{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NNNJD5R5O3JKQCX4VEFI6QK7WP","short_pith_number":"pith:NNNJD5R5","schema_version":"1.0","canonical_sha256":"6b5a91f63d76d2a80afca90a8f415fb3ccf9c049ab148ac874d99c000f70b8a0","source":{"kind":"arxiv","id":"2108.11898","version":3},"attestation_state":"computed","paper":{"title":"Supervised Compression for Resource-Constrained Edge Computing Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Marco Levorato, Ruihan Yang, Stephan Mandt, Yoshitomo Matsubara","submitted_at":"2021-08-21T11:10:29Z","abstract_excerpt":"There has been much interest in deploying deep learning algorithms on low-powered devices, including smartphones, drones, and medical sensors. However, full-scale deep neural networks are often too resource-intensive in terms of energy and storage. As a result, the bulk part of the machine learning operation is therefore often carried out on an edge server, where the data is compressed and transmitted. However, compressing data (such as images) leads to transmitting information irrelevant to the supervised task. Another popular approach is to split the deep network between the device and the s"},"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":"2108.11898","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-21T11:10:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"814e1939d678f1e7f89acf262b4f471f6ff977390017e9c92d2515133cf6059a","abstract_canon_sha256":"6c2cb357154139fbf3ca86117183d096943b37674d5911c7ef3eb6142b22c249"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:58:27.996045Z","signature_b64":"KGBJLrjb7flDJmpTT8byhZMyvP/Kczx++tjQqx7XQ4fBjZD0LOB1+rayA3OQDjcvqM03nyT0Z44Ql3tuhf5FBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b5a91f63d76d2a80afca90a8f415fb3ccf9c049ab148ac874d99c000f70b8a0","last_reissued_at":"2026-07-05T04:58:27.995641Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:58:27.995641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Supervised Compression for Resource-Constrained Edge Computing Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Marco Levorato, Ruihan Yang, Stephan Mandt, Yoshitomo Matsubara","submitted_at":"2021-08-21T11:10:29Z","abstract_excerpt":"There has been much interest in deploying deep learning algorithms on low-powered devices, including smartphones, drones, and medical sensors. However, full-scale deep neural networks are often too resource-intensive in terms of energy and storage. As a result, the bulk part of the machine learning operation is therefore often carried out on an edge server, where the data is compressed and transmitted. However, compressing data (such as images) leads to transmitting information irrelevant to the supervised task. Another popular approach is to split the deep network between the device and the s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.11898","kind":"arxiv","version":3},"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/2108.11898/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":"2108.11898","created_at":"2026-07-05T04:58:27.995702+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.11898v3","created_at":"2026-07-05T04:58:27.995702+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.11898","created_at":"2026-07-05T04:58:27.995702+00:00"},{"alias_kind":"pith_short_12","alias_value":"NNNJD5R5O3JK","created_at":"2026-07-05T04:58:27.995702+00:00"},{"alias_kind":"pith_short_16","alias_value":"NNNJD5R5O3JKQCX4","created_at":"2026-07-05T04:58:27.995702+00:00"},{"alias_kind":"pith_short_8","alias_value":"NNNJD5R5","created_at":"2026-07-05T04:58:27.995702+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/NNNJD5R5O3JKQCX4VEFI6QK7WP","json":"https://pith.science/pith/NNNJD5R5O3JKQCX4VEFI6QK7WP.json","graph_json":"https://pith.science/api/pith-number/NNNJD5R5O3JKQCX4VEFI6QK7WP/graph.json","events_json":"https://pith.science/api/pith-number/NNNJD5R5O3JKQCX4VEFI6QK7WP/events.json","paper":"https://pith.science/paper/NNNJD5R5"},"agent_actions":{"view_html":"https://pith.science/pith/NNNJD5R5O3JKQCX4VEFI6QK7WP","download_json":"https://pith.science/pith/NNNJD5R5O3JKQCX4VEFI6QK7WP.json","view_paper":"https://pith.science/paper/NNNJD5R5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.11898&json=true","fetch_graph":"https://pith.science/api/pith-number/NNNJD5R5O3JKQCX4VEFI6QK7WP/graph.json","fetch_events":"https://pith.science/api/pith-number/NNNJD5R5O3JKQCX4VEFI6QK7WP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NNNJD5R5O3JKQCX4VEFI6QK7WP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NNNJD5R5O3JKQCX4VEFI6QK7WP/action/storage_attestation","attest_author":"https://pith.science/pith/NNNJD5R5O3JKQCX4VEFI6QK7WP/action/author_attestation","sign_citation":"https://pith.science/pith/NNNJD5R5O3JKQCX4VEFI6QK7WP/action/citation_signature","submit_replication":"https://pith.science/pith/NNNJD5R5O3JKQCX4VEFI6QK7WP/action/replication_record"}},"created_at":"2026-07-05T04:58:27.995702+00:00","updated_at":"2026-07-05T04:58:27.995702+00:00"}