{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:RUT6JLMNG4ADT5MNDD4JAHEJCZ","short_pith_number":"pith:RUT6JLMN","canonical_record":{"source":{"id":"1607.01335","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2016-07-05T17:19:53Z","cross_cats_sorted":[],"title_canon_sha256":"1a78aae7718353583bace4593c67929206bf15650832792632695ef6abad8121","abstract_canon_sha256":"b7565d5fa7eeda8bc77af80bb2636f5e01596520205b50ca7fcaa8bcd35f881d"},"schema_version":"1.0"},"canonical_sha256":"8d27e4ad8d370039f58d18f8901c891647f31b842a7e534f654a15fbba8dd3a1","source":{"kind":"arxiv","id":"1607.01335","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1607.01335","created_at":"2026-05-18T01:04:08Z"},{"alias_kind":"arxiv_version","alias_value":"1607.01335v3","created_at":"2026-05-18T01:04:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.01335","created_at":"2026-05-18T01:04:08Z"},{"alias_kind":"pith_short_12","alias_value":"RUT6JLMNG4AD","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"RUT6JLMNG4ADT5MN","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"RUT6JLMN","created_at":"2026-05-18T12:30:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:RUT6JLMNG4ADT5MNDD4JAHEJCZ","target":"record","payload":{"canonical_record":{"source":{"id":"1607.01335","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2016-07-05T17:19:53Z","cross_cats_sorted":[],"title_canon_sha256":"1a78aae7718353583bace4593c67929206bf15650832792632695ef6abad8121","abstract_canon_sha256":"b7565d5fa7eeda8bc77af80bb2636f5e01596520205b50ca7fcaa8bcd35f881d"},"schema_version":"1.0"},"canonical_sha256":"8d27e4ad8d370039f58d18f8901c891647f31b842a7e534f654a15fbba8dd3a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:04:08.860676Z","signature_b64":"3J2HSPEQYRz1fQAGmKocR6happ0lGDbjPccFJkiaSfw/Q2xYCl/aL4VNrzWBojRE+CtOOKP5FAsQ7042rAdWDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d27e4ad8d370039f58d18f8901c891647f31b842a7e534f654a15fbba8dd3a1","last_reissued_at":"2026-05-18T01:04:08.859976Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:04:08.859976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1607.01335","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:04:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bk2kVDUlA/xi1oc5p4tQ9pNKDhx2GXpoSNSXh6NBCxGWHVPI4O3sicETrCjlBgT8ZfdgFSLvqdrCPokJTWWuAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T11:16:52.525541Z"},"content_sha256":"a1f6fcda3342e104010604e97648d615418f18c7c2b2f98c6fc65f24c3803f4c","schema_version":"1.0","event_id":"sha256:a1f6fcda3342e104010604e97648d615418f18c7c2b2f98c6fc65f24c3803f4c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:RUT6JLMNG4ADT5MNDD4JAHEJCZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Matrix Factorization at Scale: a Comparison of Scientific Data Analytics in Spark and C+MPI Using Three Case Studies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Aditya Devarakonda, Alex Gittens, Evan Racah, James Demmel, Jatin Chhugani, Jey Kottalam, Jialin Liu, Jim Harrell, Jiyan Yang, Kristyn Maschhoff, Lisa Gerhardt, Michael Ringenburg, Michael W. Mahoney, Prabhat, Pramod Sharma, Shane Canon, Venkat Krishnamurthy","submitted_at":"2016-07-05T17:19:53Z","abstract_excerpt":"We explore the trade-offs of performing linear algebra using Apache Spark, compared to traditional C and MPI implementations on HPC platforms. Spark is designed for data analytics on cluster computing platforms with access to local disks and is optimized for data-parallel tasks. We examine three widely-used and important matrix factorizations: NMF (for physical plausability), PCA (for its ubiquity) and CX (for data interpretability). We apply these methods to TB-sized problems in particle physics, climate modeling and bioimaging. The data matrices are tall-and-skinny which enable the algorithm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.01335","kind":"arxiv","version":3},"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":"2026-05-18T01:04:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W2Q8xiXIjyRSDup+zssOUTDDRxB63ssNIX0OaJjikthccP9hXAdmLXjCz00Q9BqEKyKPQrwDOGjR6OA3MGZ0Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T11:16:52.526240Z"},"content_sha256":"5c36072a7f9a359c3bd199ca5a7640d5ef4717d652477f66f51fae8230bbe6c2","schema_version":"1.0","event_id":"sha256:5c36072a7f9a359c3bd199ca5a7640d5ef4717d652477f66f51fae8230bbe6c2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RUT6JLMNG4ADT5MNDD4JAHEJCZ/bundle.json","state_url":"https://pith.science/pith/RUT6JLMNG4ADT5MNDD4JAHEJCZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RUT6JLMNG4ADT5MNDD4JAHEJCZ/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":"2026-05-27T11:16:52Z","links":{"resolver":"https://pith.science/pith/RUT6JLMNG4ADT5MNDD4JAHEJCZ","bundle":"https://pith.science/pith/RUT6JLMNG4ADT5MNDD4JAHEJCZ/bundle.json","state":"https://pith.science/pith/RUT6JLMNG4ADT5MNDD4JAHEJCZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RUT6JLMNG4ADT5MNDD4JAHEJCZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:RUT6JLMNG4ADT5MNDD4JAHEJCZ","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":"b7565d5fa7eeda8bc77af80bb2636f5e01596520205b50ca7fcaa8bcd35f881d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2016-07-05T17:19:53Z","title_canon_sha256":"1a78aae7718353583bace4593c67929206bf15650832792632695ef6abad8121"},"schema_version":"1.0","source":{"id":"1607.01335","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1607.01335","created_at":"2026-05-18T01:04:08Z"},{"alias_kind":"arxiv_version","alias_value":"1607.01335v3","created_at":"2026-05-18T01:04:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.01335","created_at":"2026-05-18T01:04:08Z"},{"alias_kind":"pith_short_12","alias_value":"RUT6JLMNG4AD","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"RUT6JLMNG4ADT5MN","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"RUT6JLMN","created_at":"2026-05-18T12:30:41Z"}],"graph_snapshots":[{"event_id":"sha256:5c36072a7f9a359c3bd199ca5a7640d5ef4717d652477f66f51fae8230bbe6c2","target":"graph","created_at":"2026-05-18T01:04:08Z","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":"We explore the trade-offs of performing linear algebra using Apache Spark, compared to traditional C and MPI implementations on HPC platforms. Spark is designed for data analytics on cluster computing platforms with access to local disks and is optimized for data-parallel tasks. We examine three widely-used and important matrix factorizations: NMF (for physical plausability), PCA (for its ubiquity) and CX (for data interpretability). We apply these methods to TB-sized problems in particle physics, climate modeling and bioimaging. The data matrices are tall-and-skinny which enable the algorithm","authors_text":"Aditya Devarakonda, Alex Gittens, Evan Racah, James Demmel, Jatin Chhugani, Jey Kottalam, Jialin Liu, Jim Harrell, Jiyan Yang, Kristyn Maschhoff, Lisa Gerhardt, Michael Ringenburg, Michael W. Mahoney, Prabhat, Pramod Sharma, Shane Canon, Venkat Krishnamurthy","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2016-07-05T17:19:53Z","title":"Matrix Factorization at Scale: a Comparison of Scientific Data Analytics in Spark and C+MPI Using Three Case Studies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.01335","kind":"arxiv","version":3},"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:a1f6fcda3342e104010604e97648d615418f18c7c2b2f98c6fc65f24c3803f4c","target":"record","created_at":"2026-05-18T01:04:08Z","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":"b7565d5fa7eeda8bc77af80bb2636f5e01596520205b50ca7fcaa8bcd35f881d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2016-07-05T17:19:53Z","title_canon_sha256":"1a78aae7718353583bace4593c67929206bf15650832792632695ef6abad8121"},"schema_version":"1.0","source":{"id":"1607.01335","kind":"arxiv","version":3}},"canonical_sha256":"8d27e4ad8d370039f58d18f8901c891647f31b842a7e534f654a15fbba8dd3a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d27e4ad8d370039f58d18f8901c891647f31b842a7e534f654a15fbba8dd3a1","first_computed_at":"2026-05-18T01:04:08.859976Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:04:08.859976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3J2HSPEQYRz1fQAGmKocR6happ0lGDbjPccFJkiaSfw/Q2xYCl/aL4VNrzWBojRE+CtOOKP5FAsQ7042rAdWDA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:04:08.860676Z","signed_message":"canonical_sha256_bytes"},"source_id":"1607.01335","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1f6fcda3342e104010604e97648d615418f18c7c2b2f98c6fc65f24c3803f4c","sha256:5c36072a7f9a359c3bd199ca5a7640d5ef4717d652477f66f51fae8230bbe6c2"],"state_sha256":"2adb182b1747c0e958252a523b7ad946197658a9885f4781b121c3e3fb24f817"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0F/Ib5OnxOil97KSjNBaLzSzBkT/0wbkGxAH9QikMmy8ggGQYzR2FTuo0H7iZNN+hmHLZZCng6z8q6yiLksJBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T11:16:52.529472Z","bundle_sha256":"4e36299665cdea688058a1afa088747d411a0e08711b8da8832511123560ccdb"}}