{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DBBVW4S5FBH43NIRDC76QIVCIB","short_pith_number":"pith:DBBVW4S5","schema_version":"1.0","canonical_sha256":"18435b725d284fcdb51118bfe822a24072938cd4015723bbcda855c2b4b6c543","source":{"kind":"arxiv","id":"2407.05633","version":1},"attestation_state":"computed","paper":{"title":"AdaPI: Facilitating DNN Model Adaptivity for Efficient Private Inference in Edge Computing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Caiwen Ding, Jiahui Zhao, Tong Zhou, Wujie Wen, Xiaolin Xu, Xi Xie, Yukui Luo","submitted_at":"2024-07-08T05:58:49Z","abstract_excerpt":"Private inference (PI) has emerged as a promising solution to execute computations on encrypted data, safeguarding user privacy and model parameters in edge computing. However, existing PI methods are predominantly developed considering constant resource constraints, overlooking the varied and dynamic resource constraints in diverse edge devices, like energy budgets. Consequently, model providers have to design specialized models for different devices, where all of them have to be stored on the edge server, resulting in inefficient deployment. To fill this gap, this work presents AdaPI, a nove"},"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":"2407.05633","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-08T05:58:49Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"e4d92b4a3e0cbaf94b8448141a92b77b3f22164c3df68f19c11f148814170259","abstract_canon_sha256":"ec8fa5c5e5dd5e1bc3f34f6477844685e22b272e0ef27533cba7d9efb7835dcf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:16.463995Z","signature_b64":"zXcUd1k3RoriRHTdvvCN2GvIQtaTV8CRMPrHaa2zjjjMnbasxmxpAiilvPUIQnFclRbkaLBTRJwoIVB3OFNdCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18435b725d284fcdb51118bfe822a24072938cd4015723bbcda855c2b4b6c543","last_reissued_at":"2026-07-05T08:41:16.463583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:16.463583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaPI: Facilitating DNN Model Adaptivity for Efficient Private Inference in Edge Computing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Caiwen Ding, Jiahui Zhao, Tong Zhou, Wujie Wen, Xiaolin Xu, Xi Xie, Yukui Luo","submitted_at":"2024-07-08T05:58:49Z","abstract_excerpt":"Private inference (PI) has emerged as a promising solution to execute computations on encrypted data, safeguarding user privacy and model parameters in edge computing. However, existing PI methods are predominantly developed considering constant resource constraints, overlooking the varied and dynamic resource constraints in diverse edge devices, like energy budgets. Consequently, model providers have to design specialized models for different devices, where all of them have to be stored on the edge server, resulting in inefficient deployment. To fill this gap, this work presents AdaPI, a nove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05633","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/2407.05633/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":"2407.05633","created_at":"2026-07-05T08:41:16.463641+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.05633v1","created_at":"2026-07-05T08:41:16.463641+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05633","created_at":"2026-07-05T08:41:16.463641+00:00"},{"alias_kind":"pith_short_12","alias_value":"DBBVW4S5FBH4","created_at":"2026-07-05T08:41:16.463641+00:00"},{"alias_kind":"pith_short_16","alias_value":"DBBVW4S5FBH43NIR","created_at":"2026-07-05T08:41:16.463641+00:00"},{"alias_kind":"pith_short_8","alias_value":"DBBVW4S5","created_at":"2026-07-05T08:41:16.463641+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.03961","citing_title":"Electronic Health Records-Based Data-Driven Diabetes Knowledge Unveiling and Risk Prognosis","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DBBVW4S5FBH43NIRDC76QIVCIB","json":"https://pith.science/pith/DBBVW4S5FBH43NIRDC76QIVCIB.json","graph_json":"https://pith.science/api/pith-number/DBBVW4S5FBH43NIRDC76QIVCIB/graph.json","events_json":"https://pith.science/api/pith-number/DBBVW4S5FBH43NIRDC76QIVCIB/events.json","paper":"https://pith.science/paper/DBBVW4S5"},"agent_actions":{"view_html":"https://pith.science/pith/DBBVW4S5FBH43NIRDC76QIVCIB","download_json":"https://pith.science/pith/DBBVW4S5FBH43NIRDC76QIVCIB.json","view_paper":"https://pith.science/paper/DBBVW4S5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.05633&json=true","fetch_graph":"https://pith.science/api/pith-number/DBBVW4S5FBH43NIRDC76QIVCIB/graph.json","fetch_events":"https://pith.science/api/pith-number/DBBVW4S5FBH43NIRDC76QIVCIB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DBBVW4S5FBH43NIRDC76QIVCIB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DBBVW4S5FBH43NIRDC76QIVCIB/action/storage_attestation","attest_author":"https://pith.science/pith/DBBVW4S5FBH43NIRDC76QIVCIB/action/author_attestation","sign_citation":"https://pith.science/pith/DBBVW4S5FBH43NIRDC76QIVCIB/action/citation_signature","submit_replication":"https://pith.science/pith/DBBVW4S5FBH43NIRDC76QIVCIB/action/replication_record"}},"created_at":"2026-07-05T08:41:16.463641+00:00","updated_at":"2026-07-05T08:41:16.463641+00:00"}