{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KBKUF5NMBB6WT5QTSEQ6FE7Z6P","short_pith_number":"pith:KBKUF5NM","schema_version":"1.0","canonical_sha256":"505542f5ac087d69f6139121e293f9f3d6b6e46736cdc7b6b3f9eb8be5ac1e6d","source":{"kind":"arxiv","id":"2504.16397","version":2},"attestation_state":"computed","paper":{"title":"Compass: SLO-aware Query Planner for Compound AI Serving at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Banruo Liu, Fan Lai, Minghao Fang, Wei-Yu Lin, Yihan Jiang","submitted_at":"2025-04-23T03:57:24Z","abstract_excerpt":"The rise of compound AI serving that integrates multiple operators in a pipeline enables end-user applications such as generative AI-powered meeting companions, autonomous driving, and immersive gaming. These workloads span diverse deployment spaces, from cloud-only queries to edge-assisted ones across infrastructure tiers, often including both within an application. Achieving high service goodput -- i.e., meeting service level objectives (SLOs) for pipeline latency, accuracy, and costs -- requires joint planning of operators' placement, configuration, and resource allocation. However, diverse"},"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":"2504.16397","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-04-23T03:57:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8759a1b874db834b504db7c45e5e5a785f2a1212fc084568f5fab4bfe511d853","abstract_canon_sha256":"7538770fa2370a86716cfff71dc4cbb9f14f138da92e23d5acee7b5420047f86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:08.725493Z","signature_b64":"P4o4WBpsal/8nhR+8fChhKwY4xt0txBZ67mARHdchac9D6iz/Bol3rDAJmxPti/NCOo0FGA7LwFioRzUdnDICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"505542f5ac087d69f6139121e293f9f3d6b6e46736cdc7b6b3f9eb8be5ac1e6d","last_reissued_at":"2026-05-20T00:04:08.724715Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:08.724715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compass: SLO-aware Query Planner for Compound AI Serving at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Banruo Liu, Fan Lai, Minghao Fang, Wei-Yu Lin, Yihan Jiang","submitted_at":"2025-04-23T03:57:24Z","abstract_excerpt":"The rise of compound AI serving that integrates multiple operators in a pipeline enables end-user applications such as generative AI-powered meeting companions, autonomous driving, and immersive gaming. These workloads span diverse deployment spaces, from cloud-only queries to edge-assisted ones across infrastructure tiers, often including both within an application. Achieving high service goodput -- i.e., meeting service level objectives (SLOs) for pipeline latency, accuracy, and costs -- requires joint planning of operators' placement, configuration, and resource allocation. However, diverse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16397","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.16397/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":"2504.16397","created_at":"2026-05-20T00:04:08.724845+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.16397v2","created_at":"2026-05-20T00:04:08.724845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16397","created_at":"2026-05-20T00:04:08.724845+00:00"},{"alias_kind":"pith_short_12","alias_value":"KBKUF5NMBB6W","created_at":"2026-05-20T00:04:08.724845+00:00"},{"alias_kind":"pith_short_16","alias_value":"KBKUF5NMBB6WT5QT","created_at":"2026-05-20T00:04:08.724845+00:00"},{"alias_kind":"pith_short_8","alias_value":"KBKUF5NM","created_at":"2026-05-20T00:04:08.724845+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.06370","citing_title":"ForkKV: Scaling Multi-LoRA Agent Serving via Copy-on-Write Disaggregated KV Cache","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KBKUF5NMBB6WT5QTSEQ6FE7Z6P","json":"https://pith.science/pith/KBKUF5NMBB6WT5QTSEQ6FE7Z6P.json","graph_json":"https://pith.science/api/pith-number/KBKUF5NMBB6WT5QTSEQ6FE7Z6P/graph.json","events_json":"https://pith.science/api/pith-number/KBKUF5NMBB6WT5QTSEQ6FE7Z6P/events.json","paper":"https://pith.science/paper/KBKUF5NM"},"agent_actions":{"view_html":"https://pith.science/pith/KBKUF5NMBB6WT5QTSEQ6FE7Z6P","download_json":"https://pith.science/pith/KBKUF5NMBB6WT5QTSEQ6FE7Z6P.json","view_paper":"https://pith.science/paper/KBKUF5NM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.16397&json=true","fetch_graph":"https://pith.science/api/pith-number/KBKUF5NMBB6WT5QTSEQ6FE7Z6P/graph.json","fetch_events":"https://pith.science/api/pith-number/KBKUF5NMBB6WT5QTSEQ6FE7Z6P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KBKUF5NMBB6WT5QTSEQ6FE7Z6P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KBKUF5NMBB6WT5QTSEQ6FE7Z6P/action/storage_attestation","attest_author":"https://pith.science/pith/KBKUF5NMBB6WT5QTSEQ6FE7Z6P/action/author_attestation","sign_citation":"https://pith.science/pith/KBKUF5NMBB6WT5QTSEQ6FE7Z6P/action/citation_signature","submit_replication":"https://pith.science/pith/KBKUF5NMBB6WT5QTSEQ6FE7Z6P/action/replication_record"}},"created_at":"2026-05-20T00:04:08.724845+00:00","updated_at":"2026-05-20T00:04:08.724845+00:00"}