{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:UX4ESTOHBCUNL3WWRAIGGR55LU","short_pith_number":"pith:UX4ESTOH","canonical_record":{"source":{"id":"1505.06872","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2015-05-26T09:38:08Z","cross_cats_sorted":[],"title_canon_sha256":"e0c52ba0bed75be8c63e1c090d2e0c2a8928f6d41c3e5df7e1367547eed3c7ea","abstract_canon_sha256":"9bf762bd3824d0f5655bdcce18cb652d54050235e555b7325074aa0f8bf737f7"},"schema_version":"1.0"},"canonical_sha256":"a5f8494dc708a8d5eed688106347bd5d1ff2f8e720b98ae3ce1208c07f3a7541","source":{"kind":"arxiv","id":"1505.06872","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1505.06872","created_at":"2026-05-18T02:03:27Z"},{"alias_kind":"arxiv_version","alias_value":"1505.06872v1","created_at":"2026-05-18T02:03:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.06872","created_at":"2026-05-18T02:03:27Z"},{"alias_kind":"pith_short_12","alias_value":"UX4ESTOHBCUN","created_at":"2026-05-18T12:29:44Z"},{"alias_kind":"pith_short_16","alias_value":"UX4ESTOHBCUNL3WW","created_at":"2026-05-18T12:29:44Z"},{"alias_kind":"pith_short_8","alias_value":"UX4ESTOH","created_at":"2026-05-18T12:29:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:UX4ESTOHBCUNL3WWRAIGGR55LU","target":"record","payload":{"canonical_record":{"source":{"id":"1505.06872","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2015-05-26T09:38:08Z","cross_cats_sorted":[],"title_canon_sha256":"e0c52ba0bed75be8c63e1c090d2e0c2a8928f6d41c3e5df7e1367547eed3c7ea","abstract_canon_sha256":"9bf762bd3824d0f5655bdcce18cb652d54050235e555b7325074aa0f8bf737f7"},"schema_version":"1.0"},"canonical_sha256":"a5f8494dc708a8d5eed688106347bd5d1ff2f8e720b98ae3ce1208c07f3a7541","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:03:27.697985Z","signature_b64":"348ahO32RCyHTXIkUCcvmPUj/QgO4szLpHvpjr1sKYUfIxTN/B5yzCPsaeZVhqzg7St75BeXermb5vfZnuyeCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5f8494dc708a8d5eed688106347bd5d1ff2f8e720b98ae3ce1208c07f3a7541","last_reissued_at":"2026-05-18T02:03:27.697525Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:03:27.697525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1505.06872","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":"2026-05-18T02:03:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O0vYlGX4Irovs/IYTHqFi77VaOW7zcKlcx2ME1B0/Yu78Z7EKNeHnmuFuFoYUndVduy8pBaJJ+zVpQ0UT+wRDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T06:31:30.826236Z"},"content_sha256":"002e7a6dc8a730adcde9c313426fd39d444eee96699de3e26ae3372ec2428103","schema_version":"1.0","event_id":"sha256:002e7a6dc8a730adcde9c313426fd39d444eee96699de3e26ae3372ec2428103"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:UX4ESTOHBCUNL3WWRAIGGR55LU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Identifying Dwarfs Workloads in Big Data Analytics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Chunjie Luo, Hainan Ye, Jianfeng Zhan, Lei Wang, Wanling Gao, Xinhui Tian, Xiwen He, Yuqing Zhu","submitted_at":"2015-05-26T09:38:08Z","abstract_excerpt":"Big data benchmarking is particularly important and provides applicable yardsticks for evaluating booming big data systems. However, wide coverage and great complexity of big data computing impose big challenges on big data benchmarking. How can we construct a benchmark suite using a minimum set of units of computation to represent diversity of big data analytics workloads? Big data dwarfs are abstractions of extracting frequently appearing operations in big data computing. One dwarf represents one unit of computation, and big data workloads are decomposed into one or more dwarfs. Furthermore,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.06872","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":"2026-05-18T02:03:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YZXlYaruUhn+KeUJ9KxAaV0+ueXTAXFcPBNjpHW4AdEmiXGHoQpUxMLjMntf0JpkGghHJz03DFPxr4OKCkVkAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T06:31:30.826926Z"},"content_sha256":"33948bfcd2fff0a885aa2e3a3f60a832680ea038780c2e41186ce552b24af074","schema_version":"1.0","event_id":"sha256:33948bfcd2fff0a885aa2e3a3f60a832680ea038780c2e41186ce552b24af074"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UX4ESTOHBCUNL3WWRAIGGR55LU/bundle.json","state_url":"https://pith.science/pith/UX4ESTOHBCUNL3WWRAIGGR55LU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UX4ESTOHBCUNL3WWRAIGGR55LU/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":"2026-05-27T06:31:30Z","links":{"resolver":"https://pith.science/pith/UX4ESTOHBCUNL3WWRAIGGR55LU","bundle":"https://pith.science/pith/UX4ESTOHBCUNL3WWRAIGGR55LU/bundle.json","state":"https://pith.science/pith/UX4ESTOHBCUNL3WWRAIGGR55LU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UX4ESTOHBCUNL3WWRAIGGR55LU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:UX4ESTOHBCUNL3WWRAIGGR55LU","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":"9bf762bd3824d0f5655bdcce18cb652d54050235e555b7325074aa0f8bf737f7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2015-05-26T09:38:08Z","title_canon_sha256":"e0c52ba0bed75be8c63e1c090d2e0c2a8928f6d41c3e5df7e1367547eed3c7ea"},"schema_version":"1.0","source":{"id":"1505.06872","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1505.06872","created_at":"2026-05-18T02:03:27Z"},{"alias_kind":"arxiv_version","alias_value":"1505.06872v1","created_at":"2026-05-18T02:03:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.06872","created_at":"2026-05-18T02:03:27Z"},{"alias_kind":"pith_short_12","alias_value":"UX4ESTOHBCUN","created_at":"2026-05-18T12:29:44Z"},{"alias_kind":"pith_short_16","alias_value":"UX4ESTOHBCUNL3WW","created_at":"2026-05-18T12:29:44Z"},{"alias_kind":"pith_short_8","alias_value":"UX4ESTOH","created_at":"2026-05-18T12:29:44Z"}],"graph_snapshots":[{"event_id":"sha256:33948bfcd2fff0a885aa2e3a3f60a832680ea038780c2e41186ce552b24af074","target":"graph","created_at":"2026-05-18T02:03:27Z","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":"Big data benchmarking is particularly important and provides applicable yardsticks for evaluating booming big data systems. However, wide coverage and great complexity of big data computing impose big challenges on big data benchmarking. How can we construct a benchmark suite using a minimum set of units of computation to represent diversity of big data analytics workloads? Big data dwarfs are abstractions of extracting frequently appearing operations in big data computing. One dwarf represents one unit of computation, and big data workloads are decomposed into one or more dwarfs. Furthermore,","authors_text":"Chunjie Luo, Hainan Ye, Jianfeng Zhan, Lei Wang, Wanling Gao, Xinhui Tian, Xiwen He, Yuqing Zhu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2015-05-26T09:38:08Z","title":"Identifying Dwarfs Workloads in Big Data Analytics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.06872","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":"sha256:002e7a6dc8a730adcde9c313426fd39d444eee96699de3e26ae3372ec2428103","target":"record","created_at":"2026-05-18T02:03:27Z","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":"9bf762bd3824d0f5655bdcce18cb652d54050235e555b7325074aa0f8bf737f7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2015-05-26T09:38:08Z","title_canon_sha256":"e0c52ba0bed75be8c63e1c090d2e0c2a8928f6d41c3e5df7e1367547eed3c7ea"},"schema_version":"1.0","source":{"id":"1505.06872","kind":"arxiv","version":1}},"canonical_sha256":"a5f8494dc708a8d5eed688106347bd5d1ff2f8e720b98ae3ce1208c07f3a7541","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a5f8494dc708a8d5eed688106347bd5d1ff2f8e720b98ae3ce1208c07f3a7541","first_computed_at":"2026-05-18T02:03:27.697525Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:03:27.697525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"348ahO32RCyHTXIkUCcvmPUj/QgO4szLpHvpjr1sKYUfIxTN/B5yzCPsaeZVhqzg7St75BeXermb5vfZnuyeCg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:03:27.697985Z","signed_message":"canonical_sha256_bytes"},"source_id":"1505.06872","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:002e7a6dc8a730adcde9c313426fd39d444eee96699de3e26ae3372ec2428103","sha256:33948bfcd2fff0a885aa2e3a3f60a832680ea038780c2e41186ce552b24af074"],"state_sha256":"6842db6368d0390d0b5dbf304a6517e217ad65cb82630aa701d83fae203f8e57"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J7K3UJBGnDHPZ8LAETqrIMAKahuQrGkhKo1VKTmcZqcQrw5EmE9bSuY1OgsShNOagKL3wFs1+VWH/WsgBFjsCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T06:31:30.830650Z","bundle_sha256":"7fbe30877cba31d3b917d2e809d95fc02d4bd8bcfec15d635dd14c2a0a5eae41"}}