{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:COMLRHXMXLM663M7J4IUP2GSD7","short_pith_number":"pith:COMLRHXM","canonical_record":{"source":{"id":"1612.01437","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2016-12-05T17:16:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fa6752f876649e2cbe4ad5ce883dc715213022a4d5ccf4ddd8d05794a64ccce1","abstract_canon_sha256":"0bb281d12ce5c94319704ac192dac922aa67f71ad1434858ce4e7037fd52f41e"},"schema_version":"1.0"},"canonical_sha256":"1398b89eecbad9ef6d9f4f1147e8d21fd16ffe0ec083262bd8c87c8465abe96f","source":{"kind":"arxiv","id":"1612.01437","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.01437","created_at":"2026-05-18T00:12:49Z"},{"alias_kind":"arxiv_version","alias_value":"1612.01437v2","created_at":"2026-05-18T00:12:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.01437","created_at":"2026-05-18T00:12:49Z"},{"alias_kind":"pith_short_12","alias_value":"COMLRHXMXLM6","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_16","alias_value":"COMLRHXMXLM663M7","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_8","alias_value":"COMLRHXM","created_at":"2026-05-18T12:30:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:COMLRHXMXLM663M7J4IUP2GSD7","target":"record","payload":{"canonical_record":{"source":{"id":"1612.01437","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2016-12-05T17:16:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fa6752f876649e2cbe4ad5ce883dc715213022a4d5ccf4ddd8d05794a64ccce1","abstract_canon_sha256":"0bb281d12ce5c94319704ac192dac922aa67f71ad1434858ce4e7037fd52f41e"},"schema_version":"1.0"},"canonical_sha256":"1398b89eecbad9ef6d9f4f1147e8d21fd16ffe0ec083262bd8c87c8465abe96f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:49.027689Z","signature_b64":"u8Owr8QOI26DvS6ks0y1Krl0g7863W1zwPwuMELcLmnak+y/al65x5urhrF5Dbd9gF5wZQgj5P59oEQhANJDBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1398b89eecbad9ef6d9f4f1147e8d21fd16ffe0ec083262bd8c87c8465abe96f","last_reissued_at":"2026-05-18T00:12:49.026994Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:49.026994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1612.01437","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:12:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JnkwTHXtmvHY//FOzWtI7shiLQZ/sXB4eBSkBfvuAS/hQ5hfr3VZT5fjVO6Bs3CEkH7y+r4z7N+4apAWT//2BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T02:21:02.396801Z"},"content_sha256":"c141a2688903ceecb1f6ec8bd7ce08b8027c66c6437d22610395930971ebeb91","schema_version":"1.0","event_id":"sha256:c141a2688903ceecb1f6ec8bd7ce08b8027c66c6437d22610395930971ebeb91"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:COMLRHXMXLM663M7J4IUP2GSD7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding and Optimizing the Performance of Distributed Machine Learning Applications on Apache Spark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Celestine D\\\"unner, Haralampos Pozidis, Kubilay Atasu, Manolis Sifalakis, Thomas Parnell","submitted_at":"2016-12-05T17:16:05Z","abstract_excerpt":"In this paper we explore the performance limits of Apache Spark for machine learning applications. We begin by analyzing the characteristics of a state-of-the-art distributed machine learning algorithm implemented in Spark and compare it to an equivalent reference implementation using the high performance computing framework MPI. We identify critical bottlenecks of the Spark framework and carefully study their implications on the performance of the algorithm. In order to improve Spark performance we then propose a number of practical techniques to alleviate some of its overheads. However, opti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.01437","kind":"arxiv","version":2},"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":"2026-05-18T00:12:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ntZ1zum8x82QEuWsQzz0X6Nlw5Ff4BH1eAdP2QJQePWc2L8t6b9FUOnJPESwrAP/2G6K8ORZ7W3H6gJDRl6yBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T02:21:02.397472Z"},"content_sha256":"ccdbe97465159815422bdf7af129abb084489a5827ab2bea050d1dd9cdfd3854","schema_version":"1.0","event_id":"sha256:ccdbe97465159815422bdf7af129abb084489a5827ab2bea050d1dd9cdfd3854"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/COMLRHXMXLM663M7J4IUP2GSD7/bundle.json","state_url":"https://pith.science/pith/COMLRHXMXLM663M7J4IUP2GSD7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/COMLRHXMXLM663M7J4IUP2GSD7/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":"2026-05-26T02:21:02Z","links":{"resolver":"https://pith.science/pith/COMLRHXMXLM663M7J4IUP2GSD7","bundle":"https://pith.science/pith/COMLRHXMXLM663M7J4IUP2GSD7/bundle.json","state":"https://pith.science/pith/COMLRHXMXLM663M7J4IUP2GSD7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/COMLRHXMXLM663M7J4IUP2GSD7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:COMLRHXMXLM663M7J4IUP2GSD7","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":"0bb281d12ce5c94319704ac192dac922aa67f71ad1434858ce4e7037fd52f41e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2016-12-05T17:16:05Z","title_canon_sha256":"fa6752f876649e2cbe4ad5ce883dc715213022a4d5ccf4ddd8d05794a64ccce1"},"schema_version":"1.0","source":{"id":"1612.01437","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.01437","created_at":"2026-05-18T00:12:49Z"},{"alias_kind":"arxiv_version","alias_value":"1612.01437v2","created_at":"2026-05-18T00:12:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.01437","created_at":"2026-05-18T00:12:49Z"},{"alias_kind":"pith_short_12","alias_value":"COMLRHXMXLM6","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_16","alias_value":"COMLRHXMXLM663M7","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_8","alias_value":"COMLRHXM","created_at":"2026-05-18T12:30:09Z"}],"graph_snapshots":[{"event_id":"sha256:ccdbe97465159815422bdf7af129abb084489a5827ab2bea050d1dd9cdfd3854","target":"graph","created_at":"2026-05-18T00:12:49Z","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":"In this paper we explore the performance limits of Apache Spark for machine learning applications. We begin by analyzing the characteristics of a state-of-the-art distributed machine learning algorithm implemented in Spark and compare it to an equivalent reference implementation using the high performance computing framework MPI. We identify critical bottlenecks of the Spark framework and carefully study their implications on the performance of the algorithm. In order to improve Spark performance we then propose a number of practical techniques to alleviate some of its overheads. However, opti","authors_text":"Celestine D\\\"unner, Haralampos Pozidis, Kubilay Atasu, Manolis Sifalakis, Thomas Parnell","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2016-12-05T17:16:05Z","title":"Understanding and Optimizing the Performance of Distributed Machine Learning Applications on Apache Spark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.01437","kind":"arxiv","version":2},"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:c141a2688903ceecb1f6ec8bd7ce08b8027c66c6437d22610395930971ebeb91","target":"record","created_at":"2026-05-18T00:12:49Z","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":"0bb281d12ce5c94319704ac192dac922aa67f71ad1434858ce4e7037fd52f41e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2016-12-05T17:16:05Z","title_canon_sha256":"fa6752f876649e2cbe4ad5ce883dc715213022a4d5ccf4ddd8d05794a64ccce1"},"schema_version":"1.0","source":{"id":"1612.01437","kind":"arxiv","version":2}},"canonical_sha256":"1398b89eecbad9ef6d9f4f1147e8d21fd16ffe0ec083262bd8c87c8465abe96f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1398b89eecbad9ef6d9f4f1147e8d21fd16ffe0ec083262bd8c87c8465abe96f","first_computed_at":"2026-05-18T00:12:49.026994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:12:49.026994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u8Owr8QOI26DvS6ks0y1Krl0g7863W1zwPwuMELcLmnak+y/al65x5urhrF5Dbd9gF5wZQgj5P59oEQhANJDBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:12:49.027689Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.01437","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c141a2688903ceecb1f6ec8bd7ce08b8027c66c6437d22610395930971ebeb91","sha256:ccdbe97465159815422bdf7af129abb084489a5827ab2bea050d1dd9cdfd3854"],"state_sha256":"61bb2c80f4e21cf5f30f12e593a6a3274d58e9e8fd1c358119ecb570f0eb6377"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JakXh8ZplsfVTUY3gKcArGs9pOzJFkfFUVdwAy6sN6NNZ9mxXFZlVdkRF7XUmncnnsQDN74tnJ4LtY0/5u11Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T02:21:02.402059Z","bundle_sha256":"d5ac605ac754ac55f8ae57619d274a1396901a8b1e3e684e1773f27a9deffa46"}}