{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ITME25MHRM3BEQ6Q7GU6KTFICI","short_pith_number":"pith:ITME25MH","schema_version":"1.0","canonical_sha256":"44d84d75878b361243d0f9a9e54ca81209e44f2bb9ae7ae5865fba40a5d5a7dd","source":{"kind":"arxiv","id":"1710.03368","version":1},"attestation_state":"computed","paper":{"title":"Energy-efficient Amortized Inference with Cascaded Deep Classifiers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jian Peng, Jiaqi Guan, Qiang Liu, Yang Liu","submitted_at":"2017-10-10T01:14:54Z","abstract_excerpt":"Deep neural networks have been remarkable successful in various AI tasks but often cast high computation and energy cost for energy-constrained applications such as mobile sensing. We address this problem by proposing a novel framework that optimizes the prediction accuracy and energy cost simultaneously, thus enabling effective cost-accuracy trade-off at test time. In our framework, each data instance is pushed into a cascade of deep neural networks with increasing sizes, and a selection module is used to sequentially determine when a sufficiently accurate classifier can be used for this data"},"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":"1710.03368","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-10-10T01:14:54Z","cross_cats_sorted":[],"title_canon_sha256":"a435f677616c30eedb6278303485a78b4e548c1a3aa273f174bb433f2e1dd825","abstract_canon_sha256":"03def1a726be07b45e44814d81b83305ebbd6d2e1891b5381e9b4b9493139e72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:12.219845Z","signature_b64":"6GZJLGD5SyXHCR2BSalUmChThns3gfLJg9+b/jN3It7jsGQzSpVZl39xEx9XPhvODHlyhH3P2ya0V7hiWkxDAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44d84d75878b361243d0f9a9e54ca81209e44f2bb9ae7ae5865fba40a5d5a7dd","last_reissued_at":"2026-05-18T00:33:12.219169Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:12.219169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Energy-efficient Amortized Inference with Cascaded Deep Classifiers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jian Peng, Jiaqi Guan, Qiang Liu, Yang Liu","submitted_at":"2017-10-10T01:14:54Z","abstract_excerpt":"Deep neural networks have been remarkable successful in various AI tasks but often cast high computation and energy cost for energy-constrained applications such as mobile sensing. We address this problem by proposing a novel framework that optimizes the prediction accuracy and energy cost simultaneously, thus enabling effective cost-accuracy trade-off at test time. In our framework, each data instance is pushed into a cascade of deep neural networks with increasing sizes, and a selection module is used to sequentially determine when a sufficiently accurate classifier can be used for this data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.03368","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":""},"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":"1710.03368","created_at":"2026-05-18T00:33:12.219282+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.03368v1","created_at":"2026-05-18T00:33:12.219282+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.03368","created_at":"2026-05-18T00:33:12.219282+00:00"},{"alias_kind":"pith_short_12","alias_value":"ITME25MHRM3B","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"ITME25MHRM3BEQ6Q","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"ITME25MH","created_at":"2026-05-18T12:31:21.493067+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/ITME25MHRM3BEQ6Q7GU6KTFICI","json":"https://pith.science/pith/ITME25MHRM3BEQ6Q7GU6KTFICI.json","graph_json":"https://pith.science/api/pith-number/ITME25MHRM3BEQ6Q7GU6KTFICI/graph.json","events_json":"https://pith.science/api/pith-number/ITME25MHRM3BEQ6Q7GU6KTFICI/events.json","paper":"https://pith.science/paper/ITME25MH"},"agent_actions":{"view_html":"https://pith.science/pith/ITME25MHRM3BEQ6Q7GU6KTFICI","download_json":"https://pith.science/pith/ITME25MHRM3BEQ6Q7GU6KTFICI.json","view_paper":"https://pith.science/paper/ITME25MH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.03368&json=true","fetch_graph":"https://pith.science/api/pith-number/ITME25MHRM3BEQ6Q7GU6KTFICI/graph.json","fetch_events":"https://pith.science/api/pith-number/ITME25MHRM3BEQ6Q7GU6KTFICI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ITME25MHRM3BEQ6Q7GU6KTFICI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ITME25MHRM3BEQ6Q7GU6KTFICI/action/storage_attestation","attest_author":"https://pith.science/pith/ITME25MHRM3BEQ6Q7GU6KTFICI/action/author_attestation","sign_citation":"https://pith.science/pith/ITME25MHRM3BEQ6Q7GU6KTFICI/action/citation_signature","submit_replication":"https://pith.science/pith/ITME25MHRM3BEQ6Q7GU6KTFICI/action/replication_record"}},"created_at":"2026-05-18T00:33:12.219282+00:00","updated_at":"2026-05-18T00:33:12.219282+00:00"}