{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:UAUJA4WNU3MYM7VL236LDO3RM4","short_pith_number":"pith:UAUJA4WN","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"},"canonical_sha256":"a0289072cda6d9867eabd6fcb1bb71672ef6c958b9cbfcba0931b88fe020b77d","source":{"kind":"arxiv","id":"1806.01270","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.01270","created_at":"2026-05-18T00:14:13Z"},{"alias_kind":"arxiv_version","alias_value":"1806.01270v1","created_at":"2026-05-18T00:14:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.01270","created_at":"2026-05-18T00:14:13Z"},{"alias_kind":"pith_short_12","alias_value":"UAUJA4WNU3MY","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UAUJA4WNU3MYM7VL","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UAUJA4WN","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:UAUJA4WNU3MYM7VL236LDO3RM4","target":"record","payload":{"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"},"canonical_sha256":"a0289072cda6d9867eabd6fcb1bb71672ef6c958b9cbfcba0931b88fe020b77d","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"},"source_kind":"arxiv","source_id":"1806.01270","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:14:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WjD9uAzAQDQAaft1IVGqmDiATfYEZuW6lQWKkRjeXQPu6pi6KQLQw8Z7Z8KoxuvZyDR2UROCs5mKT0zEoKtOCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T11:38:38.791507Z"},"content_sha256":"1f6008cadf79075194048e1e9eb350ee1df63a1f6b007f3f590bd6797e40b179","schema_version":"1.0","event_id":"sha256:1f6008cadf79075194048e1e9eb350ee1df63a1f6b007f3f590bd6797e40b179"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:UAUJA4WNU3MYM7VL236LDO3RM4","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:14:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TncnnjrLdn535m9xubylSnyVzQo9jGsVr6gdw1t+/pqv5ne6SnOj6Zrn8oJcDXtD8r8mnDOb741GyofEJmhBDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T11:38:38.791858Z"},"content_sha256":"4c542dc2f92c95ae466543e46fa4ab7f2cfcca1bcea7bb72b935ea2894849926","schema_version":"1.0","event_id":"sha256:4c542dc2f92c95ae466543e46fa4ab7f2cfcca1bcea7bb72b935ea2894849926"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UAUJA4WNU3MYM7VL236LDO3RM4/bundle.json","state_url":"https://pith.science/pith/UAUJA4WNU3MYM7VL236LDO3RM4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UAUJA4WNU3MYM7VL236LDO3RM4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-19T11:38:38Z","links":{"resolver":"https://pith.science/pith/UAUJA4WNU3MYM7VL236LDO3RM4","bundle":"https://pith.science/pith/UAUJA4WNU3MYM7VL236LDO3RM4/bundle.json","state":"https://pith.science/pith/UAUJA4WNU3MYM7VL236LDO3RM4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UAUJA4WNU3MYM7VL236LDO3RM4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:UAUJA4WNU3MYM7VL236LDO3RM4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7ce7448c39103c9e8a407e1a1de647d83ed8d1c74e94adab0ffa3956e5ad6ff5","cross_cats_sorted":["cs.DB","physics.data-an","stat.CO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-06-03T23:25:29Z","title_canon_sha256":"de1d13a79e1a749ab7f4c553a4a88c290de571644d4db57511e733c2728147b9"},"schema_version":"1.0","source":{"id":"1806.01270","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.01270","created_at":"2026-05-18T00:14:13Z"},{"alias_kind":"arxiv_version","alias_value":"1806.01270v1","created_at":"2026-05-18T00:14:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.01270","created_at":"2026-05-18T00:14:13Z"},{"alias_kind":"pith_short_12","alias_value":"UAUJA4WNU3MY","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UAUJA4WNU3MYM7VL","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UAUJA4WN","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:4c542dc2f92c95ae466543e46fa4ab7f2cfcca1bcea7bb72b935ea2894849926","target":"graph","created_at":"2026-05-18T00:14:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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 ","authors_text":"Alex Gittens, Jey Kottalam, Kai Rothauge, Kristyn Maschhoff, Lisa Gerhardt, Michael Ringenburg, Michael W. Mahoney, Prabhat, Shusen Wang","cross_cats":["cs.DB","physics.data-an","stat.CO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-06-03T23:25:29Z","title":"Alchemist: An Apache Spark <=> MPI Interface"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.01270","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1f6008cadf79075194048e1e9eb350ee1df63a1f6b007f3f590bd6797e40b179","target":"record","created_at":"2026-05-18T00:14:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7ce7448c39103c9e8a407e1a1de647d83ed8d1c74e94adab0ffa3956e5ad6ff5","cross_cats_sorted":["cs.DB","physics.data-an","stat.CO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-06-03T23:25:29Z","title_canon_sha256":"de1d13a79e1a749ab7f4c553a4a88c290de571644d4db57511e733c2728147b9"},"schema_version":"1.0","source":{"id":"1806.01270","kind":"arxiv","version":1}},"canonical_sha256":"a0289072cda6d9867eabd6fcb1bb71672ef6c958b9cbfcba0931b88fe020b77d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0289072cda6d9867eabd6fcb1bb71672ef6c958b9cbfcba0931b88fe020b77d","first_computed_at":"2026-05-18T00:14:13.281582Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:13.281582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r2BEdYKu1PV8SYptbzOJ+QGct2JcwIsoCBjJ4BjBNvfKHzmOsvCIRxLUZ+FtDPaib0D5LwnDgQItwKDohbBOCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:13.282367Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.01270","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f6008cadf79075194048e1e9eb350ee1df63a1f6b007f3f590bd6797e40b179","sha256:4c542dc2f92c95ae466543e46fa4ab7f2cfcca1bcea7bb72b935ea2894849926"],"state_sha256":"f373a88433f2f7ef82181488d2875721b9b658c6f5364bd9c1937a6d88631e37"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ta1oWjCr3OTsk5ELQ7kqtXmBKW055JNE+lckzlpLcgim0HQFIoswexFM8jhC45vpN6CBPDFprNE3bMaYaQM8DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T11:38:38.793556Z","bundle_sha256":"832dfa38c19255b3202756606dbabc436faba8ccfcb14ea266fedc8657ee0463"}}