{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DBAT6AOZDQX6PIZCHTQXA25LKE","short_pith_number":"pith:DBAT6AOZ","schema_version":"1.0","canonical_sha256":"18413f01d91c2fe7a3223ce1706bab5136c9c0203440b9db58b89646ef926f72","source":{"kind":"arxiv","id":"2507.00491","version":1},"attestation_state":"computed","paper":{"title":"Twill: Scheduling Compound AI Systems on Heterogeneous Mobile Edge Platforms","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.PF"],"primary_cat":"cs.MA","authors_text":"Aman Vyas, Anil Kanduri, Antonio Miele, Pasi Liljeberg, Zain Taufique","submitted_at":"2025-07-01T07:06:45Z","abstract_excerpt":"Compound AI (cAI) systems chain multiple AI models to solve complex problems. cAI systems are typically composed of deep neural networks (DNNs), transformers, and large language models (LLMs), exhibiting a high degree of computational diversity and dynamic workload variation. Deploying cAI services on mobile edge platforms poses a significant challenge in scheduling concurrent DNN-transformer inference tasks, which arrive dynamically in an unknown sequence. Existing mobile edge AI inference strategies manage multi-DNN or transformer-only workloads, relying on design-time profiling, and cannot "},"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":"2507.00491","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.MA","submitted_at":"2025-07-01T07:06:45Z","cross_cats_sorted":["cs.AI","cs.CV","cs.PF"],"title_canon_sha256":"23d8173b9fef12bdf8f01b74e3a71d02ad5552f0f0200df2bbccb07623947b90","abstract_canon_sha256":"3a1af6910577fc9dec16ee8de6798e758a64f1a7f3db1b9eb575e3b030fda369"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:09.878265Z","signature_b64":"YPYZMDnx+8/Ov89y8GxQg3RpjvAs69jSLiMxZKq0k1vcfiovFh7QtlfgQtwTyyA3InECekVPE9r7f5ejA8g1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18413f01d91c2fe7a3223ce1706bab5136c9c0203440b9db58b89646ef926f72","last_reissued_at":"2026-07-05T11:30:09.877850Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:09.877850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Twill: Scheduling Compound AI Systems on Heterogeneous Mobile Edge Platforms","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.PF"],"primary_cat":"cs.MA","authors_text":"Aman Vyas, Anil Kanduri, Antonio Miele, Pasi Liljeberg, Zain Taufique","submitted_at":"2025-07-01T07:06:45Z","abstract_excerpt":"Compound AI (cAI) systems chain multiple AI models to solve complex problems. cAI systems are typically composed of deep neural networks (DNNs), transformers, and large language models (LLMs), exhibiting a high degree of computational diversity and dynamic workload variation. Deploying cAI services on mobile edge platforms poses a significant challenge in scheduling concurrent DNN-transformer inference tasks, which arrive dynamically in an unknown sequence. Existing mobile edge AI inference strategies manage multi-DNN or transformer-only workloads, relying on design-time profiling, and cannot "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00491","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/2507.00491/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":"2507.00491","created_at":"2026-07-05T11:30:09.877904+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00491v1","created_at":"2026-07-05T11:30:09.877904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00491","created_at":"2026-07-05T11:30:09.877904+00:00"},{"alias_kind":"pith_short_12","alias_value":"DBAT6AOZDQX6","created_at":"2026-07-05T11:30:09.877904+00:00"},{"alias_kind":"pith_short_16","alias_value":"DBAT6AOZDQX6PIZC","created_at":"2026-07-05T11:30:09.877904+00:00"},{"alias_kind":"pith_short_8","alias_value":"DBAT6AOZ","created_at":"2026-07-05T11:30:09.877904+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/DBAT6AOZDQX6PIZCHTQXA25LKE","json":"https://pith.science/pith/DBAT6AOZDQX6PIZCHTQXA25LKE.json","graph_json":"https://pith.science/api/pith-number/DBAT6AOZDQX6PIZCHTQXA25LKE/graph.json","events_json":"https://pith.science/api/pith-number/DBAT6AOZDQX6PIZCHTQXA25LKE/events.json","paper":"https://pith.science/paper/DBAT6AOZ"},"agent_actions":{"view_html":"https://pith.science/pith/DBAT6AOZDQX6PIZCHTQXA25LKE","download_json":"https://pith.science/pith/DBAT6AOZDQX6PIZCHTQXA25LKE.json","view_paper":"https://pith.science/paper/DBAT6AOZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00491&json=true","fetch_graph":"https://pith.science/api/pith-number/DBAT6AOZDQX6PIZCHTQXA25LKE/graph.json","fetch_events":"https://pith.science/api/pith-number/DBAT6AOZDQX6PIZCHTQXA25LKE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DBAT6AOZDQX6PIZCHTQXA25LKE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DBAT6AOZDQX6PIZCHTQXA25LKE/action/storage_attestation","attest_author":"https://pith.science/pith/DBAT6AOZDQX6PIZCHTQXA25LKE/action/author_attestation","sign_citation":"https://pith.science/pith/DBAT6AOZDQX6PIZCHTQXA25LKE/action/citation_signature","submit_replication":"https://pith.science/pith/DBAT6AOZDQX6PIZCHTQXA25LKE/action/replication_record"}},"created_at":"2026-07-05T11:30:09.877904+00:00","updated_at":"2026-07-05T11:30:09.877904+00:00"}