{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YIVXF3SSHDGN7CZTUCFFY5VA6C","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":"9188f093fccf960061c0cf28e049258b842c3c0ddd377ecfe03ffebded7abf00","cross_cats_sorted":["cs.AI","cs.MA","cs.OS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2025-05-01T18:58:26Z","title_canon_sha256":"1add72d890e3d0a431e7a9c3b26c2ce05a6416b31a5549add8c6dd35d8f763ce"},"schema_version":"1.0","source":{"id":"2505.07833","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07833","created_at":"2026-06-09T00:04:41Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07833v2","created_at":"2026-06-09T00:04:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07833","created_at":"2026-06-09T00:04:41Z"},{"alias_kind":"pith_short_12","alias_value":"YIVXF3SSHDGN","created_at":"2026-06-09T00:04:41Z"},{"alias_kind":"pith_short_16","alias_value":"YIVXF3SSHDGN7CZT","created_at":"2026-06-09T00:04:41Z"},{"alias_kind":"pith_short_8","alias_value":"YIVXF3SS","created_at":"2026-06-09T00:04:41Z"}],"graph_snapshots":[{"event_id":"sha256:4d2950dd16de4eae58d0fb7fa2daec701bef11883d775358c091d0c839f39e08","target":"graph","created_at":"2026-06-09T00:04:41Z","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/2505.07833/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-Augmented Generation (RAG) improves the reliability of large language models by integrating external knowledge, but serving RAG pipelines efficiently is challenging because requests traverse heterogeneous components spanning LLM inference, databases, and CPU-side processing. We present Harmonia, an end-to-end RAG serving framework that addresses these bottlenecks through (i) a flexible pipeline specification interface for composing custom workflows, (ii) heterogeneity-aware deployment that provisions and configures components as a distributed inference system, and (iii) a closed-loop","authors_text":"Aditya Akella, Bodun Hu, Jayanth Srinivasa, Luis Pabon, Myungjin Lee, Saurabh Agarwal","cross_cats":["cs.AI","cs.MA","cs.OS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2025-05-01T18:58:26Z","title":"Harmonia: End-to-End RAG Serving Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07833","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":"sha256:74a553a300fba04e7505b7a36da7ab16cf4b8ff87abe99c5f438ae8c9404a434","target":"record","created_at":"2026-06-09T00:04:41Z","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":"9188f093fccf960061c0cf28e049258b842c3c0ddd377ecfe03ffebded7abf00","cross_cats_sorted":["cs.AI","cs.MA","cs.OS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2025-05-01T18:58:26Z","title_canon_sha256":"1add72d890e3d0a431e7a9c3b26c2ce05a6416b31a5549add8c6dd35d8f763ce"},"schema_version":"1.0","source":{"id":"2505.07833","kind":"arxiv","version":2}},"canonical_sha256":"c22b72ee5238ccdf8b33a08a5c76a0f0a882e0549869feb582eecdc8bbc234fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c22b72ee5238ccdf8b33a08a5c76a0f0a882e0549869feb582eecdc8bbc234fd","first_computed_at":"2026-06-09T00:04:41.011360Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T00:04:41.011360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ww78HbglUHXMSjUhgLhUu+9GE74KbxMQEsfM67PIghh9sHmtOvOEGw86YbKXxiQMjPMmi4gFkUpsgTmkwXOTBg==","signature_status":"signed_v1","signed_at":"2026-06-09T00:04:41.013015Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.07833","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74a553a300fba04e7505b7a36da7ab16cf4b8ff87abe99c5f438ae8c9404a434","sha256:4d2950dd16de4eae58d0fb7fa2daec701bef11883d775358c091d0c839f39e08"],"state_sha256":"6e36f4d97685271a05a0c2e862d285741f4a040967e9322700d28950da1e83a8"}