{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EPJWWRRLEX44KU6YN2B5PBRDLF","short_pith_number":"pith:EPJWWRRL","schema_version":"1.0","canonical_sha256":"23d36b462b25f9c553d86e83d78623595273973a80c97832edf086b87d201f18","source":{"kind":"arxiv","id":"2210.02620","version":1},"attestation_state":"computed","paper":{"title":"Inference Latency Prediction at the Edge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.PF","authors_text":"Leana Golubchik, Marco Paolieri, Zhuojin Li","submitted_at":"2022-10-06T00:46:06Z","abstract_excerpt":"With the growing workload of inference tasks on mobile devices, state-of-the-art neural architectures (NAs) are typically designed through Neural Architecture Search (NAS) to identify NAs with good tradeoffs between accuracy and efficiency (e.g., latency). Since measuring the latency of a huge set of candidate architectures during NAS is not scalable, approaches are needed for predicting end-to-end inference latency on mobile devices. Such predictions are challenging due to hardware heterogeneity, optimizations applied by ML frameworks, and the diversity of neural architectures. Motivated by t"},"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":"2210.02620","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.PF","submitted_at":"2022-10-06T00:46:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5865913b735aefe24021af255f8a3d3be6ebfea0c047e9e148e94833eef04591","abstract_canon_sha256":"ef1cb878e220e9dc303dcbf87cfa3b40540cc89058ad7bdd73d6911f3c3c7e5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:54.766007Z","signature_b64":"84r54C0Lafk+wOEOLr6lxTpZJKrH9eF8blBxlkvp/xOJQpZK9uqnM4dHYMGR4MUOEUUycxilMIsPc2qYib/cAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23d36b462b25f9c553d86e83d78623595273973a80c97832edf086b87d201f18","last_reissued_at":"2026-07-05T05:03:54.765591Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:54.765591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inference Latency Prediction at the Edge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.PF","authors_text":"Leana Golubchik, Marco Paolieri, Zhuojin Li","submitted_at":"2022-10-06T00:46:06Z","abstract_excerpt":"With the growing workload of inference tasks on mobile devices, state-of-the-art neural architectures (NAs) are typically designed through Neural Architecture Search (NAS) to identify NAs with good tradeoffs between accuracy and efficiency (e.g., latency). Since measuring the latency of a huge set of candidate architectures during NAS is not scalable, approaches are needed for predicting end-to-end inference latency on mobile devices. Such predictions are challenging due to hardware heterogeneity, optimizations applied by ML frameworks, and the diversity of neural architectures. Motivated by t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.02620","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/2210.02620/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":"2210.02620","created_at":"2026-07-05T05:03:54.765652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.02620v1","created_at":"2026-07-05T05:03:54.765652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.02620","created_at":"2026-07-05T05:03:54.765652+00:00"},{"alias_kind":"pith_short_12","alias_value":"EPJWWRRLEX44","created_at":"2026-07-05T05:03:54.765652+00:00"},{"alias_kind":"pith_short_16","alias_value":"EPJWWRRLEX44KU6Y","created_at":"2026-07-05T05:03:54.765652+00:00"},{"alias_kind":"pith_short_8","alias_value":"EPJWWRRL","created_at":"2026-07-05T05:03:54.765652+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.01505","citing_title":"ESM: A Framework for Building Effective Surrogate Models for Hardware-Aware Neural Architecture Search","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EPJWWRRLEX44KU6YN2B5PBRDLF","json":"https://pith.science/pith/EPJWWRRLEX44KU6YN2B5PBRDLF.json","graph_json":"https://pith.science/api/pith-number/EPJWWRRLEX44KU6YN2B5PBRDLF/graph.json","events_json":"https://pith.science/api/pith-number/EPJWWRRLEX44KU6YN2B5PBRDLF/events.json","paper":"https://pith.science/paper/EPJWWRRL"},"agent_actions":{"view_html":"https://pith.science/pith/EPJWWRRLEX44KU6YN2B5PBRDLF","download_json":"https://pith.science/pith/EPJWWRRLEX44KU6YN2B5PBRDLF.json","view_paper":"https://pith.science/paper/EPJWWRRL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.02620&json=true","fetch_graph":"https://pith.science/api/pith-number/EPJWWRRLEX44KU6YN2B5PBRDLF/graph.json","fetch_events":"https://pith.science/api/pith-number/EPJWWRRLEX44KU6YN2B5PBRDLF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EPJWWRRLEX44KU6YN2B5PBRDLF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EPJWWRRLEX44KU6YN2B5PBRDLF/action/storage_attestation","attest_author":"https://pith.science/pith/EPJWWRRLEX44KU6YN2B5PBRDLF/action/author_attestation","sign_citation":"https://pith.science/pith/EPJWWRRLEX44KU6YN2B5PBRDLF/action/citation_signature","submit_replication":"https://pith.science/pith/EPJWWRRLEX44KU6YN2B5PBRDLF/action/replication_record"}},"created_at":"2026-07-05T05:03:54.765652+00:00","updated_at":"2026-07-05T05:03:54.765652+00:00"}