{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IUVM4I5VBGC52AHPV4RSJAVXKY","short_pith_number":"pith:IUVM4I5V","schema_version":"1.0","canonical_sha256":"452ace23b50985dd00efaf232482b7560ee34afd09a91c020466b68a205f66ee","source":{"kind":"arxiv","id":"2507.19635","version":1},"attestation_state":"computed","paper":{"title":"Efficient and Scalable Agentic AI with Heterogeneous Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Michelle Nguyen, Sachin Katti, Zain Asgar","submitted_at":"2025-07-25T19:02:42Z","abstract_excerpt":"AI agents are emerging as a dominant workload in a wide range of applications, promising to be the vehicle that delivers the promised benefits of AI to enterprises and consumers. Unlike conventional software or static inference, agentic workloads are dynamic and structurally complex. Often these agents are directed graphs of compute and IO operations that span multi-modal data input and conversion), data processing and context gathering (e.g vector DB lookups), multiple LLM inferences, tool calls, etc. To scale AI agent usage, we need efficient and scalable deployment and agent-serving infrast"},"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":"2507.19635","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-25T19:02:42Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"c89e5801539966713d03ea1aa59c727f97f3db5084a04c6893b379cd0aace40e","abstract_canon_sha256":"010b52cb16be626e4ebc88e08c6e4077a261b36285cd5d7e0d94387eb3a7fd99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:38.047761Z","signature_b64":"Fo2nrAymQeqpEWE1gm+hcAFz1ABzmlicap1O6sU9paWp5QUCzuadBPREe6OvhMVs37mjscd/jVw41f7xyzn9Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"452ace23b50985dd00efaf232482b7560ee34afd09a91c020466b68a205f66ee","last_reissued_at":"2026-07-05T11:43:38.047200Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:38.047200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient and Scalable Agentic AI with Heterogeneous Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Michelle Nguyen, Sachin Katti, Zain Asgar","submitted_at":"2025-07-25T19:02:42Z","abstract_excerpt":"AI agents are emerging as a dominant workload in a wide range of applications, promising to be the vehicle that delivers the promised benefits of AI to enterprises and consumers. Unlike conventional software or static inference, agentic workloads are dynamic and structurally complex. Often these agents are directed graphs of compute and IO operations that span multi-modal data input and conversion), data processing and context gathering (e.g vector DB lookups), multiple LLM inferences, tool calls, etc. To scale AI agent usage, we need efficient and scalable deployment and agent-serving infrast"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19635","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/2507.19635/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":"2507.19635","created_at":"2026-07-05T11:43:38.047265+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.19635v1","created_at":"2026-07-05T11:43:38.047265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19635","created_at":"2026-07-05T11:43:38.047265+00:00"},{"alias_kind":"pith_short_12","alias_value":"IUVM4I5VBGC5","created_at":"2026-07-05T11:43:38.047265+00:00"},{"alias_kind":"pith_short_16","alias_value":"IUVM4I5VBGC52AHP","created_at":"2026-07-05T11:43:38.047265+00:00"},{"alias_kind":"pith_short_8","alias_value":"IUVM4I5V","created_at":"2026-07-05T11:43:38.047265+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18502","citing_title":"Towards Scalable Customization and Deployment of Multi-Agent Systems for Enterprise Applications","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12835","citing_title":"The Internet of Agentic AI: Communication, Coordination, and Collective Intelligence at Scale","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02963","citing_title":"KForge: LLM-Driven Cross-Platform Kernel Generation for AI Accelerators","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26297","citing_title":"Agentic AI Workload Characteristics","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16867","citing_title":"GoodServe: Towards High-Goodput Serving of Agentic LLM Inferences over Heterogeneous Resources","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2511.00739","citing_title":"Towards Understanding, Analyzing, and Optimizing Agentic AI Execution: A CPU-Centric Perspective","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16682","citing_title":"KAIROS: Stateful, Context-Aware Power-Efficient Agentic Inference Serving","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IUVM4I5VBGC52AHPV4RSJAVXKY","json":"https://pith.science/pith/IUVM4I5VBGC52AHPV4RSJAVXKY.json","graph_json":"https://pith.science/api/pith-number/IUVM4I5VBGC52AHPV4RSJAVXKY/graph.json","events_json":"https://pith.science/api/pith-number/IUVM4I5VBGC52AHPV4RSJAVXKY/events.json","paper":"https://pith.science/paper/IUVM4I5V"},"agent_actions":{"view_html":"https://pith.science/pith/IUVM4I5VBGC52AHPV4RSJAVXKY","download_json":"https://pith.science/pith/IUVM4I5VBGC52AHPV4RSJAVXKY.json","view_paper":"https://pith.science/paper/IUVM4I5V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.19635&json=true","fetch_graph":"https://pith.science/api/pith-number/IUVM4I5VBGC52AHPV4RSJAVXKY/graph.json","fetch_events":"https://pith.science/api/pith-number/IUVM4I5VBGC52AHPV4RSJAVXKY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IUVM4I5VBGC52AHPV4RSJAVXKY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IUVM4I5VBGC52AHPV4RSJAVXKY/action/storage_attestation","attest_author":"https://pith.science/pith/IUVM4I5VBGC52AHPV4RSJAVXKY/action/author_attestation","sign_citation":"https://pith.science/pith/IUVM4I5VBGC52AHPV4RSJAVXKY/action/citation_signature","submit_replication":"https://pith.science/pith/IUVM4I5VBGC52AHPV4RSJAVXKY/action/replication_record"}},"created_at":"2026-07-05T11:43:38.047265+00:00","updated_at":"2026-07-05T11:43:38.047265+00:00"}