{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MBTB6DEKLZ54MIUYNEWW45X3X7","short_pith_number":"pith:MBTB6DEK","schema_version":"1.0","canonical_sha256":"60661f0c8a5e7bc62298692d6e76fbbfe9d27871c26215ee13040b6bbd4fab1b","source":{"kind":"arxiv","id":"2505.12523","version":1},"attestation_state":"computed","paper":{"title":"Energy-Aware Deep Learning on Resource-Constrained Hardware","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.LG","authors_text":"Anil Madhavapeddy, Hamed Haddadi, Josh Millar","submitted_at":"2025-05-18T19:17:03Z","abstract_excerpt":"The use of deep learning (DL) on Internet of Things (IoT) and mobile devices offers numerous advantages over cloud-based processing. However, such devices face substantial energy constraints to prolong battery-life, or may even operate intermittently via energy-harvesting. Consequently, \\textit{energy-aware} approaches for optimizing DL inference and training on such resource-constrained devices have garnered recent interest. We present an overview of such approaches, outlining their methodologies, implications for energy consumption and system-level efficiency, and their limitations in terms "},"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":"2505.12523","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-18T19:17:03Z","cross_cats_sorted":["cs.AR"],"title_canon_sha256":"498002fd8cbcc1c6b9650fd78f5667604df43aa6b7ab1346e2f949e64d7031be","abstract_canon_sha256":"215ff78001967b9fac5e2d904024b6c505de12892d5286c44f94fa0664905f19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:05.702922Z","signature_b64":"eQGvB//CGw+KQ1SOBVmBXcT9wYgntdhql0IqG6ALTZphLO56vvhRtDgtNwOhVLPvRiABocTpGlic65WEAodSAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60661f0c8a5e7bc62298692d6e76fbbfe9d27871c26215ee13040b6bbd4fab1b","last_reissued_at":"2026-07-05T11:05:05.702500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:05.702500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Energy-Aware Deep Learning on Resource-Constrained Hardware","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.LG","authors_text":"Anil Madhavapeddy, Hamed Haddadi, Josh Millar","submitted_at":"2025-05-18T19:17:03Z","abstract_excerpt":"The use of deep learning (DL) on Internet of Things (IoT) and mobile devices offers numerous advantages over cloud-based processing. However, such devices face substantial energy constraints to prolong battery-life, or may even operate intermittently via energy-harvesting. Consequently, \\textit{energy-aware} approaches for optimizing DL inference and training on such resource-constrained devices have garnered recent interest. We present an overview of such approaches, outlining their methodologies, implications for energy consumption and system-level efficiency, and their limitations in terms "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12523","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/2505.12523/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":"2505.12523","created_at":"2026-07-05T11:05:05.702565+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12523v1","created_at":"2026-07-05T11:05:05.702565+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12523","created_at":"2026-07-05T11:05:05.702565+00:00"},{"alias_kind":"pith_short_12","alias_value":"MBTB6DEKLZ54","created_at":"2026-07-05T11:05:05.702565+00:00"},{"alias_kind":"pith_short_16","alias_value":"MBTB6DEKLZ54MIUY","created_at":"2026-07-05T11:05:05.702565+00:00"},{"alias_kind":"pith_short_8","alias_value":"MBTB6DEK","created_at":"2026-07-05T11:05:05.702565+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12806","citing_title":"Quantum Reservoir Computing for Short-Term Power Load Forecasting in Resource-Constrained Energy Systems","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MBTB6DEKLZ54MIUYNEWW45X3X7","json":"https://pith.science/pith/MBTB6DEKLZ54MIUYNEWW45X3X7.json","graph_json":"https://pith.science/api/pith-number/MBTB6DEKLZ54MIUYNEWW45X3X7/graph.json","events_json":"https://pith.science/api/pith-number/MBTB6DEKLZ54MIUYNEWW45X3X7/events.json","paper":"https://pith.science/paper/MBTB6DEK"},"agent_actions":{"view_html":"https://pith.science/pith/MBTB6DEKLZ54MIUYNEWW45X3X7","download_json":"https://pith.science/pith/MBTB6DEKLZ54MIUYNEWW45X3X7.json","view_paper":"https://pith.science/paper/MBTB6DEK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12523&json=true","fetch_graph":"https://pith.science/api/pith-number/MBTB6DEKLZ54MIUYNEWW45X3X7/graph.json","fetch_events":"https://pith.science/api/pith-number/MBTB6DEKLZ54MIUYNEWW45X3X7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MBTB6DEKLZ54MIUYNEWW45X3X7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MBTB6DEKLZ54MIUYNEWW45X3X7/action/storage_attestation","attest_author":"https://pith.science/pith/MBTB6DEKLZ54MIUYNEWW45X3X7/action/author_attestation","sign_citation":"https://pith.science/pith/MBTB6DEKLZ54MIUYNEWW45X3X7/action/citation_signature","submit_replication":"https://pith.science/pith/MBTB6DEKLZ54MIUYNEWW45X3X7/action/replication_record"}},"created_at":"2026-07-05T11:05:05.702565+00:00","updated_at":"2026-07-05T11:05:05.702565+00:00"}