{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:XBGMHUAFXSL554VFRFKHA4Y2SU","short_pith_number":"pith:XBGMHUAF","schema_version":"1.0","canonical_sha256":"b84cc3d005bc97def2a5895470731a9503d8d816aa977cc5fde327dd49a7b0ce","source":{"kind":"arxiv","id":"1501.02398","version":2},"attestation_state":"computed","paper":{"title":"Scalable high-dimensional indexing and searching with Hadoop","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.MM"],"primary_cat":"cs.IR","authors_text":"Denis Shestakov, Diana Moise","submitted_at":"2015-01-10T22:05:45Z","abstract_excerpt":"While high-dimensional search-by-similarity techniques reached their maturity and in overall provide good performance, most of them are unable to cope with very large multimedia collections. The 'big data' challenge however has to be addressed as multimedia collections have been explosively growing and will grow even faster than ever within the next few years. Luckily, computational processing power has become more available to researchers due to easier access to distributed grid infrastructures. In this paper, we show how high-dimensional indexing and searching methods can be used on scientif"},"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":"1501.02398","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2015-01-10T22:05:45Z","cross_cats_sorted":["cs.DC","cs.MM"],"title_canon_sha256":"994ad440510e05585f7ba5e8f3b36f40a0f1179bb2aeb82f99507a690b5b0f71","abstract_canon_sha256":"adc431b1286121255bfc48aba2cd2e3d9387bdf02a2a95d10810081589422ed8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:28:20.221133Z","signature_b64":"CBhkeEXd4PBxCElEnJGWeyPPrx2FDEUQRj/I0DkzQhRUt3QnvV6RP3Pdfh1LJAQ1xoySzkYyOmIqqt3h9ZcTBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b84cc3d005bc97def2a5895470731a9503d8d816aa977cc5fde327dd49a7b0ce","last_reissued_at":"2026-05-18T02:28:20.220569Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:28:20.220569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable high-dimensional indexing and searching with Hadoop","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.MM"],"primary_cat":"cs.IR","authors_text":"Denis Shestakov, Diana Moise","submitted_at":"2015-01-10T22:05:45Z","abstract_excerpt":"While high-dimensional search-by-similarity techniques reached their maturity and in overall provide good performance, most of them are unable to cope with very large multimedia collections. The 'big data' challenge however has to be addressed as multimedia collections have been explosively growing and will grow even faster than ever within the next few years. Luckily, computational processing power has become more available to researchers due to easier access to distributed grid infrastructures. In this paper, we show how high-dimensional indexing and searching methods can be used on scientif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1501.02398","kind":"arxiv","version":2},"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":"1501.02398","created_at":"2026-05-18T02:28:20.220656+00:00"},{"alias_kind":"arxiv_version","alias_value":"1501.02398v2","created_at":"2026-05-18T02:28:20.220656+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1501.02398","created_at":"2026-05-18T02:28:20.220656+00:00"},{"alias_kind":"pith_short_12","alias_value":"XBGMHUAFXSL5","created_at":"2026-05-18T12:29:50.041715+00:00"},{"alias_kind":"pith_short_16","alias_value":"XBGMHUAFXSL554VF","created_at":"2026-05-18T12:29:50.041715+00:00"},{"alias_kind":"pith_short_8","alias_value":"XBGMHUAF","created_at":"2026-05-18T12:29:50.041715+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/XBGMHUAFXSL554VFRFKHA4Y2SU","json":"https://pith.science/pith/XBGMHUAFXSL554VFRFKHA4Y2SU.json","graph_json":"https://pith.science/api/pith-number/XBGMHUAFXSL554VFRFKHA4Y2SU/graph.json","events_json":"https://pith.science/api/pith-number/XBGMHUAFXSL554VFRFKHA4Y2SU/events.json","paper":"https://pith.science/paper/XBGMHUAF"},"agent_actions":{"view_html":"https://pith.science/pith/XBGMHUAFXSL554VFRFKHA4Y2SU","download_json":"https://pith.science/pith/XBGMHUAFXSL554VFRFKHA4Y2SU.json","view_paper":"https://pith.science/paper/XBGMHUAF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1501.02398&json=true","fetch_graph":"https://pith.science/api/pith-number/XBGMHUAFXSL554VFRFKHA4Y2SU/graph.json","fetch_events":"https://pith.science/api/pith-number/XBGMHUAFXSL554VFRFKHA4Y2SU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XBGMHUAFXSL554VFRFKHA4Y2SU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XBGMHUAFXSL554VFRFKHA4Y2SU/action/storage_attestation","attest_author":"https://pith.science/pith/XBGMHUAFXSL554VFRFKHA4Y2SU/action/author_attestation","sign_citation":"https://pith.science/pith/XBGMHUAFXSL554VFRFKHA4Y2SU/action/citation_signature","submit_replication":"https://pith.science/pith/XBGMHUAFXSL554VFRFKHA4Y2SU/action/replication_record"}},"created_at":"2026-05-18T02:28:20.220656+00:00","updated_at":"2026-05-18T02:28:20.220656+00:00"}