{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IBXH3FIAXATLHNZQTDFEHK6FOP","short_pith_number":"pith:IBXH3FIA","schema_version":"1.0","canonical_sha256":"406e7d9500b826b3b73098ca43abc573c6a12cb1e770cd000b554ded94977137","source":{"kind":"arxiv","id":"2508.18298","version":2},"attestation_state":"computed","paper":{"title":"Murakkab: Resource-Efficient Agentic Workflow Orchestration in Cloud Platforms","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.MA","authors_text":"Adam Belay, Esha Choukse, Gohar Irfan Chaudhry, Haoran Qiu, \\'I\\~nigo Goiri, Ricardo Bianchini, Rodrigo Fonseca","submitted_at":"2025-08-22T17:41:27Z","abstract_excerpt":"Agentic workflows commonly coordinate multiple models and tools with complex control logic. They are quickly becoming the dominant paradigm for AI applications. However, serving them remains inefficient with today's frameworks. The key problem is that they expose workflows as opaque sequences of model and tool calls that tightly couple agent logic with model and hardware choices. Often, these workflow components are fragmented across different entities, preventing systems from reasoning about trade-offs across accuracy, latency, energy, and cost. This leads to resource waste and degraded servi"},"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":"2508.18298","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2025-08-22T17:41:27Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"cb212bf6dbfce3ddd93ca2ea0d4de683b1b796c05c00adcef7e461ee4ffdbdba","abstract_canon_sha256":"c48b71d255a8462ec6666bbc721473eedfdcecc65dbae65ee5d4751ef8469515"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:17.229301Z","signature_b64":"TcEewDCW0c454S9y8NrBP9PrpLnlR99kLdnKlXITyyfotZPy626okP+ufynsDLkJqz+s3LUbWZAD/NNlV977Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"406e7d9500b826b3b73098ca43abc573c6a12cb1e770cd000b554ded94977137","last_reissued_at":"2026-07-05T12:04:17.228759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:17.228759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Murakkab: Resource-Efficient Agentic Workflow Orchestration in Cloud Platforms","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.MA","authors_text":"Adam Belay, Esha Choukse, Gohar Irfan Chaudhry, Haoran Qiu, \\'I\\~nigo Goiri, Ricardo Bianchini, Rodrigo Fonseca","submitted_at":"2025-08-22T17:41:27Z","abstract_excerpt":"Agentic workflows commonly coordinate multiple models and tools with complex control logic. They are quickly becoming the dominant paradigm for AI applications. However, serving them remains inefficient with today's frameworks. The key problem is that they expose workflows as opaque sequences of model and tool calls that tightly couple agent logic with model and hardware choices. Often, these workflow components are fragmented across different entities, preventing systems from reasoning about trade-offs across accuracy, latency, energy, and cost. This leads to resource waste and degraded servi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18298","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/2508.18298/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":"2508.18298","created_at":"2026-07-05T12:04:17.228815+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.18298v2","created_at":"2026-07-05T12:04:17.228815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18298","created_at":"2026-07-05T12:04:17.228815+00:00"},{"alias_kind":"pith_short_12","alias_value":"IBXH3FIAXATL","created_at":"2026-07-05T12:04:17.228815+00:00"},{"alias_kind":"pith_short_16","alias_value":"IBXH3FIAXATLHNZQ","created_at":"2026-07-05T12:04:17.228815+00:00"},{"alias_kind":"pith_short_8","alias_value":"IBXH3FIA","created_at":"2026-07-05T12:04:17.228815+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21401","citing_title":"SwarmX: Agentic Scheduling for Low-Latency Agentic Systems","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06820","citing_title":"SCALE: Scalable Cross-Attention Learning with Extrapolation for Agentic Workflow Scheduling","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21401","citing_title":"SwarmX: Agentic Scheduling for Low-Latency Agentic Systems","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27361","citing_title":"Natural Language Query to Configuration for Retrieval Agents","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09593","citing_title":"Benchmarking Compound AI Applications for Hardware-Software Co-Design","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09611","citing_title":"Characterizing Performance-Energy Trade-offs of Large Language Models in Multi-Request Workflows","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06370","citing_title":"ForkKV: Scaling Multi-LoRA Agent Serving via Copy-on-Write Disaggregated KV Cache","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07238","citing_title":"FATE: Future-State-Aware Scheduling for Heterogeneous LLM Workflows","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IBXH3FIAXATLHNZQTDFEHK6FOP","json":"https://pith.science/pith/IBXH3FIAXATLHNZQTDFEHK6FOP.json","graph_json":"https://pith.science/api/pith-number/IBXH3FIAXATLHNZQTDFEHK6FOP/graph.json","events_json":"https://pith.science/api/pith-number/IBXH3FIAXATLHNZQTDFEHK6FOP/events.json","paper":"https://pith.science/paper/IBXH3FIA"},"agent_actions":{"view_html":"https://pith.science/pith/IBXH3FIAXATLHNZQTDFEHK6FOP","download_json":"https://pith.science/pith/IBXH3FIAXATLHNZQTDFEHK6FOP.json","view_paper":"https://pith.science/paper/IBXH3FIA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.18298&json=true","fetch_graph":"https://pith.science/api/pith-number/IBXH3FIAXATLHNZQTDFEHK6FOP/graph.json","fetch_events":"https://pith.science/api/pith-number/IBXH3FIAXATLHNZQTDFEHK6FOP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IBXH3FIAXATLHNZQTDFEHK6FOP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IBXH3FIAXATLHNZQTDFEHK6FOP/action/storage_attestation","attest_author":"https://pith.science/pith/IBXH3FIAXATLHNZQTDFEHK6FOP/action/author_attestation","sign_citation":"https://pith.science/pith/IBXH3FIAXATLHNZQTDFEHK6FOP/action/citation_signature","submit_replication":"https://pith.science/pith/IBXH3FIAXATLHNZQTDFEHK6FOP/action/replication_record"}},"created_at":"2026-07-05T12:04:17.228815+00:00","updated_at":"2026-07-05T12:04:17.228815+00:00"}