{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:UAUJA4WNU3MYM7VL236LDO3RM4","short_pith_number":"pith:UAUJA4WN","schema_version":"1.0","canonical_sha256":"a0289072cda6d9867eabd6fcb1bb71672ef6c958b9cbfcba0931b88fe020b77d","source":{"kind":"arxiv","id":"1806.01270","version":1},"attestation_state":"computed","paper":{"title":"Alchemist: An Apache Spark <=> MPI Interface","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","physics.data-an","stat.CO"],"primary_cat":"cs.DC","authors_text":"Alex Gittens, Jey Kottalam, Kai Rothauge, Kristyn Maschhoff, Lisa Gerhardt, Michael Ringenburg, Michael W. Mahoney, Prabhat, Shusen Wang","submitted_at":"2018-06-03T23:25:29Z","abstract_excerpt":"The Apache Spark framework for distributed computation is popular in the data analytics community due to its ease of use, but its MapReduce-style programming model can incur significant overheads when performing computations that do not map directly onto this model. One way to mitigate these costs is to off-load computations onto MPI codes. In recent work, we introduced Alchemist, a system for the analysis of large-scale data sets. Alchemist calls MPI-based libraries from within Spark applications, and it has minimal coding, communication, and memory overheads. In particular, Alchemist allows "},"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":"1806.01270","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-06-03T23:25:29Z","cross_cats_sorted":["cs.DB","physics.data-an","stat.CO"],"title_canon_sha256":"de1d13a79e1a749ab7f4c553a4a88c290de571644d4db57511e733c2728147b9","abstract_canon_sha256":"7ce7448c39103c9e8a407e1a1de647d83ed8d1c74e94adab0ffa3956e5ad6ff5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:13.282367Z","signature_b64":"r2BEdYKu1PV8SYptbzOJ+QGct2JcwIsoCBjJ4BjBNvfKHzmOsvCIRxLUZ+FtDPaib0D5LwnDgQItwKDohbBOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0289072cda6d9867eabd6fcb1bb71672ef6c958b9cbfcba0931b88fe020b77d","last_reissued_at":"2026-05-18T00:14:13.281582Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:13.281582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Alchemist: An Apache Spark <=> MPI Interface","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","physics.data-an","stat.CO"],"primary_cat":"cs.DC","authors_text":"Alex Gittens, Jey Kottalam, Kai Rothauge, Kristyn Maschhoff, Lisa Gerhardt, Michael Ringenburg, Michael W. Mahoney, Prabhat, Shusen Wang","submitted_at":"2018-06-03T23:25:29Z","abstract_excerpt":"The Apache Spark framework for distributed computation is popular in the data analytics community due to its ease of use, but its MapReduce-style programming model can incur significant overheads when performing computations that do not map directly onto this model. One way to mitigate these costs is to off-load computations onto MPI codes. In recent work, we introduced Alchemist, a system for the analysis of large-scale data sets. Alchemist calls MPI-based libraries from within Spark applications, and it has minimal coding, communication, and memory overheads. In particular, Alchemist allows "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.01270","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":"1806.01270","created_at":"2026-05-18T00:14:13.281717+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.01270v1","created_at":"2026-05-18T00:14:13.281717+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.01270","created_at":"2026-05-18T00:14:13.281717+00:00"},{"alias_kind":"pith_short_12","alias_value":"UAUJA4WNU3MY","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"UAUJA4WNU3MYM7VL","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"UAUJA4WN","created_at":"2026-05-18T12:32:56.356000+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/UAUJA4WNU3MYM7VL236LDO3RM4","json":"https://pith.science/pith/UAUJA4WNU3MYM7VL236LDO3RM4.json","graph_json":"https://pith.science/api/pith-number/UAUJA4WNU3MYM7VL236LDO3RM4/graph.json","events_json":"https://pith.science/api/pith-number/UAUJA4WNU3MYM7VL236LDO3RM4/events.json","paper":"https://pith.science/paper/UAUJA4WN"},"agent_actions":{"view_html":"https://pith.science/pith/UAUJA4WNU3MYM7VL236LDO3RM4","download_json":"https://pith.science/pith/UAUJA4WNU3MYM7VL236LDO3RM4.json","view_paper":"https://pith.science/paper/UAUJA4WN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.01270&json=true","fetch_graph":"https://pith.science/api/pith-number/UAUJA4WNU3MYM7VL236LDO3RM4/graph.json","fetch_events":"https://pith.science/api/pith-number/UAUJA4WNU3MYM7VL236LDO3RM4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UAUJA4WNU3MYM7VL236LDO3RM4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UAUJA4WNU3MYM7VL236LDO3RM4/action/storage_attestation","attest_author":"https://pith.science/pith/UAUJA4WNU3MYM7VL236LDO3RM4/action/author_attestation","sign_citation":"https://pith.science/pith/UAUJA4WNU3MYM7VL236LDO3RM4/action/citation_signature","submit_replication":"https://pith.science/pith/UAUJA4WNU3MYM7VL236LDO3RM4/action/replication_record"}},"created_at":"2026-05-18T00:14:13.281717+00:00","updated_at":"2026-05-18T00:14:13.281717+00:00"}