{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OK4TXZ24VNXLMXK6DW2GXJXCK5","short_pith_number":"pith:OK4TXZ24","canonical_record":{"source":{"id":"2501.14456","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-01-24T12:38:25Z","cross_cats_sorted":[],"title_canon_sha256":"aeaaca0f59c64fe8d4d2f62159e6df9d43a6f5189add512dd4c1256f7cef921a","abstract_canon_sha256":"d67cab746162d4b1fecbb3702a1f34a50c031dbc4ed52b6eebcab0a337feb74f"},"schema_version":"1.0"},"canonical_sha256":"72b93be75cab6eb65d5e1db46ba6e2577a9c302646ed9ab32850968c0b8482ce","source":{"kind":"arxiv","id":"2501.14456","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14456","created_at":"2026-07-05T10:05:01Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14456v1","created_at":"2026-07-05T10:05:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14456","created_at":"2026-07-05T10:05:01Z"},{"alias_kind":"pith_short_12","alias_value":"OK4TXZ24VNXL","created_at":"2026-07-05T10:05:01Z"},{"alias_kind":"pith_short_16","alias_value":"OK4TXZ24VNXLMXK6","created_at":"2026-07-05T10:05:01Z"},{"alias_kind":"pith_short_8","alias_value":"OK4TXZ24","created_at":"2026-07-05T10:05:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OK4TXZ24VNXLMXK6DW2GXJXCK5","target":"record","payload":{"canonical_record":{"source":{"id":"2501.14456","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-01-24T12:38:25Z","cross_cats_sorted":[],"title_canon_sha256":"aeaaca0f59c64fe8d4d2f62159e6df9d43a6f5189add512dd4c1256f7cef921a","abstract_canon_sha256":"d67cab746162d4b1fecbb3702a1f34a50c031dbc4ed52b6eebcab0a337feb74f"},"schema_version":"1.0"},"canonical_sha256":"72b93be75cab6eb65d5e1db46ba6e2577a9c302646ed9ab32850968c0b8482ce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:01.072078Z","signature_b64":"+N+mZR0nVjR479HUtEZbUkd35ByuiHxsVIfHhdUJGguea6lpn9CMOi1DJ9TRQi67TqoebUNKa7dQLV58MKkGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72b93be75cab6eb65d5e1db46ba6e2577a9c302646ed9ab32850968c0b8482ce","last_reissued_at":"2026-07-05T10:05:01.071632Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:01.071632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.14456","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":"2026-07-05T10:05:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SPsSulJjFfQAcXrFbpnaN1OAGhma/GbdcgI/n3M8etp8j06d5Y4FiXdYXTjyv8sDg+SsLfqxMDPSsyM5oMHZAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T04:23:56.585896Z"},"content_sha256":"5ff63caf20197aebabdc5162b18c863fc01d0b20519fd67f6e3a1dda64464a5a","schema_version":"1.0","event_id":"sha256:5ff63caf20197aebabdc5162b18c863fc01d0b20519fd67f6e3a1dda64464a5a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OK4TXZ24VNXLMXK6DW2GXJXCK5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Experimentally Evaluating the Resource Efficiency of Big Data Autoscaling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Jonathan Will, Lauritz Thamsen, Nico Treide, Odej Kao","submitted_at":"2025-01-24T12:38:25Z","abstract_excerpt":"Distributed dataflow systems like Spark and Flink enable data-parallel processing of large datasets on clusters. Yet, selecting appropriate computational resources for dataflow jobs is often challenging. For efficient execution, individual resource allocations, such as memory and CPU cores, must meet the specific resource requirements of the job. An alternative to selecting a static resource allocation for a job execution is autoscaling as implemented for example by Spark.\n  In this paper, we evaluate the resource efficiency of autoscaling batch data processing jobs based on resource demand bo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14456","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.14456/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T10:05:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MMUcl0bJNPynC78I2s9EMlBEE65J8/AIPZLN5rYeDIkpCOaF1jLpBOkhjAHcM+MfLo7PWh9kthC3HGq70i4ZAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T04:23:56.586488Z"},"content_sha256":"2c6cdf5e6eef65dccb739ef34f6d7a8ca7f088d8fb7c26040f0f7f7d61394466","schema_version":"1.0","event_id":"sha256:2c6cdf5e6eef65dccb739ef34f6d7a8ca7f088d8fb7c26040f0f7f7d61394466"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OK4TXZ24VNXLMXK6DW2GXJXCK5/bundle.json","state_url":"https://pith.science/pith/OK4TXZ24VNXLMXK6DW2GXJXCK5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OK4TXZ24VNXLMXK6DW2GXJXCK5/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":"2026-08-24T04:23:56Z","links":{"resolver":"https://pith.science/pith/OK4TXZ24VNXLMXK6DW2GXJXCK5","bundle":"https://pith.science/pith/OK4TXZ24VNXLMXK6DW2GXJXCK5/bundle.json","state":"https://pith.science/pith/OK4TXZ24VNXLMXK6DW2GXJXCK5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OK4TXZ24VNXLMXK6DW2GXJXCK5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OK4TXZ24VNXLMXK6DW2GXJXCK5","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":"d67cab746162d4b1fecbb3702a1f34a50c031dbc4ed52b6eebcab0a337feb74f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-01-24T12:38:25Z","title_canon_sha256":"aeaaca0f59c64fe8d4d2f62159e6df9d43a6f5189add512dd4c1256f7cef921a"},"schema_version":"1.0","source":{"id":"2501.14456","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14456","created_at":"2026-07-05T10:05:01Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14456v1","created_at":"2026-07-05T10:05:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14456","created_at":"2026-07-05T10:05:01Z"},{"alias_kind":"pith_short_12","alias_value":"OK4TXZ24VNXL","created_at":"2026-07-05T10:05:01Z"},{"alias_kind":"pith_short_16","alias_value":"OK4TXZ24VNXLMXK6","created_at":"2026-07-05T10:05:01Z"},{"alias_kind":"pith_short_8","alias_value":"OK4TXZ24","created_at":"2026-07-05T10:05:01Z"}],"graph_snapshots":[{"event_id":"sha256:2c6cdf5e6eef65dccb739ef34f6d7a8ca7f088d8fb7c26040f0f7f7d61394466","target":"graph","created_at":"2026-07-05T10:05:01Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.14456/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Distributed dataflow systems like Spark and Flink enable data-parallel processing of large datasets on clusters. Yet, selecting appropriate computational resources for dataflow jobs is often challenging. For efficient execution, individual resource allocations, such as memory and CPU cores, must meet the specific resource requirements of the job. An alternative to selecting a static resource allocation for a job execution is autoscaling as implemented for example by Spark.\n  In this paper, we evaluate the resource efficiency of autoscaling batch data processing jobs based on resource demand bo","authors_text":"Jonathan Will, Lauritz Thamsen, Nico Treide, Odej Kao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-01-24T12:38:25Z","title":"Experimentally Evaluating the Resource Efficiency of Big Data Autoscaling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14456","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":"sha256:5ff63caf20197aebabdc5162b18c863fc01d0b20519fd67f6e3a1dda64464a5a","target":"record","created_at":"2026-07-05T10:05:01Z","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":"d67cab746162d4b1fecbb3702a1f34a50c031dbc4ed52b6eebcab0a337feb74f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-01-24T12:38:25Z","title_canon_sha256":"aeaaca0f59c64fe8d4d2f62159e6df9d43a6f5189add512dd4c1256f7cef921a"},"schema_version":"1.0","source":{"id":"2501.14456","kind":"arxiv","version":1}},"canonical_sha256":"72b93be75cab6eb65d5e1db46ba6e2577a9c302646ed9ab32850968c0b8482ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72b93be75cab6eb65d5e1db46ba6e2577a9c302646ed9ab32850968c0b8482ce","first_computed_at":"2026-07-05T10:05:01.071632Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:01.071632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+N+mZR0nVjR479HUtEZbUkd35ByuiHxsVIfHhdUJGguea6lpn9CMOi1DJ9TRQi67TqoebUNKa7dQLV58MKkGBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:01.072078Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.14456","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ff63caf20197aebabdc5162b18c863fc01d0b20519fd67f6e3a1dda64464a5a","sha256:2c6cdf5e6eef65dccb739ef34f6d7a8ca7f088d8fb7c26040f0f7f7d61394466"],"state_sha256":"02c50b0d08c0cb5a2c3ce39b021fa05e612f033091fbd8cc4f1f52da0e474fe5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1dH8c8XryNpP3vDMfceBRRuTe8i7O9YH3FQpdZqS8t5F1BL1bV2KkljLYL+GW8OKiTMaYl40bzuGtJ7LyJOeBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-24T04:23:56.590103Z","bundle_sha256":"30fa4da58bafb31ebc227ff2601a8515231bb4a06c9d4585edefc2c43658f99c"}}