17:27:40.555677Z","signature_b64":"VCD7QXUL/Hv0QFl3ZJvijKK20eoGInrbIvxiKUOeciQ4hpF6DFfZmVjdeRGPkGXSrYF0xF71k8L18Mieh0xQBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0e93b7b476b770fdf681180f88faf5a4ddb111e4a36ebf1f26858e637e415b2","last_reissued_at":"2026-07-04T17:27:40.555250Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T17:27:40.555250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Taught Hashing for Fast Similarity Search","license":"http://creativecommons.org/licenses/by/3.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Dell Zhang, Deng Cai, Jinsong Lu, Jun Wang","submitted_at":"2010-04-29T19:25:17Z","abstract_excerpt":"The ability of fast similarity search at large scale is of great importance to many Information Retrieval (IR) applications. A promising way to accelerate similarity search is semantic hashing which designs compact binary codes for a large number of documents so that semantically similar documents are mapped to similar codes (within a short Hamming distance). Although some recently proposed techniques are able to generate high-quality codes for documents known in advance, obtaining the codes for previously unseen documents remains to be a very challenging problem. In this paper, we emphasise t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1004.5370","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/1004.5370/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":"1004.5370","created_at":"2026-07-04T17:27:40.555321+00:00"},{"alias_kind":"arxiv_version","alias_value":"1004.5370v1","created_at":"2026-07-04T17:27:40.555321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1004.5370","created_at":"2026-07-04T17:27:40.555321+00:00"},{"alias_kind":"pith_short_12","alias_value":"2DUTW62HNN3Q","created_at":"2026-07-04T17:27:40.555321+00:00"},{"alias_kind":"pith_short_16","alias_value":"2DUTW62HNN3Q7X3I","created_at":"2026-07-04T17:27:40.555321+00:00"},{"alias_kind":"pith_short_8","alias_value":"2DUTW62H","created_at":"2026-07-04T17:27:40.555321+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/2DUTW62HNN3Q7X3ICGAPRD5PLJ","json":"https://pith.science/pith/2DUTW62HNN3Q7X3ICGAPRD5PLJ.json","graph_json":"https://pith.science/api/pith-number/2DUTW62HNN3Q7X3ICGAPRD5PLJ/graph.json","events_json":"https://pith.science/api/pith-number/2DUTW62HNN3Q7X3ICGAPRD5PLJ/events.json","paper":"https://pith.science/paper/2DUTW62H"},"agent_actions":{"view_html":"https://pith.science/pith/2DUTW62HNN3Q7X3ICGAPRD5PLJ","download_json":"https://pith.science/pith/2DUTW62HNN3Q7X3ICGAPRD5PLJ.json","view_paper":"https://pith.science/paper/2DUTW62H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1004.5370&json=true","fetch_graph":"https://pith.science/api/pith-number/2DUTW62HNN3Q7X3ICGAPRD5PLJ/graph.json","fetch_events":"https://pith.science/api/pith-number/2DUTW62HNN3Q7X3ICGAPRD5PLJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2DUTW62HNN3Q7X3ICGAPRD5PLJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2DUTW62HNN3Q7X3ICGAPRD5PLJ/action/storage_attestation","attest_author":"https://pith.science/pith/2DUTW62HNN3Q7X3ICGAPRD5PLJ/action/author_attestation","sign_citation":"https://pith.science/pith/2DUTW62HNN3Q7X3ICGAPRD5PLJ/action/citation_signature","submit_replication":"https://pith.science/pith/2DUTW62HNN3Q7X3ICGAPRD5PLJ/action/replication_record"}},"created_at":"2026-07-04T17:27:40.555321+00:00","updated_at":"2026-07-04T17:27:40.555321+00:00"}