{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:KTQCM7TXIUODE6KSTKGQ3DFWXZ","short_pith_number":"pith:KTQCM7TX","schema_version":"1.0","canonical_sha256":"54e0267e77451c3279529a8d0d8cb6be525a2e2e7e6b6ba69076dadeaf30cd13","source":{"kind":"arxiv","id":"1703.02952","version":7},"attestation_state":"computed","paper":{"title":"A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analytics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Ali Shahin Shamsabadi, Ali Taheri, Hamed Haddadi, Hamid R. Rabiee, Kleomenis Katevas, Nicholas D. Lane, Seyed Ali Osia, Sina Sajadmanesh","submitted_at":"2017-03-08T18:21:03Z","abstract_excerpt":"Internet of Things (IoT) devices and applications are being deployed in our homes and workplaces. These devices often rely on continuous data collection to feed machine learning models. However, this approach introduces several privacy and efficiency challenges, as the service operator can perform unwanted inferences on the available data. Recently, advances in edge processing have paved the way for more efficient, and private, data processing at the source for simple tasks and lighter models, though they remain a challenge for larger, and more complicated models. In this paper, we present a h"},"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":"1703.02952","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-08T18:21:03Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"c88831fbbb9b4073c3f6d94f195ff716d83be1124270570c4a513d16e64a4f88","abstract_canon_sha256":"69159fc70af859aba5da0ea6e3f0140a780121df9146c2813fda985056f05804"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:08:08.588355Z","signature_b64":"+uAka2jg9Wxpum/xm/g2JM3ZbxK45wvlHtzkMSjcdKGpKwY+JRu/p0aB7Mt48nQ6uubIZXmKvcPfZIOQEmsOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54e0267e77451c3279529a8d0d8cb6be525a2e2e7e6b6ba69076dadeaf30cd13","last_reissued_at":"2026-07-05T01:08:08.587867Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:08:08.587867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analytics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Ali Shahin Shamsabadi, Ali Taheri, Hamed Haddadi, Hamid R. Rabiee, Kleomenis Katevas, Nicholas D. Lane, Seyed Ali Osia, Sina Sajadmanesh","submitted_at":"2017-03-08T18:21:03Z","abstract_excerpt":"Internet of Things (IoT) devices and applications are being deployed in our homes and workplaces. These devices often rely on continuous data collection to feed machine learning models. However, this approach introduces several privacy and efficiency challenges, as the service operator can perform unwanted inferences on the available data. Recently, advances in edge processing have paved the way for more efficient, and private, data processing at the source for simple tasks and lighter models, though they remain a challenge for larger, and more complicated models. In this paper, we present a h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.02952","kind":"arxiv","version":7},"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/1703.02952/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":"1703.02952","created_at":"2026-07-05T01:08:08.587922+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.02952v7","created_at":"2026-07-05T01:08:08.587922+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.02952","created_at":"2026-07-05T01:08:08.587922+00:00"},{"alias_kind":"pith_short_12","alias_value":"KTQCM7TXIUOD","created_at":"2026-07-05T01:08:08.587922+00:00"},{"alias_kind":"pith_short_16","alias_value":"KTQCM7TXIUODE6KS","created_at":"2026-07-05T01:08:08.587922+00:00"},{"alias_kind":"pith_short_8","alias_value":"KTQCM7TX","created_at":"2026-07-05T01:08:08.587922+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1907.06034","citing_title":"Towards Characterizing and Limiting Information Exposure in DNN Layers","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KTQCM7TXIUODE6KSTKGQ3DFWXZ","json":"https://pith.science/pith/KTQCM7TXIUODE6KSTKGQ3DFWXZ.json","graph_json":"https://pith.science/api/pith-number/KTQCM7TXIUODE6KSTKGQ3DFWXZ/graph.json","events_json":"https://pith.science/api/pith-number/KTQCM7TXIUODE6KSTKGQ3DFWXZ/events.json","paper":"https://pith.science/paper/KTQCM7TX"},"agent_actions":{"view_html":"https://pith.science/pith/KTQCM7TXIUODE6KSTKGQ3DFWXZ","download_json":"https://pith.science/pith/KTQCM7TXIUODE6KSTKGQ3DFWXZ.json","view_paper":"https://pith.science/paper/KTQCM7TX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.02952&json=true","fetch_graph":"https://pith.science/api/pith-number/KTQCM7TXIUODE6KSTKGQ3DFWXZ/graph.json","fetch_events":"https://pith.science/api/pith-number/KTQCM7TXIUODE6KSTKGQ3DFWXZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KTQCM7TXIUODE6KSTKGQ3DFWXZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KTQCM7TXIUODE6KSTKGQ3DFWXZ/action/storage_attestation","attest_author":"https://pith.science/pith/KTQCM7TXIUODE6KSTKGQ3DFWXZ/action/author_attestation","sign_citation":"https://pith.science/pith/KTQCM7TXIUODE6KSTKGQ3DFWXZ/action/citation_signature","submit_replication":"https://pith.science/pith/KTQCM7TXIUODE6KSTKGQ3DFWXZ/action/replication_record"}},"created_at":"2026-07-05T01:08:08.587922+00:00","updated_at":"2026-07-05T01:08:08.587922+00:00"}