{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2010:SR45IXIQGVA7OUGVVS5ONTTIUM","short_pith_number":"pith:SR45IXIQ","schema_version":"1.0","canonical_sha256":"9479d45d103541f750d5acbae6ce68a336b3b94fd83fd41ecf9d21fb823fcc6a","source":{"kind":"arxiv","id":"1004.4489","version":1},"attestation_state":"computed","paper":{"title":"MIREX: MapReduce Information Retrieval Experiments","license":"http://creativecommons.org/licenses/by/3.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Claudia Hauff, Djoerd Hiemstra","submitted_at":"2010-04-26T11:36:38Z","abstract_excerpt":"We propose to use MapReduce to quickly test new retrieval approaches on a cluster of machines by sequentially scanning all documents. We present a small case study in which we use a cluster of 15 low cost ma- chines to search a web crawl of 0.5 billion pages showing that sequential scanning is a viable approach to running large-scale information retrieval experiments with little effort. The code is available to other researchers at: http://mirex.sourceforge.net"},"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":"1004.4489","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/3.0/","primary_cat":"cs.IR","submitted_at":"2010-04-26T11:36:38Z","cross_cats_sorted":[],"title_canon_sha256":"666e93ac30e9721d255bfaa692ad9d957beef77c17dbd604226c53c9800fb3af","abstract_canon_sha256":"02bf3b29f3b13b6a6a0a30418ed6a8d9a6409ffadfe5eb08f930591662739e35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:56:36.534247Z","signature_b64":"ZIAANJuH4O+UJ50KLQ5KUYoMmdKR8dk+R4PpUdvY0g2CYS8Q4bv/flXIPD9vgTcCITe+ap1K6UfAlI9M0N3SBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9479d45d103541f750d5acbae6ce68a336b3b94fd83fd41ecf9d21fb823fcc6a","last_reissued_at":"2026-05-18T03:56:36.533517Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:56:36.533517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MIREX: MapReduce Information Retrieval Experiments","license":"http://creativecommons.org/licenses/by/3.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Claudia Hauff, Djoerd Hiemstra","submitted_at":"2010-04-26T11:36:38Z","abstract_excerpt":"We propose to use MapReduce to quickly test new retrieval approaches on a cluster of machines by sequentially scanning all documents. We present a small case study in which we use a cluster of 15 low cost ma- chines to search a web crawl of 0.5 billion pages showing that sequential scanning is a viable approach to running large-scale information retrieval experiments with little effort. The code is available to other researchers at: http://mirex.sourceforge.net"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1004.4489","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":"1004.4489","created_at":"2026-05-18T03:56:36.533645+00:00"},{"alias_kind":"arxiv_version","alias_value":"1004.4489v1","created_at":"2026-05-18T03:56:36.533645+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1004.4489","created_at":"2026-05-18T03:56:36.533645+00:00"},{"alias_kind":"pith_short_12","alias_value":"SR45IXIQGVA7","created_at":"2026-05-18T12:26:13.927090+00:00"},{"alias_kind":"pith_short_16","alias_value":"SR45IXIQGVA7OUGV","created_at":"2026-05-18T12:26:13.927090+00:00"},{"alias_kind":"pith_short_8","alias_value":"SR45IXIQ","created_at":"2026-05-18T12:26:13.927090+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/SR45IXIQGVA7OUGVVS5ONTTIUM","json":"https://pith.science/pith/SR45IXIQGVA7OUGVVS5ONTTIUM.json","graph_json":"https://pith.science/api/pith-number/SR45IXIQGVA7OUGVVS5ONTTIUM/graph.json","events_json":"https://pith.science/api/pith-number/SR45IXIQGVA7OUGVVS5ONTTIUM/events.json","paper":"https://pith.science/paper/SR45IXIQ"},"agent_actions":{"view_html":"https://pith.science/pith/SR45IXIQGVA7OUGVVS5ONTTIUM","download_json":"https://pith.science/pith/SR45IXIQGVA7OUGVVS5ONTTIUM.json","view_paper":"https://pith.science/paper/SR45IXIQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1004.4489&json=true","fetch_graph":"https://pith.science/api/pith-number/SR45IXIQGVA7OUGVVS5ONTTIUM/graph.json","fetch_events":"https://pith.science/api/pith-number/SR45IXIQGVA7OUGVVS5ONTTIUM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SR45IXIQGVA7OUGVVS5ONTTIUM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SR45IXIQGVA7OUGVVS5ONTTIUM/action/storage_attestation","attest_author":"https://pith.science/pith/SR45IXIQGVA7OUGVVS5ONTTIUM/action/author_attestation","sign_citation":"https://pith.science/pith/SR45IXIQGVA7OUGVVS5ONTTIUM/action/citation_signature","submit_replication":"https://pith.science/pith/SR45IXIQGVA7OUGVVS5ONTTIUM/action/replication_record"}},"created_at":"2026-05-18T03:56:36.533645+00:00","updated_at":"2026-05-18T03:56:36.533645+00:00"}