{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:Q4G2UT7MUMX4RF5UBLJP4HRVHW","short_pith_number":"pith:Q4G2UT7M","canonical_record":{"source":{"id":"1507.08340","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2015-07-29T22:59:49Z","cross_cats_sorted":["cs.AR","cs.PF"],"title_canon_sha256":"e992a0649905564a6f00077397f0fe1f985fb2d72f5827eb925f07b02e79059c","abstract_canon_sha256":"829740dfeec9cebadeb474cfa1ef5fa93732180893330a2ebaeee3dac1c1ab87"},"schema_version":"1.0"},"canonical_sha256":"870daa4feca32fc897b40ad2fe1e353d85ab8ae01428b4960b6b9e0a2a9e5669","source":{"kind":"arxiv","id":"1507.08340","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.08340","created_at":"2026-05-18T01:36:04Z"},{"alias_kind":"arxiv_version","alias_value":"1507.08340v1","created_at":"2026-05-18T01:36:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.08340","created_at":"2026-05-18T01:36:04Z"},{"alias_kind":"pith_short_12","alias_value":"Q4G2UT7MUMX4","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_16","alias_value":"Q4G2UT7MUMX4RF5U","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_8","alias_value":"Q4G2UT7M","created_at":"2026-05-18T12:29:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:Q4G2UT7MUMX4RF5UBLJP4HRVHW","target":"record","payload":{"canonical_record":{"source":{"id":"1507.08340","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2015-07-29T22:59:49Z","cross_cats_sorted":["cs.AR","cs.PF"],"title_canon_sha256":"e992a0649905564a6f00077397f0fe1f985fb2d72f5827eb925f07b02e79059c","abstract_canon_sha256":"829740dfeec9cebadeb474cfa1ef5fa93732180893330a2ebaeee3dac1c1ab87"},"schema_version":"1.0"},"canonical_sha256":"870daa4feca32fc897b40ad2fe1e353d85ab8ae01428b4960b6b9e0a2a9e5669","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:36:04.356216Z","signature_b64":"maDqH+32StT6+t/zWvCNq1Dz7l6wF/HbBBPKBkqCGC1zeFGWemFptXiqLEfqECefyipP21WtsieGSf9rHJPoCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"870daa4feca32fc897b40ad2fe1e353d85ab8ae01428b4960b6b9e0a2a9e5669","last_reissued_at":"2026-05-18T01:36:04.355356Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:36:04.355356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1507.08340","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":"2026-05-18T01:36:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UdPkRIlYqYBsGjZxa5VFVhxzWPI6OUZltl6f4CP+PU4JrbIvb9YomCKYXqQMsu/Ux1W6t40MsXE7rhdAyfRXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T00:55:50.498170Z"},"content_sha256":"e791d7a8e041e0ca4b6444b625618c6563920e05be6fca29ddc2961c49268ba2","schema_version":"1.0","event_id":"sha256:e791d7a8e041e0ca4b6444b625618c6563920e05be6fca29ddc2961c49268ba2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:Q4G2UT7MUMX4RF5UBLJP4HRVHW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How Data Volume Affects Spark Based Data Analytics on a Scale-up Server","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AR","cs.PF"],"primary_cat":"cs.DC","authors_text":"Ahsan Javed Awan, Eduard Ayguade, Mats Brorsson, Vladimir Vlassov","submitted_at":"2015-07-29T22:59:49Z","abstract_excerpt":"Sheer increase in volume of data over the last decade has triggered research in cluster computing frameworks that enable web enterprises to extract big insights from big data. While Apache Spark is gaining popularity for exhibiting superior scale-out performance on the commodity machines, the impact of data volume on the performance of Spark based data analytics in scale-up configuration is not well understood. We present a deep-dive analysis of Spark based applications on a large scale-up server machine. Our analysis reveals that Spark based data analytics are DRAM bound and do not benefit by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.08340","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":"2026-05-18T01:36:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+3DQN7+k9b57WfRL2C9kggkwPT0QUcwp9af4TLJ4Y09EWxl3waiGeUNKT9rTndx/Tw9EAgl/5A6hj5xazbj0Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T00:55:50.498879Z"},"content_sha256":"14eb7fab729226dbd57b68a158a7ae948b5b31ce537c6b12f30f075ab5948bbf","schema_version":"1.0","event_id":"sha256:14eb7fab729226dbd57b68a158a7ae948b5b31ce537c6b12f30f075ab5948bbf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q4G2UT7MUMX4RF5UBLJP4HRVHW/bundle.json","state_url":"https://pith.science/pith/Q4G2UT7MUMX4RF5UBLJP4HRVHW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q4G2UT7MUMX4RF5UBLJP4HRVHW/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":"2026-05-26T00:55:50Z","links":{"resolver":"https://pith.science/pith/Q4G2UT7MUMX4RF5UBLJP4HRVHW","bundle":"https://pith.science/pith/Q4G2UT7MUMX4RF5UBLJP4HRVHW/bundle.json","state":"https://pith.science/pith/Q4G2UT7MUMX4RF5UBLJP4HRVHW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q4G2UT7MUMX4RF5UBLJP4HRVHW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:Q4G2UT7MUMX4RF5UBLJP4HRVHW","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":"829740dfeec9cebadeb474cfa1ef5fa93732180893330a2ebaeee3dac1c1ab87","cross_cats_sorted":["cs.AR","cs.PF"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2015-07-29T22:59:49Z","title_canon_sha256":"e992a0649905564a6f00077397f0fe1f985fb2d72f5827eb925f07b02e79059c"},"schema_version":"1.0","source":{"id":"1507.08340","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.08340","created_at":"2026-05-18T01:36:04Z"},{"alias_kind":"arxiv_version","alias_value":"1507.08340v1","created_at":"2026-05-18T01:36:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.08340","created_at":"2026-05-18T01:36:04Z"},{"alias_kind":"pith_short_12","alias_value":"Q4G2UT7MUMX4","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_16","alias_value":"Q4G2UT7MUMX4RF5U","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_8","alias_value":"Q4G2UT7M","created_at":"2026-05-18T12:29:37Z"}],"graph_snapshots":[{"event_id":"sha256:14eb7fab729226dbd57b68a158a7ae948b5b31ce537c6b12f30f075ab5948bbf","target":"graph","created_at":"2026-05-18T01:36:04Z","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":"Sheer increase in volume of data over the last decade has triggered research in cluster computing frameworks that enable web enterprises to extract big insights from big data. While Apache Spark is gaining popularity for exhibiting superior scale-out performance on the commodity machines, the impact of data volume on the performance of Spark based data analytics in scale-up configuration is not well understood. We present a deep-dive analysis of Spark based applications on a large scale-up server machine. Our analysis reveals that Spark based data analytics are DRAM bound and do not benefit by","authors_text":"Ahsan Javed Awan, Eduard Ayguade, Mats Brorsson, Vladimir Vlassov","cross_cats":["cs.AR","cs.PF"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2015-07-29T22:59:49Z","title":"How Data Volume Affects Spark Based Data Analytics on a Scale-up Server"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.08340","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:e791d7a8e041e0ca4b6444b625618c6563920e05be6fca29ddc2961c49268ba2","target":"record","created_at":"2026-05-18T01:36:04Z","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":"829740dfeec9cebadeb474cfa1ef5fa93732180893330a2ebaeee3dac1c1ab87","cross_cats_sorted":["cs.AR","cs.PF"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2015-07-29T22:59:49Z","title_canon_sha256":"e992a0649905564a6f00077397f0fe1f985fb2d72f5827eb925f07b02e79059c"},"schema_version":"1.0","source":{"id":"1507.08340","kind":"arxiv","version":1}},"canonical_sha256":"870daa4feca32fc897b40ad2fe1e353d85ab8ae01428b4960b6b9e0a2a9e5669","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"870daa4feca32fc897b40ad2fe1e353d85ab8ae01428b4960b6b9e0a2a9e5669","first_computed_at":"2026-05-18T01:36:04.355356Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:36:04.355356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"maDqH+32StT6+t/zWvCNq1Dz7l6wF/HbBBPKBkqCGC1zeFGWemFptXiqLEfqECefyipP21WtsieGSf9rHJPoCA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:36:04.356216Z","signed_message":"canonical_sha256_bytes"},"source_id":"1507.08340","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e791d7a8e041e0ca4b6444b625618c6563920e05be6fca29ddc2961c49268ba2","sha256:14eb7fab729226dbd57b68a158a7ae948b5b31ce537c6b12f30f075ab5948bbf"],"state_sha256":"559391b7eb0b204e149aa74343fa44034224ec602a044976cabfffa06bc8a053"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GYH6xql9SK2q7/QKBQdQkFKunTFLsCgWUGLU8ND7f02Ve3E6LP37IY0mOHDIGwQsmCm/jQ5r/rQn/T0QOvuNCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T00:55:50.502355Z","bundle_sha256":"4b28a791bb11c637a05a7b5387eb4848d0f3f187448b1f7c2862d23b618f0b75"}}