{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HNGH74XWXD5OLYUK5AMLS7VL72","short_pith_number":"pith:HNGH74XW","schema_version":"1.0","canonical_sha256":"3b4c7ff2f6b8fae5e28ae818b97eabfea1316d225af91c4f85168d3418fa6622","source":{"kind":"arxiv","id":"2108.09457","version":1},"attestation_state":"computed","paper":{"title":"DeepEdgeBench: Benchmarking Deep Neural Networks on Edge Devices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.AI","authors_text":"Anshul Jindal, Michael Gerndt, Mohak Chadha, Stephan Patrick Baller","submitted_at":"2021-08-21T08:13:22Z","abstract_excerpt":"EdgeAI (Edge computing based Artificial Intelligence) has been most actively researched for the last few years to handle variety of massively distributed AI applications to meet up the strict latency requirements. Meanwhile, many companies have released edge devices with smaller form factors (low power consumption and limited resources) like the popular Raspberry Pi and Nvidia's Jetson Nano for acting as compute nodes at the edge computing environments. Although the edge devices are limited in terms of computing power and hardware resources, they are powered by accelerators to enhance their pe"},"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":"2108.09457","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-08-21T08:13:22Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"77c12809b43582c332a37b3d3a58ef8130132b4739277f1d18453f5c483264a3","abstract_canon_sha256":"8635def417b78f28b3f8e325b0c3e60d0550578ac6176ccb312a17c2f752e159"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:07:54.516495Z","signature_b64":"QC9tycyvKWi7CYKIrEkMUTXdJjA2KCWtpB8dMO1LMWn0XtHIaMjdwPhQickHQChqV6DHcX6TjM2q0RMK9vm1AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b4c7ff2f6b8fae5e28ae818b97eabfea1316d225af91c4f85168d3418fa6622","last_reissued_at":"2026-07-05T03:07:54.516039Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:07:54.516039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepEdgeBench: Benchmarking Deep Neural Networks on Edge Devices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.AI","authors_text":"Anshul Jindal, Michael Gerndt, Mohak Chadha, Stephan Patrick Baller","submitted_at":"2021-08-21T08:13:22Z","abstract_excerpt":"EdgeAI (Edge computing based Artificial Intelligence) has been most actively researched for the last few years to handle variety of massively distributed AI applications to meet up the strict latency requirements. Meanwhile, many companies have released edge devices with smaller form factors (low power consumption and limited resources) like the popular Raspberry Pi and Nvidia's Jetson Nano for acting as compute nodes at the edge computing environments. Although the edge devices are limited in terms of computing power and hardware resources, they are powered by accelerators to enhance their pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.09457","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/2108.09457/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":"2108.09457","created_at":"2026-07-05T03:07:54.516097+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.09457v1","created_at":"2026-07-05T03:07:54.516097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.09457","created_at":"2026-07-05T03:07:54.516097+00:00"},{"alias_kind":"pith_short_12","alias_value":"HNGH74XWXD5O","created_at":"2026-07-05T03:07:54.516097+00:00"},{"alias_kind":"pith_short_16","alias_value":"HNGH74XWXD5OLYUK","created_at":"2026-07-05T03:07:54.516097+00:00"},{"alias_kind":"pith_short_8","alias_value":"HNGH74XW","created_at":"2026-07-05T03:07:54.516097+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.26119","citing_title":"Edge AI Deployment Beyond Models: A BSP-Aware Systems Framework for Industrial Embedded Platforms","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2606.09175","citing_title":"CANS: Accelerating Multiuser Collaborative Edge Inference via Cooperative Autodidactic NeuroSurgeon","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HNGH74XWXD5OLYUK5AMLS7VL72","json":"https://pith.science/pith/HNGH74XWXD5OLYUK5AMLS7VL72.json","graph_json":"https://pith.science/api/pith-number/HNGH74XWXD5OLYUK5AMLS7VL72/graph.json","events_json":"https://pith.science/api/pith-number/HNGH74XWXD5OLYUK5AMLS7VL72/events.json","paper":"https://pith.science/paper/HNGH74XW"},"agent_actions":{"view_html":"https://pith.science/pith/HNGH74XWXD5OLYUK5AMLS7VL72","download_json":"https://pith.science/pith/HNGH74XWXD5OLYUK5AMLS7VL72.json","view_paper":"https://pith.science/paper/HNGH74XW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.09457&json=true","fetch_graph":"https://pith.science/api/pith-number/HNGH74XWXD5OLYUK5AMLS7VL72/graph.json","fetch_events":"https://pith.science/api/pith-number/HNGH74XWXD5OLYUK5AMLS7VL72/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HNGH74XWXD5OLYUK5AMLS7VL72/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HNGH74XWXD5OLYUK5AMLS7VL72/action/storage_attestation","attest_author":"https://pith.science/pith/HNGH74XWXD5OLYUK5AMLS7VL72/action/author_attestation","sign_citation":"https://pith.science/pith/HNGH74XWXD5OLYUK5AMLS7VL72/action/citation_signature","submit_replication":"https://pith.science/pith/HNGH74XWXD5OLYUK5AMLS7VL72/action/replication_record"}},"created_at":"2026-07-05T03:07:54.516097+00:00","updated_at":"2026-07-05T03:07:54.516097+00:00"}