{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BGY5TZN5JSNLSWQTHLMTDLMZW7","short_pith_number":"pith:BGY5TZN5","schema_version":"1.0","canonical_sha256":"09b1d9e5bd4c9ab95a133ad931ad99b7d776685c0699bd7d9b1caf8eae729421","source":{"kind":"arxiv","id":"2606.03364","version":1},"attestation_state":"computed","paper":{"title":"BlobShuffle: Cost-Effective Repartitioning in Stream Processing Systems via Object Storage Exemplified with Kafka Streams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.PF","cs.SE"],"primary_cat":"cs.DC","authors_text":"Adriano Vogel, Otmar Ertl, S\\\"oren Henning","submitted_at":"2026-06-02T09:13:48Z","abstract_excerpt":"Shuffling or repartitioning data streams is an essential operation of state-of-the-art stream processing frameworks to support stateful workloads in a large-scale, distributed setting. In today's cloud deployments, however, shuffling can become a major cost driver due to substantial network traffic across multiple availability zones (AZs) as well as an operational burden when operating a high-throughput, strongly consistent messaging backbone at scale. We present BlobShuffle, a novel approach to cost-effective shuffling for stream processing systems that leverages cloud object storage as an in"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.03364","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-06-02T09:13:48Z","cross_cats_sorted":["cs.DB","cs.PF","cs.SE"],"title_canon_sha256":"2e900b5191b11b301c76482d14d4d8a63b4672f05a4aaf25acd49dcaa771b535","abstract_canon_sha256":"dc4c9133571fd82c08ae33ac9bec25c81d6497e2caaa44053722f6e5746af232"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:56.015095Z","signature_b64":"iUmkQc2fWUnzOskfH32JIgrTQXdRLNkLq2TsVmADeZCJQB3Ia5lZk2vN5izf4ZIyq6XPuzjfxf/pPnk22CuEDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09b1d9e5bd4c9ab95a133ad931ad99b7d776685c0699bd7d9b1caf8eae729421","last_reissued_at":"2026-06-03T01:05:56.014749Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:56.014749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BlobShuffle: Cost-Effective Repartitioning in Stream Processing Systems via Object Storage Exemplified with Kafka Streams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.PF","cs.SE"],"primary_cat":"cs.DC","authors_text":"Adriano Vogel, Otmar Ertl, S\\\"oren Henning","submitted_at":"2026-06-02T09:13:48Z","abstract_excerpt":"Shuffling or repartitioning data streams is an essential operation of state-of-the-art stream processing frameworks to support stateful workloads in a large-scale, distributed setting. In today's cloud deployments, however, shuffling can become a major cost driver due to substantial network traffic across multiple availability zones (AZs) as well as an operational burden when operating a high-throughput, strongly consistent messaging backbone at scale. We present BlobShuffle, a novel approach to cost-effective shuffling for stream processing systems that leverages cloud object storage as an in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03364","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/2606.03364/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.03364","created_at":"2026-06-03T01:05:56.014811+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03364v1","created_at":"2026-06-03T01:05:56.014811+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03364","created_at":"2026-06-03T01:05:56.014811+00:00"},{"alias_kind":"pith_short_12","alias_value":"BGY5TZN5JSNL","created_at":"2026-06-03T01:05:56.014811+00:00"},{"alias_kind":"pith_short_16","alias_value":"BGY5TZN5JSNLSWQT","created_at":"2026-06-03T01:05:56.014811+00:00"},{"alias_kind":"pith_short_8","alias_value":"BGY5TZN5","created_at":"2026-06-03T01:05:56.014811+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BGY5TZN5JSNLSWQTHLMTDLMZW7","json":"https://pith.science/pith/BGY5TZN5JSNLSWQTHLMTDLMZW7.json","graph_json":"https://pith.science/api/pith-number/BGY5TZN5JSNLSWQTHLMTDLMZW7/graph.json","events_json":"https://pith.science/api/pith-number/BGY5TZN5JSNLSWQTHLMTDLMZW7/events.json","paper":"https://pith.science/paper/BGY5TZN5"},"agent_actions":{"view_html":"https://pith.science/pith/BGY5TZN5JSNLSWQTHLMTDLMZW7","download_json":"https://pith.science/pith/BGY5TZN5JSNLSWQTHLMTDLMZW7.json","view_paper":"https://pith.science/paper/BGY5TZN5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03364&json=true","fetch_graph":"https://pith.science/api/pith-number/BGY5TZN5JSNLSWQTHLMTDLMZW7/graph.json","fetch_events":"https://pith.science/api/pith-number/BGY5TZN5JSNLSWQTHLMTDLMZW7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BGY5TZN5JSNLSWQTHLMTDLMZW7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BGY5TZN5JSNLSWQTHLMTDLMZW7/action/storage_attestation","attest_author":"https://pith.science/pith/BGY5TZN5JSNLSWQTHLMTDLMZW7/action/author_attestation","sign_citation":"https://pith.science/pith/BGY5TZN5JSNLSWQTHLMTDLMZW7/action/citation_signature","submit_replication":"https://pith.science/pith/BGY5TZN5JSNLSWQTHLMTDLMZW7/action/replication_record"}},"created_at":"2026-06-03T01:05:56.014811+00:00","updated_at":"2026-06-03T01:05:56.014811+00:00"}